AI Coding Plan

Coding Plan

Kimi

Kimi Membership | Kimi Code

• Tiers (RMB/month): Andante 49, Moderato 99, Allegretto 199, Allegro 699
• Subscription renewal: due to tight compute resources, priority is given to currently subscribed users; renewal was available until 2026-08-20 00:00, after which direct purchase is no longer available
• Kimi Code is now powered by the flagship K3.1 Pro series (3T-class parameters, up to 1M context, with marked gains over K3 in coding, 3D creation, financial research and long-horizon agent tasks), offering a standard-speed and a high-speed choice depending on how much a task values quality versus speed; it is compatible with mainstream agent tools including Kimi Code CLI, Claude Code and VS Code
• Model IDs and membership tier requirements (6 in total, usable over both the OpenAI-compatible and Anthropic-compatible protocols): k3.1-pro, k3 and k3-256k require Moderato / Plus or above, with 1M context requiring Allegretto / Pro or above; k3.1-pro supports thinking mode only, defaults to max, and rejects requests with thinking disabled; k3.1-pro-highspeed (output roughly 2–3× faster than k3.1-pro, drawing about 2× the allowance, up to 1M context) requires Allegretto / Pro or above; kimi-for-coding (K2.8 Preview) requires Andante / Plus or above; kimi-for-coding-highspeed (K2.7 Code HighSpeed) requires Allegretto / Pro or above
• API endpoints are split into domestic and overseas: OpenAI-compatible (both the Chat Completions and the Responses protocols; the documented Responses endpoint is the domestic https://api.kimi.com/coding/v1/responses) — domestic https://api.kimi.com/coding/v1, overseas https://api.kimi.ai/coding/v1; Anthropic-compatible — domestic https://api.kimi.com/coding/, overseas https://api.kimi.ai/coding/; Kimi Open Platform — domestic https://api.moonshot.cn/v1, overseas https://api.moonshot.ai/v1
• API pricing (RMB per 1M tokens):
  • K3: cached input 2, uncached input 20, output 100, 1M context
  • K2.7-Code: cached input 1.3, uncached input 6.5, output 27, 256K context
  • K2.7-Code-HighSpeed: cached input 2.6, uncached input 13.0, output 54, 256K context

MiniMax

MiniMax M Plan | FAQ | International

• M Plan is MiniMax's individual AI subscription and replaces the former Token Plan (Token Plan is no longer sold). Monthly list price: Go ¥49 / $22, Explore ¥119 / $55, Build ¥469 / $132; annual billing costs 10 months (2 months free); the first month is 50% off during the launch (through 2026-10-14)
• Included models: all tiers include the text model MiniMax-M3.1-Flash (natively multimodal, 1M context, tunable thinking depth), image and audio generation, web search and multimodal understanding; Explore and Build additionally include the H3 video model (Go excludes video); music and similar resources are not included
• Usage (relative to Go): Explore is 3x; Build is 12x in the Chinese-site docs but 7.5x in the international docs (the two sites disagree); text/image/audio and other non-video models are subject to 5-hour and weekly windows, while video models are subject only to the weekly window
• Credit packs: 1,000 credits = ¥7 (international $1), valid for 1 year from purchase; plan quota is used before credit packs
• The text model's official name is MiniMax-M3.1-Flash (released 2026-10-19; the international site calls it an open-weight model for everyday work): the former MiniMax-M3.1-Flash-Preview has been retired and requests using the old name are served by MiniMax-M3.1-Flash; the models overview, the M Plan overview and subscription pricing pages and the FAQ now all write the text model as M3.1 Flash and no longer label it as available only through M Plan and MiniMax Code
• Retirement schedule: the MiniMax M2.5 and M2.7 families stopped being available to new users on 2026-10-19 and are retired on 2026-11-18, with existing pay-as-you-go API users able to keep calling them until the retirement date; M Plan and Token Plan requests to M2.5 and M2.7 are routed to M3.1 Flash (the original model names are kept as compatible entry points, so no model names need changing and plan usage entitlements are unchanged). M2.7, M2.7-highspeed, M2.5, M2.5-highspeed, M2.1, M2.1-highspeed and MiniMax-M2 have been removed from the language-model table in the models overview and from the language-model price table on the pay-as-you-go page, leaving only M3.1-Flash and M3 as language models
• The M Plan API key (formerly the "Subscription Key") works with any tool that speaks the OpenAI- or Anthropic-compatible protocol (the docs list Claude Code, Codex, Cursor, OpenCode, Pi, Hermes Agent and OpenClaw); using MiniMax Code requires no separate subscription or M Plan API key; tiers cannot be downgraded — monthly plans can be upgraded to a higher monthly or annual tier, and annual plans only to a higher annual tier; once auto-renewal is turned off it cannot be restored (buy again; value remaining before expiry can be credited toward an upgrade)
• Existing Token Plan subscribers: with auto-renewal on, the current plan and benefits stay unchanged (retaining historical perks such as unlimited quotas and the 150% weekly quota), and you can upgrade to M Plan at any time (the unused portion is prorated and credited); upgrade mapping: Plus → Go/Explore/Build, Max → Explore/Build, Ultra → Build; after upgrading you cannot return to Token Plan
• Legacy Token Plan migration: in China, Max-hs ¥199 → Max ¥119 (fee down ¥80 plus ~¥160 of credits granted monthly) and Ultra-hs ¥899 → Ultra ¥469 (down ¥430 plus ~¥860 of credits granted monthly), with Starter ¥29 and Plus-hs ¥98 retained for existing subscribers only; internationally, Max-hs $80 → Max and Ultra-hs $150 → Ultra (each down \(30 plus ~\)60 of credits granted monthly), with Starter $10 and Plus-hs $40 retained; annual plans of retired tiers receive equivalent credits monthly (each grant valid for 1 year, non-rolling)
• Legacy benefits: benefits for users who subscribed before 2026-06-05 are retained; compensation credits are valid for 1 year; entitlement bonuses remain valid only during continuous subscription periods and are waived when changing tiers or cancelling
• MiniMax API pricing (RMB per 1M tokens):
  • MiniMax-M3.1-Flash: cached input 0.10, uncached input 1.00, output 4.00 (international $0.015 / $0.15 / $0.60)
  • MiniMax-M3 <= 512K input tokens: cached input 0.42, uncached input 2.10, output 8.40
  • MiniMax-M3 > 512K input tokens: cached input 0.84, uncached input 4.20, output 16.80
  • M3 effective unit prices are unchanged, but the "permanent 50% off" label and struck-through list prices are back: ≤512K input tokens list prices 4.20 / 16.80 / 0.84 (input / output / cached input) and >512K 8.40 / 33.60 / 1.68, halved to the values above; the international site carries the same label — ≤512K $0.30 / $1.20 / $0.06 and >512K $0.60 / $2.40 / $0.12 against struck-through list prices of $0.60 / $2.40 / $0.12 and $1.20 / $4.80 / $0.24
  • 1M context

Zhipu (GLM, Z.ai)

Zhipu GLM Coding Plan

• Lite Plan (118 RMB/month): 2,000 points per 5 hours, 10,000 points per week
• Pro Plan (538 RMB/month): 12,000 points per 5 hours, 60,000 points per week
• Max Plan (1078 RMB/month): 28,000 points per 5 hours, 140,000 points per week
• Point refresh rules: the 5-hour points refresh dynamically (the allowance resets 5 hours after consumption) and the weekly points refresh on a 7-day cycle starting from the time the plan was purchased; after a subscriber upgrades, the points allowance refreshes immediately to the new tier, whereas renewal does not trigger a points reset and the existing refresh cycle is unchanged
• Model points consumed = (input tokens × Input coefficient + cached input tokens × Cached Input coefficient + output tokens × Output coefficient) / 10,000
• MCP points consumed = number of calls × Output coefficient
• All plans support GLM-5.3 and GLM-5.3-Flash; requests for the previous models GLM-5.2/GLM-5.1 are automatically routed to GLM-5.3, and requests for GLM-5-Turbo/GLM-4.7 are automatically routed to GLM-5.3-Flash
• Off-peak hours consume points at 50% of the base rate; peak hours are weekdays 14:00–18:00 (UTC+8)
• Limited-time campaigns (both ended): the "GLM-5.3-Flash Usage Campaign" (2026-09-03 to 2026-10-07, daily 23:00–09:00, unlimited GLM-5.3-Flash usage via ZCode and AutoClaw plus doubled quota on other agents) and the "Double Festival" campaign (2026-09-25 to 2026-10-07, all-day usage charged at the off-peak rate) expired on 2026-10-07; as of 2026-10-09 no limited-time campaign is running on either site
• Coefficients: GLM-5.3 — Input 6.9 / Cached Input 1.7 / Output 24; GLM-5.3-Flash (including the visual understanding MCP) — Input 2.3 / Cached Input 0.56 / Output 8
• Token usage varies with the cache hit rate:

Cache Hit Rate	Model	Lite (M Tokens/week)	Pro (M Tokens/week)	Max (M Tokens/week)
95%	GLM-5.3	0.48～0.97	2.90～5.80	6.76～13.52
95%	GLM-5.3-Flash	1.46～2.92	8.77～17.55	20.47～40.95
96%	GLM-5.3	0.50～0.99	2.97～5.95	6.94～13.87
96%	GLM-5.3-Flash	1.50～3.00	9.00～18.01	21.01～42.02
98%	GLM-5.3	0.52～1.04	3.13～6.27	7.31～14.63
98%	GLM-5.3-Flash	1.58～3.17	9.50～19.00	22.17～44.33

Range explanation: maximum tokens assumes all usage in off-peak hours at 0.5× points; minimum tokens assumes all usage in peak hours at 1×. By fully utilizing the off-peak discount, you can save up to 92% compared with pay-as-you-go calls to the GLM-5.3 standard API - API pricing (RMB per 1M tokens): - GLM-5.3: cached input 2, uncached input 8, output 28, 1M context - GLM-5.3-Flash: cached input 0.23, uncached input 0.8, output 2.8, 1M context - GLM-5.3-FlashX: natively multimodal (input modalities cover images, video, files and text), cached input 0.57, uncached input 2, output 7, 1M context - GLM-5.2: cached input 2, uncached input 8, output 28, 1M context - GLM-5.1: cached input 1.3/2, uncached input 6/8, output 24/28, 200K context - GLM-5-Turbo: cached input 1.2/1.8, uncached input 5/7, output 22/26, 200K context - GLM-4.7: cached input 0.4/0.6/0.8, uncached input 2/3/4, output 8/14/16, 200K context

Zhipu GLM Coding Plan Team Edition

• Team Standard (598 RMB/month): maximum 60M tokens per seat per 5 hours, maximum 300M tokens per seat per week
• Team Advanced (1198 RMB/month): maximum 160M tokens per seat per 5 hours, maximum 800M tokens per seat per week
• "Maximum" refers to the total tokens that can actually be consumed at a 1× consumption coefficient; current per-model consumption rules:
  • GLM-4.7, GLM-4.5-Air: consume at 1× all day
  • GLM-5.2, GLM-5-Turbo: 3× during peak hours and 2× during off-peak hours; as a limited-time benefit, off-peak hours consume only 1×
  • Peak hours are 14:00–18:00 (UTC+8) daily

Zhipu International GLM Coding Plan: all plans support GLM-5.3 and GLM-5.3-Flash; requests for GLM-5.2/GLM-5.1 auto-route to GLM-5.3, and GLM-4.7 auto-routes to GLM-5.3-Flash

Cloud Providers

• Volcano Engine Coding Plan (Personal Edition) | Documentation
  • Lite Plan (40 RMB/month): maximum ~1,200 requests per 5 hours, ~9,000 per week, ~18,000 per subscription month
  • Pro Plan (200 RMB/month): 5x the Lite Plan quota
  • Supported models: Doubao-Seed-2.1-pro, Doubao-Seed-2.1-lite, Doubao-Seed-2.0-mini, Doubao-Seed-Evolving, MiniMax-M3 (being retired), Kimi-K2.7-Code (being retired), Kimi-K2.8-Preview, Kimi-K3 (high deduction coefficient, recommended only for Pro plan users), Kimi-K3.1-Pro, GLM-5.3, GLM-5.3-Flash, DeepSeek-V4-Flash, DeepSeek-V4-Pro, DeepSeek-V4.1-Flash, DeepSeek-V4.1-Flash-Economy
  • 1M-context support: doubao-seed-evolving, glm-5.3, glm-5.3-flash, kimi-k3.1-pro, kimi-k3, kimi-k2.8-preview, deepseek-v4.1-flash, deepseek-v4.1-flash-economy, deepseek-v4-flash, deepseek-v4-pro
  • Limited-time promotions: deepseek-v4.1-flash deduction coefficient at 50% off (2026-09-23 00:00 to 2026-12-30 23:59:59), deepseek-v4.1-flash-economy deduction coefficient at 50% off (2026-10-20 00:00 to 2026-12-30 23:59:59); Kimi-K2.8-Preview quota campaign (2026-09-18 00:00 to 2026-12-14 23:59:59, comparable to the Agent Plan 40%-off promotion period); Kimi-K3.1-Pro quota campaign (2026-10-24 00:00 to 2026-11-09 23:59:59, comparable to the Agent Plan 50%-off promotion period)
  • Key model specs: Doubao-Seed-2.1-pro (new-generation flagship, 1024k context / 256k output), Doubao-Seed-2.1-lite (lightweight and efficient, 1024k/256k), Doubao-Seed-2.0-mini (fast responses, 256k/128k), DeepSeek-V4.1-Flash (552B total-parameter MoE, native multimodal vision understanding, 1024k/384k), DeepSeek-V4.1-Flash-Economy (identical model weights to DeepSeek-V4.1-Flash with the same capability and results, lower price and slightly slower generation, multimodal input, 1024k/384k), Kimi-K2.8-Preview (close to K3 with higher thinking efficiency, 1M/1M, text and image input), Kimi-K3.1-Pro (Moonshot's flagship model for enterprise-grade long-horizon tasks and agentic coding, supporting deep thinking, function calling and context caching with 5-minute and 1-hour cache writes, 1024k context / 1024k output), GLM-5.3-Flash (Zhipu's first natively multimodal model, 320B total params / 18B active, 1M/128K)
• Volcano Engine Agent Plan (Personal Edition)
  • Agent Fuel Points (AFP) are the unified billing unit: text/embedding models = (input token × input coefficient + output token × output coefficient) / 10,000; video models = tokens / 10,000 × coefficient; image models = number of successfully generated images × coefficient. Coefficients are determined solely by the model and do not vary with input length
  • Deduction coefficients per model (input/output identical): doubao-seed-2.0-mini 0.25 (without audio input) / 2.5 (with audio input); deepseek-v4-flash 0.5; doubao-seed-2.1-lite 0.5 (4.5 with audio input); glm-5.3-flash 0.5; doubao-seed-evolving, minimax-m3 (being retired), doubao-seed-2.1-pro 2.5; deepseek-v4.1-flash 2.5 (1.25 at a limited-time 50% off, 2026-09-15 00:00 to 2026-12-30 23:59:59); deepseek-v4.1-flash-economy 2 (1 at a limited-time 50% off, 2026-10-20 00:00 to 2026-12-30 23:59:59); kimi-k2.7-code (being retired) 4.5; kimi-k2.8-preview 8 (4.8 at a limited-time 40% off, 2026-09-17 00:00 to 2026-12-14 23:59:59); glm-5.3 (glm-latest) 4.5; deepseek-v4-pro 5.5; kimi-k3 10 (5 at a limited-time 50% off, 2026-10-12 00:00 to 2026-10-25 23:59); kimi-k3.1-pro 7 (3.5 at a limited-time 50% off, 2026-10-24 00:00 to 2026-11-09 23:59:59); doubao-embedding-vision 0.5
  • Tiers (AFP, per 5 hours / week / month / day): Small 40 RMB/month (2000/7000/20000/10000), Medium 200 (10000/35000/100000/50000), Large 500 (25000/87500/250000/125000), Max 1000 (50000/175000/500000/250000)
  • Image, video and speech models and Harness have no 5-hour or weekly limits; they are subject only to the daily and monthly limits, with the daily limit equal to half the monthly limit
  • All plans support: doubao-seed-2.1-pro, doubao-seed-2.1-lite, doubao-seed-2.0-mini, deepseek-v4-flash, deepseek-v3.2, minimax-m3 (being retired), glm-5.3, glm-5.3-flash, kimi-k2.7-code (being retired), kimi-k2.8-preview, kimi-k3.1-pro, deepseek-v4-pro, deepseek-v4.1-flash, deepseek-v4.1-flash-economy, doubao-embedding-vision, doubao-seedream-5-0-pro, doubao-seedream-5.0-flash (image generation, 60 AFP per output image with input images not counted), doubao-seed-tts-2.0, doubao-seed-asr-2.0
  • Medium and above additionally support: doubao-seedance-2.0, doubao-seedance-2.0-fast, doubao-seedance-2.0-mini, doubao-seedance-2.5
  • Agent Evolution: first 50 files free
• Alibaba Cloud Bailian Token Plan (Personal Edition)
  • Lite (60, 39 for a limited time), Essential (120, 79), Standard (180, 139), Pro (600, 499) RMB/month, corresponding to 11,500 / 25,500 / 45,000 / 180,000 Credits per month; Usage Pack (100 RMB/month) = 20,000 Credits, purchasable only with an active subscription, up to 5 held at a time (100,000 Credits in total), with pack credits not counted towards the plan's monthly quota
  • Since 2026-09-22 the fixed 7-day window quota has been abolished in favour of a subscription-month quota (from 2026-10-14 the official wording is "the quota is counted by subscription month", resetting based on the subscription date rather than a fixed calendar date); service is paused once the plan quota is used up and no Usage Pack credits remain, and unused quota does not roll over
  • Deduction order: each request is deducted first from the current subscription month's plan quota, and once exhausted from the Usage Pack quota
  • Upgrades: the current subscription cycle is not reset; the price difference is paid for the remaining days and the new quota is granted for the current cycle, with the new tier's monthly quota applying from the next subscription month
  • Essential supports 2–3 concurrent agents and carries all Lite benefits
  • For the subscriber's own use only: the same API Key may be configured on several of the subscriber's own devices (such as a home computer and an office computer); sharing it with others may be judged a violation and lead to a ban
  • Supported models: auto, qwen3.8-max, qwen3.8-flash, qwen3.7-max, qwen3.7-plus, qwen3.6-flash, qwen-image-3.0-pro, qwen-audio-3.0-tts-plus, qwen-audio-3.0-realtime-plus, qwen-audio-3.0-asr-flash, wan2.7-image, wan2.7-image-pro, wan3.0-video, deepseek-v4.1-flash, deepseek-v4.1-flash-1017, deepseek-v4-pro, deepseek-v4-pro-0813, deepseek-v4-flash-0731, glm-5.3, glm-5.2, happyhorse-1.1-i2v, happyhorse-1.1-t2v, happyhorse-1.1-r2v, decision-model-preview
  • Limited-time night discount (22:00–08:00 daily): 40% off Credits for qwen3.8-max and qwen3.8-flash; 50% off for deepseek-v4-pro-0813, deepseek-v4-flash-0731, deepseek-v4.1-flash and deepseek-v4.1-flash-1017
  • decision-model-preview (domain model – decision model) is free for a limited time and consumes no Credits
• Alibaba Cloud Bailian Token Plan (Team Edition)
  • Standard Seat ¥198/seat/month (25,000 Credits), Advanced Seat ¥698 (100,000), Premium Seat ¥1,398 (250,000); Shared Usage Pack ¥5,000/pack (625,000 Credits)
  • Credits consumed per request are dynamically determined by model type, token usage, reasoning mode and tool calls; for example, with Qwen3.6-plus every 5,000 uncached input tokens, every 50,000 cached input tokens or every 5,000/6 output tokens equals one Credit
  • API price per Credit (implicit caching): 0.01–0.02 RMB within 256K context, 0.04–0.08 RMB for 256K–1M
  • Supported models: auto, qwen3.8-max, qwen3.8-flash, qwen3.7-max, qwen3.7-plus, qwen3.6-plus, qwen3.6-flash, qwen-image-2.0, qwen-image-2.0-pro, qwen-image-3.0-pro, qwen-audio-3.0-tts-plus, qwen-audio-3.0-realtime-plus, qwen-audio-3.0-asr-flash, wan2.7-image, wan2.7-image-pro, deepseek-v4.1-flash, deepseek-v4.1-flash-1017, deepseek-v4-pro, deepseek-v4-pro-0813, deepseek-v4-flash-0731, kimi-k2.7-code, kimi-k2.6, kimi-k2.5, glm-5.3, glm-5.2, glm-5.1, glm-5, MiniMax-M2.5, happyhorse-1.1-i2v, happyhorse-1.1-t2v, happyhorse-1.1-r2v
• Tencent Cloud LLM Token Plan
  • Enterprise Professional Plan: 1 RMB/100 Credits, minimum purchase 50K Credits (500 RMB/month); Light Enjoyment Plan: 2 RMB per million tokens
  • Enterprise supported models (varies slightly by region): Auto, Hy4 preview, GLM-5.3, GLM-5.3-Flash, GLM-5.2, Kimi K2.7 Code, Kimi K2.7 Code HighSpeed, Kimi K3, Kimi-K2.6, MiniMax-M2.7 (retiring 2026-11-17), MiniMax-M3, DeepSeek-V4-Pro, DeepSeek-V4-Flash 0731 Official (retiring 2026-10-31), DeepSeek-V4-Pro 0813 Official, DeepSeek-V4.1-Flash (not Official direct-supply), DeepSeek-V4.1-Flash-1017 (not Official direct-supply), DeepSeek-V4.1-Flash-1017 Official direct-supply, DeepSeek-V4-Flash 0731 Official direct-supply, DeepSeek-V4-Pro 0813 Official direct-supply, DeepSeek-V4-Flash-Vision-Exp Official direct-supply, MiMo-V2.6-Pro, MiMo-V2.6-Flash
  • Peak-valley billing: for DeepSeek models, peak hours are weekdays (Mon–Fri) 9:00–12:00 and 14:00–18:00 with all other times off-peak; weekends are billed at off-peak rates all day
  • Credit prices (credits per 1M tokens): DeepSeek-V4.1-Flash and DeepSeek-V4.1-Flash-1017 (both including their Official direct-supply versions) cached 2 / uncached 100 / output 400 (off-peak), 4 / 200 / 800 (peak); Hy4 preview 30 / 600 / 1800; MiMo-V2.6-Pro 2.5/300/600 in Guangzhou and 2.59/313.05/626.1 in Singapore; MiMo-V2.6-Flash 2/100/200 in Guangzhou and 2.02/100.75/201.5 in Singapore
  • Personal Hy Token Plan: Lite 28 RMB/month (560 credits), Standard 78 (1,560), Pro 238 (4,760), Max 468 (9,360); supports Hy3 and Hy4 preview
  • Personal Universal Token Plan: Lite 39 (780 credits), Standard 99 (1,980), Pro 299 (5,980), Max 599 (11,980); supports Auto, DeepSeek-V4.1-Flash-1017 Official direct-supply, DeepSeek-V4-Flash Official direct-supply, DeepSeek-V4-Pro Official direct-supply, MiniMax-M2.7 (retiring 2026-11-17), MiniMax-M3, GLM-5.2, GLM-5.3, GLM-5.3-Flash, Kimi K2.7 Code, Kimi K3, Hy4 preview, MiMo-V2.6-Flash
• Baidu Qianfan Token Plan (Personal Edition) | Personal Edition Documentation | Enterprise Edition Documentation
  • Mini 9.9 RMB/month (10M tokens), Lite 40 (42M), Pro 200 (230M), Max 600 (700M)
  • Supported models: DeepSeek-V4-Pro, DeepSeek-V4-Flash, GLM-5.2, GLM-5.1, Kimi-K2.6, ERNIE 5.1
• Baidu Qianfan Coding Plan
  • Coding Plan Lite at 40 RMB/month: up to ~1,200 requests per 5 hours, ~9,000 per week, ~18,000 per subscription month; Coding Plan Pro at 200 RMB/month: 6,000 / 45,000 / 90,000
  • Supported models and deduction coefficients: DeepSeek-V4-Pro (peak 5 / off-peak 4), GLM-5.1 (peak 4 / off-peak 3), Baidu Search (10); peak hours are generally 10:30-12:00 and 14:00-18:00 daily (varies with traffic)
  • Official notice: "the supported model range will be adjusted dynamically with model iterations. Coding Plan has stopped model updates; users who need newer models are advised to migrate to Token Plan (Personal Edition)". This update reduced the model library to the two language models above (the Model Names that can be set in the config file likewise dropped to deepseek-v4-pro and glm-5.1), removing Kimi-K2.5, DeepSeek-V3.2, DeepSeek-V4-Flash, GLM-5, MiniMax-M2.5 and ERNIE-4.5-Turbo-20260402
• JD Cloud Coding Plan
  • Lite Plan (19.9 first purchase, 40 renewal, RMB/month): maximum 1,200 requests per 5 hours, 9,000 per week, 18,000 per subscription month
  • Pro Plan (99.9 first purchase, 200 renewal, RMB/month): maximum 6,000 requests per 5 hours, 45,000 per week, 90,000 per subscription month
  • Supported models: DeepSeek-V3.2, GLM-5, GLM-4.7, MiniMax-M2.5, Kimi-K2.5, Kimi-K2-Turbo, Qwen3-Coder
• iFlytek Astron Token Plan Team Edition | Subscription
  • Standard Member 200 RMB/seat/month (20,000 Credits, 2M TPM), Advanced Member 600 (60,000 Credits, 3M TPM), Premium Member 1200 (200,000 Credits, 5M TPM)
  • Supported models: Spark-X2.5, Spark-X2-Flash, GLM-5.2, GLM-5.1, GLM-5, DeepSeek-V4-Pro, DeepSeek-V4-Flash, DeepSeek-V3.2, Kimi-K2.6, Kimi-K2.5, MiniMax-M2.5, Qwen3.5-397B-A17B, Qwen3.6-35B-A3B, Qwen3.5-35B-A3B, Qwen3-Coder-Next-FP8, GLM-4.7-Flash
• iFlytek Astron Coding Plan | Subscription
  • Professional (39 RMB/month): ~1,200 requests per 5 hours, ~9,000 per week, ~18,000 per subscription month; supports Spark-X2-Agent, Spark-X2, Auto, GLM-5.1, GLM-5, MiniMax-M2.5, Kimi-K2.6, Kimi-K2.5, DeepSeek-V3.2, Spark-X2-Flash, Qwen3.6-35B-A3B, GLM-4.7-Flash, Qwen3.5-35B-A3B, Qwen3-Coder-Next-FP8, Qwen3.5-397B-A17B
  • Efficient (199 RMB/month): ~6,000 requests per 5 hours, ~45,000 per week, ~90,000 per subscription month; supports Spark-X2-Agent, Spark-X2, Auto, GLM-5, GLM-5.2, DeepSeek-V4-Pro, DeepSeek-V4-Flash, MiniMax-M2.5, Kimi-K2.6, Kimi-K2.5, DeepSeek-V3.2, Spark-X2-Flash, Qwen3.6-35B-A3B, GLM-4.7-Flash, Qwen3.5-35B-A3B, Qwen3-Coder-Next-FP8, Qwen3.5-397B-A17B
• CTCloud Programming Token Plan (Credits Edition)
  • 29 (3,000 credits), 89 (10,000), 199 (25,000), 399 (50,000), 699 (100,000) RMB/month
  • Supported models: DeepSeek-V4-Pro, DeepSeek-V4-Flash-0731, GLM-5.2, GLM-5.1, Kimi-K2.6, MiniMax-M3
  • Credit-to-token conversion (tokens per credit, input/output): DeepSeek-V4-Pro 1,111/370; DeepSeek-V4-Flash 3,333/1,111; GLM-5.2 1,250/357; GLM-5.1 input [0,32k] 1,667 (output 417), (32k,200k] 1,250 (output 357); Kimi-K2.6 1,538/370; MiniMax-M3 input [0,512k] 4,762 (output 1,190), (512k,1M] 2,381 (output 595)
  • The previous token-metered plans allow renewals by existing subscribers only; since 2026-10-10 they support DeepSeek-V4-Flash-0731, GLM-5.1 and GLM-5.2 (GLM-5.0 and DeepSeek-V3.2 were removed as previously announced)
• Huawei Cloud MaaS Token Plan
  • Lite 59 RMB/month (50M tokens per subscription month), Standard 149 (130M), Pro 399 (380M), Max 799 (880M)
  • Supported models: GLM-5, GLM-5.1, Kimi-K2.6, DeepSeek-V3.2, DeepSeek-V4-Flash

Others

• StepFun Step Plan | Pricing and billing
  • Mini 49 RMB/month (400M Credits), Plus 99 (1600M), Pro 199 (8000M), Max 699 (40000M); quarterly 129 / 269 / 539 / 1889 and yearly 456 / 936 / 1860 / 6666 RMB (quarterly and yearly are paid upfront while Credits are still issued monthly, in 3 and 12 instalments)
  • Time-of-day deduction: calling step-5-preview costs twice the Credits during peak hours (Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time) as during off-peak hours, which cover all other times and are deducted at the regular rate; some legacy subscriptions are exempt from the rule
  • Booster packs (open to subscribers only, valid 30 days and counted separately from the subscription period): Small 49 RMB / 400M Credits, Large 99 RMB / 1600M Credits; when both subscription Credits and booster-pack Credits are held, the balance that expires first is deducted first
  • Supported models: step-5-preview (next-generation flagship base model), step-3.7-flash, step-3.5-flash-2603, step-3.5-flash, stepaudio-2.5-realtime, stepaudio-2.5-chat, stepaudio-2.5-tts, stepaudio-2.5-asr, step-router-v1 (intelligent routing between deepseek-v4-pro and step-3.5-flash)
• Xiaomi MiMo Token Plan (Personal Edition)
  • Lite (39 RMB or 6 USD/month): 4.1B Credits per month; Standard (99 RMB or 16 USD): 11B; Pro (329 RMB or 50 USD): 38B; Max (659 RMB or 100 USD): 82B
  • Supported models (6): MiMo-V2.6-Pro, MiMo-V2.6-Flash, MiMo-V2.5-ASR, MiMo-V2.5-TTS-VoiceClone, MiMo-V2.5-TTS-VoiceDesign, MiMo-V2.5-TTS
  • mimo-v2.5-pro and mimo-v2.5 were retired at 10:00 Beijing time on 2026-10-21, leaving MiMo-V2.6-Pro and MiMo-V2.6-Flash as the only language models; the Credit-consumption rows for the two retired models (V2.5-Pro 2.5 / 300 / 600 and V2.5 2 / 100 / 200 Credits per token) were dropped with them
  • Discounts: 88% off first purchase, 88% off annual auto-renewal, 0.8× consumption at night (0:00–8:00)
• OpenCode Go
  • The docs publish token prices, monthly allowances, estimated requests (5 hours/week/month), per-request token estimates and data retention for all 30 models
  • Three plans: Go (\(10/month)**, **Go Plus (\)40/month) and Go Teams ($20/member/month); token prices are identical across all three, Go Plus only raises the per-model usage limits (monthly allowances are 2–8x those of Go, mostly 4x), and Go Teams gives every member their own limits, $5/month higher than Go on every model
  • Go and Go Plus are for workspaces with a single member (such as the Personal workspace created at sign-up), and either can upgrade to Go Teams at any time with the unused part of the month's allowance credited; Go Teams covers every member of a multi-member workspace at $20 per member per month, a member who joins mid-period is charged $20 and gets a full monthly allowance, service accounts are not covered, and Go Teams starts with Extra Usage on (falling back to the Console balance once the limits are reached), which can be turned off or on again on the Go page
  • Usage limits are defined per model as a monthly amount: 5 hours = 20% of the monthly limit, week = 50%, month = 100%; on Go Teams each member's monthly limit is the same-tier Go allowance plus $5, and their 5-hour and weekly limits are likewise derived from that higher allowance; each response reports how much the request counted via the opencode.allowance field
  • Endpoints: OpenAI-compatible https://opencode.ai/inference/go/openai/v1/{chat/completions,responses}, Anthropic-compatible https://opencode.ai/inference/go/anthropic/v1/messages and Google-compatible https://opencode.ai/inference/go/google/v1beta/models/<model-id> (Gemini 4 Argon); reference models inside OpenCode as opencode-go/<model-id> (e.g. opencode-go/kimi-k3), and list them via https://opencode.ai/inference/go/v1/models
  • Monthly usage allowances (Go / Go Plus; Go Teams is the same-tier Go allowance +$5): $15 / $60 — GLM-5.3, Kimi K3.1 Pro, Kimi K3, MiMo-V2.6-Pro, MiMo-V2.5-Pro, Qwen3.8 Max, DeepSeek V4 Pro, Grok 4.7, GPT 6 Luna, GPT 5.6 Luna, Claude Haiku 5.5; $30 / $90 — Qwen3.8 Flash; $30 / $120 — Hy4 preview and Gemini 4 Argon (token prices at a limited-time 50% off); $60 / $120 — MiMo-V2.6-Flash, MiMo-V2.5, Muse Spark 1.3 Contributor, Muse Spark 1.2 Contributor; $60 / $180 — GLM-5.3-Flash, GLM-5.2, Kimi K2.7 Code, MiniMax M3, Qwen3.7 Plus; $60 / $240 — LongCat-2.0, Hy3; $100 / \(200 — DeepSeek V4.1 Flash (\)105 on Go Teams; estimated 5-hour requests 43,330 on Go and 108,330 on Go Plus); $20 / $80 — MiniMax M3.1 Flash; $15 / $60 — Step 5 Preview; unlimited for a limited time — Beam Free and Iceman Contributor Free
  • Token prices (identical on Go, Go Plus and Go Teams, per 1M tokens: input / output / cache read / cache write): GLM-5.3-Flash 0.15 / 0.50 / 0.03; GLM-5.3, GLM-5.2 1.40 / 4.40 / 0.26; Kimi K3.1 Pro 2.00 / 10.00 / 0.20 / 2.00; Kimi K3 3.00 / 15.00 / 0.30; Kimi K2.7 Code 0.95 / 4.00 / 0.19; LongCat-2.0 0.30 / 1.20 / 0.006; MiMo-V2.6-Flash, MiMo-V2.5 0.14 / 0.28 / 0.0028; MiMo-V2.6-Pro, MiMo-V2.5-Pro 0.435 / 0.87 / 0.003625; MiniMax M3 (≤512K tokens) 0.30 / 1.20 / 0.06, (>512K tokens) 0.60 / 2.40 / 0.12; Muse Spark 1.3 Contributor, Muse Spark 1.2 Contributor 0.10 / 0.20 / 0.002; Qwen3.8 Max 2.00 / 6.00 / 0.25 / 2.50; Qwen3.8 Flash 0.15 / 0.47 / 0.016 / 0.20; Qwen3.7 Plus (≤256K tokens) 0.40 / 1.60 / 0.04 / 0.50, (>256K tokens) 1.20 / 4.80 / 0.12 / 1.50; DeepSeek V4.1 Flash (off-peak) 0.15 / 0.60 / 0.003, (peak) 0.30 / 1.20 / 0.006; DeepSeek V4 Pro (off-peak) 0.66 / 1.98 / 0.022, (peak) 1.32 / 3.96 / 0.044 (peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday); Hy4 preview 0.834 / 2.501 / 0.042; Hy3 0.14 / 0.58 / 0.035; MiniMax M3.1 Flash 0.15 / 0.60 / 0.015; Step 5 Preview 1.00 / 2.70 / 0.10; Grok 4.7 (≤200K tokens) 2.00 / 6.00 / 0.50, (>200K tokens) 4.00 / 12.00 / 1.00; GPT 6 Luna (≤272K tokens) 0.10 / 0.50 / 0.01 / 0.125, (>272K tokens) 0.20 / 0.75 / 0.02 / 0.25; GPT 5.6 Luna (≤272K tokens) 0.20 / 1.20 / 0.02 / 0.25, (>272K tokens) 0.40 / 1.80 / 0.04 / 0.50; Claude Haiku 5.5 (≤100K tokens) 0.10 / 0.50 / 0.01 / 0.125, (>100K tokens) 0.50 / 2.50 / 0.05 / 0.625; Gemini 4 Argon 2.00 / 10.00 / 0.10 (was 4.00 / 20.00 / 0.20 at list price; 50% off through 2026-11-30)
  • Client requirement: requests must carry the session header x-opencode-session for routing and prompt-cache optimisation; the docs list validated clients (Hermes, Claude Code, Codex, ZCode, Pi, jcode, Kilo Code CLI) and known problematic clients (DeepSeek Harness, GitHub Copilot Chat, Kimi Code, MiMo Code)
  • Restricted models are governed by workspace privacy settings: paid endpoints that train on request data are blocked by default and the allowed region is Europe & United States, while workspaces without saved privacy settings also allow Global for requests from China; an owner or admin enables DeepSeek V4.1 Flash and V4 Pro by selecting Global under Regions in Settings › Privacy, and Muse Spark 1.3 Contributor and Muse Spark 1.2 Contributor by turning on "Allow paid endpoints that train on request data"; Gemini 4 Argon does not train on request data and retains none of it (0 days), so the switch does not apply; Iceman Contributor Free is free for a limited time in exchange for permission to use prompts and completions to improve the model, and its data retention is listed as Not ZDR
  • Supported models: Grok 4.7, GLM-5.3/5.3-Flash/5.2, GPT 6 Luna, GPT 5.6 Luna, Claude Haiku 5.5, Gemini 4 Argon, Kimi K3.1 Pro/K3/K2.7 Code, LongCat-2.0, MiMo-V2.6-Flash/V2.6-Pro/V2.5/V2.5-Pro, MiniMax M3, Muse Spark 1.3 Contributor, Muse Spark 1.2 Contributor, Qwen3.8 Max/Qwen3.8 Flash/Qwen3.7 Plus, DeepSeek V4.1 Flash/V4 Pro, Hy4 preview, Hy3, MiniMax M3.1 Flash, Step 5 Preview, Beam Free (limited-time free, limited regions), Iceman Contributor Free (limited-time free)
  • Kimi K3.1 Pro: 1M context, model ID kimi-k3.1-pro, OpenAI-compatible endpoint https://opencode.ai/inference/go/openai/v1/chat/completions (@ai-sdk/openai-compatible), estimated requests 147 per 5 hours, 368 per week and 735 per month on Go and 588 / 1,471 / 2,941 on Go Plus, with about 1,050 input, 76,500 cached input and 300 output tokens per request
  • Two models added on 2026-10-08: Claude Haiku 5.5 — tiered at 100K tokens, ≤100K tokens input $0.10 / output $0.50 / cache read $0.01 / cache write $0.125 and >100K tokens input $0.50 / output $2.50 / cache read $0.05 / cache write $0.625 per 1M tokens, monthly usage allowance $15 on Go and $60 on Go Plus, estimated request limits 3,850 / 5 hours, 9,620 / week and 19,230 / month on Go and 15,380 / 38,460 / 76,920 on Go Plus, model ID claude-haiku-5-5, endpoint https://opencode.ai/zen/go/v1/messages (@ai-sdk/anthropic); Step 5 Preview Free — input/output/cache read all free with unlimited requests and monthly allowance (limited-time), model ID step-5-preview-free, endpoint https://opencode.ai/zen/go/v1/chat/completions
  • 2026-10-14 model-library change (33 → 32 models): DeepSeek V4 Flash and DeepSeek V4 Flash Vision Exp were removed (their rows disappear from the token-price table, both monthly-allowance tables, the estimated-request table, the endpoint table and the privacy table, their two lines are dropped from the per-request token estimates, and the DeepSeek peak/off-peak note changes from "DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp" to "DeepSeek V4.1 Flash / V4 Pro"), and Gemini 4 Argon Contributor was added — token prices input $4.00 / output $20.00 / cache read \(0.20 per 1M tokens (no cache-write price), monthly allowance Go ~~\)30~~ **\(60** and Go Plus ~~\)120~~ $240 (both marked "2x · Limited time", i.e. a limited-time doubling), estimated requests 440 per 5 hours, 1,080 per week and 2,120 per month on Go and 1,760 / 4,320 / 8,480 on Go Plus, model ID gemini-4-argon-contributor, endpoint https://opencode.ai/inference/go/v1/models/gemini-4-argon-contributor (@ai-sdk/google, the only model in the doc using the /v1/models/<model-id> form), and a privacy row of Model training Yes with Data retention Not ZDR plus the note "Your prompts and completions may be used to train future Google models." No other model's price, allowance or request limit changed
• StepFun International Coding Plan
• SenseTime SenseNova TokenPlan
  • Credit pools (public-beta entitlements): the general pool caps at 120,000 credits per rolling 5-hour window and 1,200,000 credits per rolling week (raised from 60,000 / 600,000 on 2026-10-27); the Flash-Lite pool stays at 60,000 credits per rolling 5-hour window and 600,000 per rolling week
  • Deduction order: Flash-Lite draws on the Flash-Lite pool first and then on the general pool (Flash-Lite stays usable while general credits remain); every other model only draws on the general pool
  • The Flash-Lite spend rebate ended on 2026-10-27: while it ran, each credit of Flash-Lite pool consumption rebated 1 general credit (aggregated per calendar day, settled hourly, each rebate valid 30 days from arrival, not counted against either rolling window). Rebate credits already credited keep their balance and expiry, and consumption counted before the switch is still settled under the old rules
  • When the increase takes effect, every account's available general credits are reset to the new window caps; the available Flash-Lite credits are unchanged
  • Supported models (7): SenseNova 6.8 Flash Lite, SenseNova U1.5 Lite, SenseNova U1.5 Fast, DeepSeek V4 Flash, DeepSeek V4.1 Flash, GLM-5.2, Kimi K3
• UniAI GLM-5 Coding Plan
• Moorethreads AI Coding Plan
• KwaiKAT Coding Plan
• Command Code
  • Plans (all "+ processing fee"; credits are a per-model shared pool and model token prices match the upstream official prices — the vendor calls it zero markup):
    • Go: $1/month with $10 in credits (10x), roughly 9K requests; from 2026-09-28 new subscribers receive per-model credits instead of a flat $10 pool (each model's monthly usage is worth \(6–\)10), while existing subscribers keep the flat $10 pool for the current cycle and switch over automatically at renewal
    • GOAT: $10/month with up to $100 in credits (up to 10x, which the vendor calls the highest multiplier of any $10 coding plan) — even more with deals; roughly 75K requests; includes API access; usage limits are up to $20 per 5 hours, $50 per week and $100 per month
    • Pro: $20/month with up to $110 in credits across 45+ models — everything in GOAT plus closed premium models such as Claude, GPT and Gemini; usage limits are up to $22 per 5 hours, $55 per week and $110 per month; $120+ in potential value when model deals are active
    • Max: $100/month with $150 in credits (up to $300 equivalent with deals), roughly 219K requests; includes open and premium models, API access, higher rate limits and priority support
    • Provider (API plan): $15/month plus processing fee, pay-as-you-go at zero markup with OpenAI- and Anthropic-compatible endpoints; topped-up credits roll over and never expire
  • Limited-time free models: Laguna S 2.1, Glyph Cluster and Beam 1.0 (on every tier — Go, GOAT, Pro, Max 10x and Max 20x), plus Ling 3.1 Flash 1019 (1M context; input, output and cache read all Free through 16:00 UTC on 2026-11-03). The free variants of MiniMax M3.1 Flash and Ornith 1.5 122B have been removed from every plan's model table; only the paid variants remain
  • Model counts: 97 models in all — Go lists 58, GOAT 71 and Pro 87
  • Supported models (partial): taste-1 (the vendor's own model), DeepSeek V4.1 Flash, DeepSeek V4.1 Flash Fast, GLM-5.3 FlashX, GLM-5.2, Qwen 3.8 Omni Flash, Qwen 3.8 27B, Qwen 3.8 Max Prime, Qwen 3.7 Max, Qwen 3.7 Plus, Tencent Hy3, MiMo V2.6 Flash / Pro / Pro UltraSpeed, Grok 4.7, Step 5 Preview, Muse Spark 1.3 Contributor, Muse Spark Open, GPT-6 Luna, GPT-6 Sol, GPT-6.1 Terra (1.1M context, Pro only), Claude Haiku 5.5, Claude Sonnet 5.5, Gemini 4 Argon, Mistral Large 4, Jev (a decision model usable only headless via cmd -p and the Provider API), Jev 1.14.0 (a decision model with 32K context, likewise usable only headless via cmd -p and the Provider API), Ling 3.1, Nemotron, Nemotron 3.5 Super VL, MiniMax M3.1 Flash, Ornith 1.5 122B, Beam 1.0 (limited-time free, 1M context), Inkling and others
  • Monthly credits per plan (per-model, from the docs pages' Monthly credits tables, in USD): Ling 3.1 Flash Go $6 / GOAT $100 / Pro $110; DeepSeek V4.1 Flash Go $10 / GOAT $100 / Pro $110; GLM-5.3 Flash Go $10 / GOAT $100 / Pro $110; DeepSeek V4.1 Flash Fast Go $6 / GOAT $60 / Pro $70; Qwen 3.7 Max Go $10 / GOAT $33 / Pro $43; GPT-5.6 Sol GOAT $20 / Pro $30; Muse Spark 1.3 Contributor Go $6 / GOAT $20 / Pro $30; Muse Spark Open and Nemotron 3.5 Super VL Go $6 / GOAT $20 / Pro $30 each; Jev 1.14.0 GOAT $20 / Pro $30; Qwen 3.8 Max Prime GOAT $20 / Pro $30; MiniMax M3.1 Flash Go $6 / GOAT $20 / Pro $30; Ornith 1.5 122B Go $6 / GOAT $20 / Pro $30; Kimi K3.1 Pro Go $6 / GOAT $20 / Pro $30; GPT-6.1 Terra Pro $20
  • MiniMax M3.1 Flash token prices (per 1M tokens: input / output / cache read): $0.15 / $0.60 / $0.015 with 1M context
  • Ornith 1.5 122B token prices (per 1M tokens: input / output / cache read): $0.16 / $0.64 / $0.02 with 262K context; estimated requests are 1,430 per 5 hours, 2,870 per week and 4,780 per month on Go, 3,180 / 7,960 / 15,900 on GOAT and 4,780 / 11,900 / 23,900 on Pro
  • Kimi K3.1 Pro token prices (per 1M tokens: input / output / cache read): $2.00 / $10.00 / $0.20 with 1M context; estimated requests are 132 per 5 hours, 265 per week and 441 per month on Go, 294 / 735 / 1,470 on GOAT and 441 / 1,100 / 2,210 on Pro
  • GPT-6.1 Terra token prices (per 1M tokens: input / output / cache read / cache write): $1.00 / $5.00 / $0.05 / $1.25 with 1.1M context, offered on Pro only; monthly credits are Pro $20 and estimated requests are 976 per 5 hours, 2,440 per week and 4,880 per month
  • DeepSeek V4.1 Flash follows the official peak/off-peak pricing: off-peak 0.15 / 0.60 / 0.003 and peak 0.30 / 1.20 / 0.006 (per 1M tokens: input / output / cache read; peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday)
  • Zero data retention (ZDR) is available on every model and is enforced with CMD_ZDR=1 (e.g. CMD_ZDR=1 cmd); models where ZDR is included carry no extra cost, while on the rest ZDR requests meter at the plan's default usage (Go: $6) even when the model carries a boosted figure
• DeepSeek API Pricing:
  • Peak-valley pricing: off-peak prices are half of peak; peak hours are Monday to Friday 9:00-12:00 and 14:00-18:00 Beijing time
  • deepseek-flash (DeepSeek-V4.1-Flash-1017, 1M context, supports image understanding): off-peak cached input 0.02 / uncached input 1 / output 4 RMB per 1M tokens; peak 0.04 / 2 / 8
  • deepseek-v4-pro (DeepSeek-V4-Pro-0813, 1M context, no image understanding): off-peak cached input 0.15 / uncached input 4.5 / output 13.5 RMB per 1M tokens; peak 0.30 / 9.0 / 27.0
  • Web search and fetch (Search, Fetch) are separate APIs billed per successful request: both Search and Fetch cost 5 RMB per 1,000 successful requests; when the DeepSeek API is used in DeepSeek Harness, Claude Code or Codex, the Search / Fetch calls made through server-side tool use are currently not billed and will be charged per request from 00:00 Beijing time on November 1, 2026

Prompts, Requests, and Tokens

• Prompt: User inputs a prompt into the CLI and presses Enter to send it. From the request perspective, it's when the last message is from the user, not from a tool call result.
• Request: In addition to the prompt itself generating one request, after each round of tool calls, the tool call results are sent along with the context until there are no more tool calls.
• Token: Each request has a certain amount of input and output tokens.

One prompt corresponds to multiple requests, and each request has many input and output tokens. Some input tokens will hit the cache. In actual testing in Vibe Coding scenarios, among input + output tokens:

• Input tokens account for 99.5%, because with multi-turn conversations, input tokens accumulate and are repeatedly counted
  • Among which cached tokens account for approximately 90-95% of input + output tokens
• Output tokens account for 0.5%

Common API Pricing Models

• OpenAI Model: Automatic caching, with uncached input price, cached input price, and output price
  • OpenAI has three prices: Input, Cached Input, and Output. If the access doesn't hit the cache, the uncached portion is charged at the Input rate; OpenAI may perform caching; if the access hits the cache, the cached portion is charged at the Cached Input rate.
  • Typically Cached Input is 0.1x the Input price, sometimes between 0.1-0.2x.
• Anthropic Model: Manual caching, with uncached input price, cached input price, input price with cache write (different TTLs may correspond to different prices), and output price
  • Claude has five prices: Base Input Tokens, 5m Cache Writes, 1h Cache Writes, Cache Hits & Refreshes, and Output Tokens. If caching is not used, each input is charged at the Base Input Tokens rate; if caching is used, the portion written to cache is charged at the 5m/1h Cache Writes rate, and subsequent cache hits are charged at the Cache Hits & Refreshes rate.
  • Currently 5m Cache Writes are 1.25x the Base Input Tokens price, 1h Cache Writes are 2x the Base Input Tokens price, and Cache Hits & Refreshes are 0.1x the Base Input Tokens price.

Model Parameters Comparison

Name	Parameters	Active	Vision
DeepSeek-V4-Flash-0731	284B	13B	N
DeepSeek-V4-Flash	284B	13B	N
DeepSeek-V4-Pro-0813	1.6T	49B	N
DeepSeek-V4-Pro	1.6T	49B	N
DeepSeek-V4.1-Flash	552B	8B input / 16B output	Y
GLM-4.7-Flash	30B	3B	N
GLM-4.7	355B	32B	N
GLM-5.1	744B	40B	N
GLM-5.2	744B	40B	N
GLM-5.3-Flash	320B	18B	Y
GLM-5.3	744B	40B	N
Hy3-preview	295B	21B	N
Kimi-K3	2.8T	104B	Y
Kimi-K2.6	1T	32B	Y
MiniMax-M3	428B	23B	Y
MiniMax-M2.7	230B	10B	N
Qwen3.8-2.4T-A95B	2.4T	95B	Y
Qwen3.8-27B	27B	-	Y
Qwen3.8-Flash-Next	180B	6B	Y
Qwen3.5-397B-A17B	397B	17B	Y

Update History

• 2026/11/01: Command Code's limited-time free model Ling 3.1 Flash 1019 now covers the Go and Pro plans too — Go's listing rises from 57 to 58 models and Pro's from 86 to 87, with the library total still 97; the model (ID ling-3-1-flash-1019-free, 1M context, Free on input, output and cache read with requests not drawing on credits, free through 16:00 UTC on 2026-11-03) is now available the same way on all five tiers (Go, GOAT, Pro, Max 10x and Max 20x). Plan prices and tiers, and every other model's token prices and monthly credits, are unchanged
• 2026/11/01: Command Code's Pro plan raised the monthly credits for DeepSeek V4.1 Flash and GLM-5.3 Flash — both go from \(90 to **\)110**, matching Ling 3.1 Flash's Pro credits; estimated requests rose accordingly, DeepSeek V4.1 Flash from 46,200 per 5 hours / 115,000 per week / 231,000 per month to 56,400 / 141,000 / 282,000, and GLM-5.3 Flash from 10,600 / 26,500 / 53,100 to 13,000 / 32,400 / 64,900. Both models' token prices (DeepSeek V4.1 Flash off-peak 0.15 / 0.60 / 0.003 and peak 0.30 / 1.20 / 0.006; GLM-5.3 Flash $0.15 / $0.50 / \(0.03 per 1M tokens for input / output / cache read), the Pro plan price (\)20/month), its usage limits (up to $22 per 5 hours, $55 per week and $110 per month) and every other model's monthly credits are unchanged
• 2026/10/31: The MiniMax docs site changed domains and paths: the Chinese site moved from platform.minimaxi.com to platform.minimax.cn, its subscription docs from /docs/token-plan/{intro,faq} to /docs/m-plan/{intro,faq} and the pay-as-you-go pricing page from /docs/guides/pricing-paygo to /docs/pricing/overview (the old URLs redirect with 302 / 307 / 308 respectively); the English site likewise moved /docs/token-plan/* to /docs/m-plan/* and /docs/guides/pricing-paygo to /docs/pricing/overview; the API-pricing link in the KB now points at the new address
• 2026/10/31: Command Code's GOAT plan raised the monthly credits for DeepSeek V4.1 Flash and GLM-5.3 Flash — both go from \(80 to **\)100**, with estimated requests rising accordingly: DeepSeek V4.1 Flash from 41,000 per 5 hours / 103,000 per week / 205,000 per month to 51,300 / 128,000 / 256,000, and GLM-5.3 Flash from 9,440 / 23,600 / 47,200 to 11,800 / 29,500 / 59,000. Both models' token prices (DeepSeek V4.1 Flash off-peak 0.15 / 0.60 / 0.003 and peak 0.30 / 1.20 / 0.006; GLM-5.3 Flash $0.15 / $0.50 / \(0.03 per 1M tokens for input / output / cache read) are unchanged, as are the GOAT plan price (\)10/month), its usage limits (up to $20 per 5 hours, $50 per week and $100 per month) and its "up to $100 in credits, up to 10x" description
• 2026/10/31: Command Code added the limited-time free model Ling 3.1 Flash 1019 (model ID ling-3-1-flash-1019-free, 1M context; input, output and cache read all Free with requests not drawing on credits, free through 16:00 UTC on 2026-11-03), taking GOAT's listing from 70 to 71 models and the library total from 96 to 97; the model counts as free with no credit draw in GOAT's monthly credits and estimated-request tables. Plan prices and tiers, and every other model's token prices and monthly credits, are unchanged
• 2026/10/31: OpenCode Go raised the monthly usage allowance for DeepSeek V4.1 Flash — Go from \(80 to **\)100, Go Plus from \(160 to **\)200 and Go Teams from \(85 to **\)105** (Go Teams remains the same-tier Go allowance plus \(5), with the estimated requests rising to 43,330 per 5 hours, 108,330 per week and 216,670 per month on Go, 86,670 / 216,670 / 433,330 on Go Plus and 45,500 / 113,750 / 227,500 on Go Teams. The model's token prices (off-peak 0.15 / 0.60 / 0.003, peak 0.30 / 1.20 / 0.006 per 1M tokens) and its peak/off-peak windows, the other 29 models' token prices and monthly allowances, the three plan prices (\)10 Go, $40 Go Plus, $20 per member per month for Go Teams) and the other allowance rules are unchanged
• 2026/10/30: Alibaba Cloud Bailian removed the free quota of the qwen-image-2.0 family: qwen-image-2.0, qwen-image-2.0-pro and the dated versions of both (2026-06-22, 2026-04-22, 2026-03-03) went from 100 images to "none", with output prices unchanged at RMB 0.2 per image for qwen-image-2.0 and RMB 0.5 for qwen-image-2.0-pro; qwen-image-2.1-pro and qwen-image-2.1-turbo keep 10 images. The change concerns free quotas in Bailian's general model catalogue; the tiers, prices, quotas and supported-model lists of the Bailian Token Plans (personal and team editions) and Coding Plan are unchanged
• 2026/10/30: OpenCode Go's Go Teams now derives each member's 5-hour and weekly limits from the $5-higher monthly allowance instead of matching Go: for GLM-5.3, the Go Teams estimated requests changed from 220 per 5 hours / 540 per week / 1,440 per month to 293 / 720 / 1,440, while Go stays at 220 / 540 / 1,080 and the Go Plus figures are unchanged; the plan description now reads that every member gets their own limits, \(5/month higher than Go on every model. The three plans' prices (\)10 / $40 / \(20 per member per month), every model's token prices and monthly allowance (Go Teams is the same-tier Go allowance +\)5), the 30-model library and the other allowance rules are unchanged
• 2026/10/30: Alibaba Cloud Bailian added the third-party-deployed model antdigital/Ling-3.1-flash (deployed by Ling / Ant Digital, China North 2 – Beijing): RMB 2 input / RMB 6 output per million tokens with no free quota, and cache-hit input billed at 20% of the input price. The model is an addition to the general model catalogue: the supported-model lists, tiers, prices and allowances of Token Plan Personal/Team and of Coding Plan are unchanged, and neither Token Plan edition includes this model
• 2026/10/29: MiniMax unified the name of M Plan's credential as the M Plan API key (formerly the "Subscription Key"): the M Plan overview, subscription pricing page and FAQ now say "M Plan API key" throughout. MiniMax Code still works by signing in with no separate subscription or key, while other AI tools use the key or, where supported, sign in with a MiniMax account; wording around allowances changed from "usage" to "quota", and the tier quota table writes Go as "1×" instead of "-" (Explore 3×, Build 7.5×). The three tiers' prices (Go ¥49 / $22, Explore ¥119 / $55, Build ¥469 / $132), quota multipliers, supported models, 5-hour and weekly window rules and credit-pack rules are unchanged
• 2026/10/29: Volcano Engine's Kimi-K3.1-Pro raised its maximum output from 128k to 1024k (the 1024k context window is unchanged), and the model's length limits in both the Coding Plan (Personal Edition) and Agent Plan (Personal Edition) model-spec tables and in the model list now read 1024k (both plan tables previously recorded 128k). The two plans' tiers and prices, deduction coefficients (the Coding Plan quota campaign, and the Agent Plan coefficient of 7 at a limited-time 50% off, i.e. 3.5, through 2026-11-09 23:59:59) and supported-model lists are unchanged
• 2026/10/29: Alibaba Cloud Bailian's general model catalogue largely dropped its free quotas, with older models moving from "1 million tokens / 500k tokens / 20 million tokens / 10k characters / 36,000 seconds / a set number of images or seconds" to "none": in text generation, qwen-max, the qwen-plus family (qwen-plus, qwen-plus-latest, qwen-plus-2025-12-01/07-14/04-28/01-25), the dated versions of qwen3.7-max and qwen3.7-max-preview, qwen3.7-plus-2026-05-26, qwen3.6-plus and its dated versions, qwen3.5-plus and its dated versions, qwen3.7-flash-2026-07-15, qwen3.6-flash and its dated versions, qwen3.5-flash and its dated versions, qwen-flash and its dated versions, qwen-long, qwen3.5-omni-plus-2026-03-15, the qwen3.5-omni-flash family, qwen3-omni-flash and its realtime version, the qwen3.5-omni-flash-realtime series, qwen3.5-omni-plus-realtime-2026-03-15, qwen3.5-livetranslate-flash-realtime and its dated version, qwen3-livetranslate-flash-2025-12-01, qwen-vl-ocr-2025-11-20, qwen3-coder-flash and its dated version, qwen3.6-35b-a3b, qwen3.6-27b, qwen3.5-397b-a17b / 122b-a10b / 27b / 35b-a3b, glm-5.2, glm-5.1, glm-5, kimi-k2.6 and kimi-k2.5; in embeddings, text-embedding-v1/v2/v3 (500k tokens), text-embedding-async-v1 (20 million tokens), qwen2.5-vl-embedding, multimodal-embedding-v1 and gte-rerank-v2; in speech, qwen-audio-3.0-tts-plus/flash and cosyvoice-v3-plus / v3-flash / v2 (10k characters), qwen-audio-3.0-realtime-plus/flash, qwen-audio-3.0-asr-flash with its streaming/filetrans versions, fun-asr-realtime-2026-02-28, fun-asr-mtl-realtime-2025-12-10 and fun-asr-flash-8k-realtime-2026-01-28 (36,000 seconds); in image and video generation, the 50–500 images of the Wan wan2.6 / 2.5 / 2.2 / 2.1 / 2.0 series and wanx-v1, the 10–200 seconds of the wan2.x / wan3.0 and wanx2.1 video models, fun-music-preview's 1,000 seconds and the 10 seconds of happyhorse-1.0-t2v/i2v. Third-party deployments that previously listed no quota are now marked "none" uniformly: the whole Kimi (Moonshot deployment) set (kimi/kimi-k3.1-pro, kimi/kimi-k3.1-pro-highspeed, kimi/kimi-k3, kimi/kimi-k2.7-code, kimi/kimi-k2.7-code-highspeed, kimi/kimi-k2.6, kimi/kimi-k2.5), MiniMax/MiniMax-M2.7 / M2.5 / M2.1, and the DeepSeek series on the vanchin and siliconflow deployments. The free-quota validity note is now stated once in the table header as "within 90 days of activating Bailian / the model's release / approval, whichever is later"; fun-music-v1 has 1,000 seconds and paraformer-8k-v2 with paraformer-realtime-8k-v2 have 36,000 seconds per month (granted at 00:00 on the first of each month, valid for one month). The qwen3.8 series, natively deployed DeepSeek-V4 / V4.1, GLM-5.3, natively deployed kimi-k3, natively deployed MiniMax-M3.1 / M2.5 and the qwen-audio-3.1 series keep their 1 million token free quota. No model's unit price changed, and the tiers, prices, allowances and supported-model lists of Bailian's Token Plan (Personal and Team editions) and Coding Plan are unchanged
• 2026/10/29: OpenCode Go added a third plan, Go Teams ($20 per member per month): every member gets their own Go allowance plus $5/month more on every model (GLM-5.3-Flash, GLM-5.2, Kimi K2.7 Code, LongCat-2.0, MiMo-V2.6-Flash, MiMo-V2.5, MiniMax M3, Muse Spark 1.3/1.2 Contributor, Qwen3.7 Plus and Hy3 rise from $60 to $65; DeepSeek V4.1 Flash from $80 to $85; MiniMax M3.1 Flash from $20 to $25; Qwen3.8 Flash, Hy4 preview and Gemini 4 Argon from $30 to $35; every other model from $15 to $20), and each member's 5-hour and weekly limits equal Go's while the monthly limit follows the $5-higher allowance. Go and Go Plus remain single-member workspace plans and either can upgrade to Go Teams at any time with the unused part of the month's allowance credited; a member joining mid-period is charged $20 and gets a full monthly allowance, service accounts are not covered, and Go Teams starts with Extra Usage on. Token prices are identical across the three plans. MiniMax M3 is now tiered by input length: ≤512K tokens $0.30 input / $1.20 output / $0.06 cache read and >512K tokens $0.60 / $2.40 / $0.12 per 1M tokens, with the monthly allowance unchanged at $60 on Go and \(180 on Go Plus. The model library still has 30 models, and the Go and Go Plus prices (\)10 / $40 per month) and every other model's prices and allowances are unchanged

• 2026/10/28: Volcano Engine's DeepSeek-V4.1-Flash-Economy has a 1024k context window (previously recorded as 1049k) with the 384k maximum output unchanged. Availability across all four Agent Plan tiers (Small / Medium / Large / Max) and both Coding Plan tiers (Lite, Pro), the deduction coefficient (2, halved to 1 during the limited-time promotion through 2026-12-30 23:59:59), and plan prices and tiers are unchanged

• 2026/10/28: Volcano Engine's Auto mode now routes to kimi-k3.1-pro (previously kimi-k3): Auto's deduction coefficient is 1 in Coding Plan and 0.5 in Agent Plan during the 2026-06-10 18:00 to 2026-11-08 23:59:59 campaign, and both plans substantially raise the share of kimi-k3.1-pro routing at night (00:00–08:00); Coding Plan previously stated only Auto's coefficient and named no routing target. Plan tiers and prices, every model's coefficient, the supported-model lists and the 1M-context list are unchanged

• 2026/10/28: Alibaba Cloud Bailian model catalogue and price update (all at the model-catalogue level; the tiers, prices, allowances and supported-model lists of Token Plan Personal and Team editions and of Coding Plan are unchanged): qwen3.8-flash gained European Union and China Hong Kong deployments at RMB 1.094 input / RMB 3.427 output per million tokens (the global deployment stays at RMB 0.8 input / 2.7 output with a 1 million token free quota), and both regions' explicit-cache supported-model lists now include qwen3.8-flash; new real-time speech-to-speech model qwen-audio-3.1-realtime-flash — China North 2 (Beijing) RMB 1.5 text input / 6 audio input / 4.5 text output / 12 audio output per million tokens (with a 1 million token free quota), international deployments 1.677 / 6.781 / 5.104 / 13.636, the same prices as qwen-audio-3.0-realtime-flash; real-time speech-to-speech billing is now stated explicitly: text-only responses are billed at the text output price, and when both text and audio are output only the audio is charged output fees (the accompanying text is not charged extra). The 3D generation Tripo series moved to credit-based billing at 1 credit = RMB 0.07, cost = (base item credits + credits of the enabled add-ons) × RMB 0.07: Tripo-H3.1 text-to-3D 10 credits and single/multi-image-to-3D 20 credits, Tripo-P1.0 text-to-3D 30 credits and single/multi-image-to-3D 40 credits, texture add-ons 10 credits for standard (2K) / 20 for high-definition (4K) / 30 for ultra (8K), plus new billable items Tripo-ImageToSplat, Tripo-Texture, Tripo-Segmentation (mesh segmentation 40 credits, smart segmentation 85 / 55 credits), Tripo-MeshCompletion, Tripo-Retopology, Tripo-ConvertFormat, Tripo-AutoRig (25 credits), Tripo-RigCheck (not billed) and Tripo-AnimationRetarget (10 credits per animation)

• 2026/10/27: OpenCode Go's model library grew from 29 to 30 models with the limited-time free Iceman Contributor Free — input, output and cache read are all free, both Go and Go Plus monthly usage allowances and the estimated request counts are unlimited (limited-time), model ID iceman-contributor-free, endpoint https://opencode.ai/inference/go/openai/v1/chat/completions (@ai-sdk/openai-compatible); the model is free for a limited time in exchange for permission to use prompts and completions to improve the model, with Model training Yes and Data retention Not ZDR, and the note "Free for a limited time in exchange for permission to use your prompts and completions to improve the model." Both plan prices (Go $10 / Go Plus $40 per month) and the other 29 models' token prices and monthly allowances are unchanged

• 2026/10/27: SenseTime SenseNova TokenPlan raised the general credit window caps — the general pool goes from 60,000 to 120,000 credits per rolling 5-hour window and from 600,000 to 1,200,000 credits per rolling week (both effective 2026-10-27), while the Flash-Lite pool stays at 60,000 per 5-hour window and 600,000 per week. When the increase takes effect every account's available general credits are reset to the new window caps, and the available Flash-Lite credits stay unchanged. The Flash-Lite spend rebate ended the same day — it had rebated 1 general credit per credit of Flash-Lite pool consumption (aggregated per calendar day, settled hourly, each rebate valid 30 days, not counted against either window); rebate credits already credited keep their balance and expiry, consumption counted before the switch is still settled under the old rules, and Flash-Lite remains usable while general credits last. Models other than Flash-Lite still draw only on the general pool, and the supported models remain SenseNova 6.8 Flash Lite, SenseNova U1.5 Lite, SenseNova U1.5 Fast, DeepSeek V4 Flash, DeepSeek V4.1 Flash, GLM-5.2 and Kimi K3

• 2026/10/27: Command Code added GPT-6.1 Terra (1.1M context) on Pro only — $1.00 input / $5.00 output / $0.05 cache read / $1.25 cache write per 1M tokens, with Pro $20 in monthly credits and estimated requests of 976 per 5 hours, 2,440 per week and 4,880 per month. The library grows from 95 to 96 models (Pro's listing from 85 to 86, while Go still lists 57 and GOAT 70); plan prices and every other model's token prices and monthly credits are unchanged

• 2026/10/27: Command Code raised the credits and usage limits of GOAT and Pro. GOAT ($10/month) goes from $80 in credits (8x) to up to $100 (up to 10x), and its usage limits go from $14 per 5 hours, $35 per week and $70 per month to **up to $20 / $50 / \(100**. **Pro** (\)20/month) goes from $80 to up to $110 in credits, and its usage limits go from $16 / $40 / $80 to up to $22 / $55 / $110. Premium models still carry up to $20 of monthly usage per model on both plans, with Claude Haiku 5.5 at $30, and the per-model credit caps are unchanged (Ling 3.1 Flash up to $100; DeepSeek V4.1 Flash and GLM-5.3 Flash $80 each; Tencent Hy3 and Qwen 3.8 27B \(70 each). Go (\)1/month), Max (\(100/month) and Provider (\)15/month) prices and credits, and every model's token prices, are unchanged

• 2026/10/26: Alibaba Cloud Bailian's Kimi (Moonshot deployment) section for China North 2 (Beijing) gained two models alongside the existing kimi/kimi-k3, kimi/kimi-k2.7-code-highspeed, kimi/kimi-k2.7-code, kimi/kimi-k2.6 and kimi/kimi-k2.5: kimi/kimi-k3.1-pro at RMB 13 input / RMB 68 output per million tokens, and kimi/kimi-k3.1-pro-highspeed at RMB 26 input / RMB 136 output per million tokens (the free-quota column marks "none" for the high-speed model and lists no specific allowance for k3.1-pro). Context-cache discount: cached input for kimi/kimi-k3.1-pro is billed at 10% of the input price (the same as kimi/kimi-k3), and kimi/kimi-k3.1-pro-highspeed at 5%. The prices and cache discounts of the five earlier models (kimi/kimi-k3 at 20/100, kimi/kimi-k2.7-code-highspeed at 13/54, kimi/kimi-k2.7-code and kimi/kimi-k2.6 at 6.5/27 each, kimi/kimi-k2.5 at 4/21 RMB per million tokens) and the pricing of every other deployment and model are unchanged. Bailian's Token Plan (Personal and Team editions) and Coding Plan keep their tiers, prices, allowances and supported-model lists, and neither Token Plan edition lists the k3.1 series

• 2026/10/25: OpenCode Go retired the limited-time free LongCat 2.5 Preview Free model, taking the model library from 30 to 29: the supported-model list, token-price tables, both plans' monthly allowance tables, estimated-request tables, endpoint table and data retention table all dropped its rows (model ID longcat-2.5-preview-free), leaving Beam Free as the only unlimited-for-a-limited-time model in the allowance tables. The two plan prices (Go $10 / Go Plus $40) and every other model's token prices and monthly allowances are unchanged

• 2026/10/25: Volcano Engine's Coding Plan (Personal Edition) and Agent Plan (Personal Edition) added the kimi-k3.1-pro model (Moonshot's flagship for enterprise-grade long-horizon tasks and agentic coding, supporting deep thinking, function calling and context caching with 5-minute and 1-hour cache writes, 1024k context / 128k output, available on all four tiers): the Agent Plan deduction coefficient is 7, at 50% off (3.5) from 2026-10-24 00:00 to 2026-11-09 23:59:59; the available quota of this model in the Coding Plan from 2026-10-24 00:00 to 2026-11-09 23:59:59 is comparable to that during the Agent Plan 50%-off deduction promotion. Both plans' 1M-context lists now include kimi-k3.1-pro, and the plan tiers and prices as well as every other model's deduction coefficient are unchanged

• 2026/10/25: OpenCode Go replaced Gemini 4 Argon Contributor with the regular Gemini 4 Argon: token prices changed from $4.00 input / $20.00 output / \(0.20 cache read per 1M tokens to **\)2.00 / $10.00 / $0.10** (50% off through 2026-11-30, list prices still $4.00 / $20.00 / \(0.20), the monthly allowance dropped from the limited-time-doubled ~~\)30~~ \(60 / ~~\)120~~ \(240 back to **\)30 / $120**, the model ID changed from gemini-4-argon-contributor to gemini-4-argon, and the endpoint changed from https://opencode.ai/inference/go/v1/models/gemini-4-argon-contributor to https://opencode.ai/inference/go/google/v1beta/models/gemini-4-argon. The model no longer trains on requests and completions and retains data for 0 days, so it left the list governed by the workspace privacy switch "Allow paid endpoints that train on request data", which now covers only Muse Spark 1.3 Contributor and Muse Spark 1.2 Contributor. Estimated requests are unchanged (440 per 5 hours, 1,080 per week and 2,120 per month on Go; 1,760 / 4,320 / 8,480 on Go Plus); each response now also reports how much the request counted through the opencode.allowance field. Every other model's token prices and monthly allowances and both plan prices are unchanged

• 2026/10/24: Volcano Engine Agent Plan (Personal Edition) added the image-generation model doubao-seedream-5.0-flash (available on all plans, 60 AFP per output image with no AFP charged for input images); image generation now offers two models, doubao-seedream-5-0-pro and doubao-seedream-5.0-flash. Every other model and its deduction coefficient, the 1M-context support list, and the plan tiers and prices are unchanged

• 2026/10/24: OpenCode Go now spells out how to enable restricted models: workspace privacy settings decide which models are usable — paid endpoints that train on request data are blocked by default and the allowed region is Europe & United States, while workspaces without saved privacy settings also allow Global for requests from China; an owner or admin enables DeepSeek V4.1 Flash and V4 Pro by selecting Global under Regions in Settings › Privacy, and Gemini 4 Argon Contributor, Muse Spark 1.3 Contributor and Muse Spark 1.2 Contributor by turning on "Allow paid endpoints that train on request data". The two plan prices and every model's token prices and monthly allowances are unchanged

• 2026/10/24: OpenCode Go's model library grew from 29 to 30 models with the addition of Kimi K3.1 Pro (1M context, model ID kimi-k3.1-pro): $2.00 input / $10.00 output / $0.20 cache read / $2.00 cache write per 1M tokens (identical on Go and Go Plus), a monthly allowance of $15 on Go and $60 on Go Plus (the same group as Kimi K3), estimated requests of 147 per 5 hours, 368 per week and 735 per month on Go and 588 / 1,471 / 2,941 on Go Plus, and about 1,050 input, 76,500 cached input and 300 output tokens per request; it uses the OpenAI-compatible endpoint (@ai-sdk/openai-compatible). Kimi K3's price and allowance are unchanged, as are the two plan prices and every other model's token prices and monthly allowances

• 2026/10/24: Command Code's model library now has 95 models (Go lists 57, GOAT 70 and Pro 85, previously 56 / 69 / 86): Kimi K3.1 Pro was added with 1M context at $2.00 / $10.00 / $0.20 per 1M tokens (input / output / cache read), monthly credits of Go $6 / GOAT $20 / Pro $30 and estimated requests of 132 per 5 hours, 265 per week and 441 per month on Go, 294 / 735 / 1,470 on GOAT and 441 / 1,100 / 2,210 on Pro. At the same time MiMo V2.5 and MiMo V2.5 Pro were removed from Pro's model table, monthly credits table and estimated-requests table, so neither model is offered on any plan any more. MiMo V2.6 Flash, MiMo V2.6 Pro and MiMo V2.6 Pro UltraSpeed are unaffected, and every other model's token prices and monthly credits, as well as the plan prices and tiers, are unchanged

• 2026/10/24: Kimi Code's flagship model changed: Kimi Code now runs on the flagship K3.1 Pro series (3T-class parameters, up to 1M context, with marked gains over K3 in coding, 3D creation, financial research and long-horizon agent tasks), and the earlier description of "the K2.8 Preview standard mode and the K2.7 Code HighSpeed mode, up to 260 Tokens/s" is replaced by a general statement that users pick a standard-speed or high-speed model depending on the task. The usable model IDs went from 4 to 6: k3.1-pro (callable by Moderato / Plus and above, up to 1M context for Allegretto / Pro and above, thinking mode only with max as the default, and requests with thinking disabled are rejected) and k3.1-pro-highspeed (Allegretto / Pro and above, output roughly 2–3× faster than k3.1-pro while drawing about 2× the allowance, up to 1M context) are new; the tier requirements and context entitlements of k3, k3-256k, kimi-for-coding (K2.8 Preview) and kimi-for-coding-highspeed (K2.7 Code HighSpeed) are unchanged. Tier prices are unchanged (Andante 49, Moderato 99, Allegretto 199, Allegro 699 RMB/month), as is the API pricing of K3, K2.7-Code and K2.7-Code-HighSpeed

• 2026/10/23: Command Code's Go and GOAT plans no longer offer MiMo V2.5 or MiMo V2.5 Pro — Go's listing falls from 58 to 56 models and GOAT's from 71 to 69, taking the library total from 96 to 94. Both models remain on Pro, which still lists 86, at their discounted $0.14 / $0.28 / $0.0028 and $0.435 / $0.87 / $0.0036 per 1M tokens (input / output / cache read) with monthly credits of $40 and $30. MiMo V2.6 Flash, MiMo V2.6 Pro and MiMo V2.6 Pro UltraSpeed are unaffected at $0.14 / $0.28 / $0.0028, $0.435 / $0.87 / $0.0036 and $4.35 / $8.70 / $0.036 per 1M tokens; the first two carry Go $6 / GOAT $20 / Pro $30 and V2.6 Pro UltraSpeed carries GOAT $10 / Pro $20. The limited-time free models remain Laguna S 2.1, Glyph Cluster and Beam 1.0. Plan prices and tiers and every other model's token prices and monthly credits are unchanged

• 2026/10/23: Command Code's model library shrank from 98 to 96 models (GOAT from 73 to 71 and Pro from 88 to 86; Go still lists 58 of the 96): the free variants of MiniMax M3.1 Flash and Ornith 1.5 122B were removed from the GOAT and Pro model tables, while the paid variants are unchanged — token prices remain $0.15 / $0.60 / $0.015 and $0.16 / $0.64 / $0.02 per 1M tokens (input / output / cache read) respectively, with monthly credits of Go $6 / GOAT $20 / Pro $30 and unchanged estimated requests. The limited-time free models are now Laguna S 2.1, Glyph Cluster and Beam 1.0, the same on Go, GOAT, Pro, Max 10x and Max 20x. The plan prices and tiers and every other model's token prices and monthly credits are unchanged

• 2026/10/22: Command Code's Go model table dropped the free variants of Ornith 1.5 122B and MiniMax M3.1 Flash (input, output and cache read all Free without drawing on credits), taking the Go listing from 60 to 58 models and the Go model table from 98 to 96 models in all; the paid variants of both models remain on Go at $0.16 / $0.64 / $0.02 and $0.15 / $0.60 / $0.015 per 1M tokens (input / output / cache read) with monthly credits of $6 each. GOAT (73 models) and Pro (88 models) still list both free variants, so the limited-time free models on Go are now Laguna S 2.1, Glyph Cluster and Beam 1.0. The plan prices and every other model's price and credits are unchanged

• 2026/10/22: OpenCode Go's limited-time free MiniMax M3.1 Flash became a standard metered model — token prices changed from Free to input $0.15 / output $0.60 / cache read \(0.015 per 1M tokens (identical on Go and Go Plus), the monthly usage allowance changed from unlimited for a limited time to **\)20** on Go and $80 on Go Plus, and the estimated requests changed from unlimited to 3,880 per 5 hours, 9,690 per week and 19,380 per month on Go (15,500 / 38,760 / 77,520 on Go Plus); the model ID changed from minimax-m3.1-flash-free to minimax-m3.1-flash at the same OpenAI-compatible endpoint https://opencode.ai/inference/go/openai/v1/chat/completions (@ai-sdk/openai-compatible), the privacy row stays Model training Not used with Data retention 0 days, and the model is no longer labelled limited-time free. The limited-time free models are now LongCat 2.5 Preview Free and Beam Free. The two plan prices ($10 Go / $40 Go Plus) and every other model's price and allowance are unchanged

• 2026/10/22: Alibaba Cloud Model Studio dropped the free quota for MiniMax/MiniMax-M3.1-Flash, which now shows none (prices and model specs unchanged at 1 RMB input / 4 RMB output per 1M tokens with cached input billed at 10% of the input price); the audio-generation model qwen-audio-3.1-tts-next gained Singapore-region prices of 6.781 RMB input / 5.104 RMB output per 1M tokens (Beijing remains 6 RMB input / 12 RMB output with a 1M-token free quota). The tiers, prices, allowances and supported models of the Model Studio Token Plan Personal and Team editions are unchanged

• 2026/10/22: The limited-time free run for Command Code's Ornith 1.5 122B ended (it was due to run through 23:00 PT on 2026-10-21) — its same-named free variant is still listed on the Go, GOAT and Pro model tables with Free input, output and cache read that do not draw on credits, but no deadline is shown any more. The limited-time free models are now Laguna S 2.1, Glyph Cluster, Beam 1.0 and MiniMax M3.1 Flash on all five tiers (Go, GOAT, Pro, Max 10x and Max 20x); the Ornith 1.5 122B free variant and the free TypeSafe Jev no longer count. GOAT now lists Ling 3.1 Flash (\(100 in credits) as its own per-model credit entry alongside DeepSeek V4.1 Flash (\)80), GLM-5.3 Flash (\(80), Tencent Hy3 (\)70) and Qwen 3.8 27B ($70), with the total model count unchanged. The plan prices, tiers and every other model's token prices and monthly credits are unchanged

• 2026/10/22: Alibaba Cloud Model Studio updated its model catalogue and pricing — it added MiniMax/MiniMax-M3.1-Flash (deployed by MiniMax, thinking mode only) at 1 RMB input / 4 RMB output per 1M tokens, with the free quota shown in the Model Studio console and cached input billed at 10% of the input price; MiniMax/MiniMax-M3 is now tiered by input length, at 2.10 RMB input / 8.40 RMB output per 1M tokens for up to 512K input tokens and 4.20 / 16.80 RMB beyond 512K (previously a flat 4.20 / 16.80 RMB, so calls with up to 512K input tokens now cost half as much, matching MiniMax's own tiered pricing), with the cached-input ratio unchanged at 20%; and it added Zhipu glm-5.3-prime (non-thinking and thinking modes, no token-length tiers) at 16 RMB input / 56 RMB output per 1M tokens with no free quota and a 25% cached-input ratio (20% in Singapore and US Virginia), the same tier as glm-5.3 and glm-5.2. The tiers, prices, allowances and supported models of the Model Studio Token Plan Personal and Team editions are unchanged — neither edition includes glm-5.3-prime, the Personal edition carries no MiniMax models and the Team edition still lists only MiniMax-M2.5

• 2026/10/22: The model tables on the Go, GOAT and Pro plans no longer mark zero data retention (ZDR) support per model — the ZDR column is gone from all three tables and the ZDR rules are now stated in the FAQ instead: enforcing ZDR with CMD_ZDR=1 costs nothing extra on models where ZDR is included, while on the rest requests meter at the plan's default usage (Go: $6) even when a model carries a boosted figure. The plan prices and tiers, the library size (98 models — Go 60, GOAT 73, Pro 88) and every model's token prices and monthly credits are unchanged

• 2026/10/21: OpenCode Go's limited-time 4x allowance for Step 5 Preview expired and its monthly usage allowance dropped back to the regular values — Go \(15** and Go Plus **\)60 (previously $60 / $240 under the 4x boost), with the "4x · Limited time" marking dropped; estimated requests fell back in step to 430 / 1,070 / 2,130 (5 hours / week / month) on Go and 1,720 / 4,280 / 8,520 on Go Plus. Token prices are unchanged (input $1.00 / output $2.70 / cache read $0.10 per 1M tokens), as is the per-request estimate of 1,000 input tokens, 55,000 cached tokens and 200 output tokens, and no other model's price, allowance or request limit changed

• 2026/10/21: Alibaba Cloud Model Studio no longer offers qwen3.8-max-prime (the Prime-mode variant, formerly 24 RMB input / 72 RMB output per 1M tokens on the Chinese site with no free quota), leaving qwen3.8-max and qwen3.8-max-0902 as the only Qwen 3.8 Max models (12 RMB input / 36 RMB output per 1M tokens, 1M-token free quota, half price for Batch calls and discounts on context caching — unit prices unchanged). The peak/off-peak note is now stated generically — peak hours 08:00–22:00 and off-peak 22:00–next 08:00 Beijing time — with the periods themselves and every model's unit prices unchanged. The Token Plan Personal and Team editions' tiers, prices, allowances and supported models are unchanged, and neither edition includes qwen3.8-max-prime

• 2026/10/21: MiniMax restored the "permanent 50% off" label and struck-through list prices on pay-as-you-go MiniMax-M3 without changing the effective unit prices — ≤512K input tokens cached input 0.42, uncached input 2.10, output 8.40 (struck-through list prices 0.84 / 4.20 / 16.80) and >512K 0.84 / 4.20 / 16.80 (list prices 1.68 / 8.40 / 33.60); the international site carries the same label, ≤512K $0.06 / $0.30 / $1.20 and >512K $0.12 / $0.60 / $2.40, against struck-through list prices of $0.12 / $0.60 / $2.40 and $0.24 / $1.20 / $4.80. MiniMax-M3.1-Flash pricing (0.10 / 1.00 / 4.00, international $0.015 / $0.15 / $0.60), every M Plan tier price, the usage allowances and the credit-pack rules are unchanged

• 2026/10/21: Command Code's two limited-time credit raises expired and DeepSeek V4.1 Flash's monthly credits dropped back — GOAT from \(100 to **\)80**, Pro unchanged at $90 (it had already reverted on Oct 20) and Go unchanged at $10; estimated requests fell back too, GOAT from 51,300 to 41,000 per 5 hours, 128,000 to 103,000 per week and 256,000 to 205,000 per month, and Pro from 56,400 to 46,200, 141,000 to 115,000 and 282,000 to 231,000. The Mistral Large 4 raise ended at the same time: monthly credits Go from $10 back to $6, GOAT from $40 back to $20 and Pro from $50 back to $30, with estimated requests Go from 336 down to 202 per 5 hours, 672 to 403 per week and 1,120 to 672 per month, GOAT from 896 to 448, 2,240 to 1,120 and 4,480 to 2,240, and Pro from 1,120 to 672, 2,800 to 1,680 and 5,600 to 3,360. All three plans' model tables gained a ZDR column marking each model as "ZDR included at no extra cost", "ZDR costs extra" or "no ZDR", with a note that enforcing ZDR via CMD_ZDR=1 costs nothing extra on the included models while models marked as costing extra may change price under the upstream provider's rules (on Go such requests meter at that tier's default usage of $6). Both models' token prices (DeepSeek V4.1 Flash off-peak 0.15 / 0.60 / 0.003 and peak 0.30 / 1.20 / 0.006; Mistral Large 4 1.36 / 4.18 / 0.14 per 1M tokens), the library size (98 models — Go 60, GOAT 73, Pro 88), every other model's monthly credits and all plan prices and tiers are unchanged

• 2026/10/21: Zhipu's API price table added the multimodal model GLM-5.3-FlashX: input modalities cover images, video, files and text, 1M context, with cached input 0.57, uncached input 2 and output 7 RMB per 1M tokens. The table's "Other models and services" section no longer lists GLM-5.2 separately, though its billing and unit prices are unchanged (cached input 2, uncached input 8, output 28 RMB per 1M tokens, 1M context); GLM-5.3 (cached input 2 / uncached input 8 / output 28), GLM-5.3-Flash (0.23 / 0.8 / 2.8), GLM-OCR (0.2 RMB per 1M tokens for both input and output, no Batch API) and GLM-TTS (2 RMB per 10K characters) are all unchanged

• 2026/10/21: The Xiaomi MiMo Token Plan (Personal Edition) completed its model retirement: mimo-v2.5-pro and mimo-v2.5 were retired at 10:00 Beijing time on 2026-10-21, cutting the supported models from 8 to 6 — the only language models left are MiMo-V2.6-Pro and MiMo-V2.6-Flash, while the four audio models MiMo-V2.5-ASR, MiMo-V2.5-TTS-VoiceClone, MiMo-V2.5-TTS-VoiceDesign and MiMo-V2.5-TTS remain available; the language-model Credit table drops the mimo-v2.5-pro (2.5 / 300 / 600 Credits per token) and mimo-v2.5 (2 / 100 / 200) rows. Monthly plan prices and allowances (Lite 39 RMB / 6 USD, Standard 99 / 16, Pro 329 / 50, Max 659 / 100 per month; 4.1 / 11 / 38 / 82B Credits per month), the yearly plan allowances, ASR at 30M Credits per hour, free TTS for a limited time and the discount rules are unchanged; the yearly plans' RMB prices were re-stated at Lite 408, Standard 1044, Pro 3468 and Max 6948 RMB per year (the USD yearly prices of 63.36 / 168.96 / 528.00 / 1056.00 are unchanged)

• 2026/10/21: Command Code adjusted its model library (96 → 98 models; Go went from 58 to 60 listed models, GOAT from 71 to 73, Pro from 86 to 88): added Ornith 1.5 122B (262K context) at token prices of $0.16 input / $0.64 output / $0.02 cache read per 1M tokens, with monthly credits of $6 on Go, $20 on GOAT and $30 on Pro and estimated requests of 1,430 per 5 hours, 2,870 per week and 4,780 per month on Go, 3,180 / 7,960 / 15,900 on GOAT and 4,780 / 11,900 / 23,900 on Pro; a limited-time free variant was added alongside it (through 23:00 PT on 2026-10-21, Free on input, output and cache read, requests do not draw on credits and it has no entry in the estimated-request table). The limited-time free models are now Laguna S 2.1, Glyph Cluster, Beam 1.0, MiniMax M3.1 Flash and Ornith 1.5 122B, the same on all five tiers. The plan prices (Go $1, GOAT $10, Pro $20, Max $100 and Provider $15 per month plus processing fee), the tiers, and every other model's token prices and monthly credits are unchanged

• 2026/10/21: The Tencent Cloud LLM Token Plan's Enterprise Professional Plan added the non-Official-direct-supply DeepSeek-V4.1-Flash-1017 (model ID deepseek-v4.1-flash-1017) to its model library: it is listed in both the Guangzhou and Singapore regions ahead of DeepSeek-V4.1-Flash and coexists with the Official direct-supply version already listed (model ID deepseek/deepseek-flash), and both carry the same credit prices — cached input 2 / uncached input 100 / output 400 (off-peak), 4 / 200 / 800 (peak) credits per 1M tokens. The peak/off-peak windows, the plan tiers and prices (1 RMB per 100 credits, minimum 50K credits per purchase), the Personal Hy Token Plan and Universal Token Plan tiers, allowances and supported models, and every other model's credit prices are unchanged

• 2026/10/20: Alibaba Cloud Bailian Token Plan (Personal Edition) positions the Usage Pack as a top-up to the plan's monthly quota: when the plan quota is insufficient, Usage Packs can be bought at 100 RMB each per month for 20,000 Credits each, only with an active subscription and up to 5 held at a time (100,000 Credits in total); pack credits do not count towards the plan's monthly quota and are deducted automatically once the plan quota is used up. Service is accordingly paused only when the plan quota is used up and no Usage Pack credits remain, with quota restored after the next subscription month. The plan tiers and prices (Lite 60 / Essential 120 / Standard 180 / Pro 600 RMB per month, 39/79/139/499 for a limited time), each tier's Credits (11,500 / 25,500 / 45,000 / 180,000), the upgrade rules, the supported models and the limited-time night discount are unchanged

• 2026/10/20: Command Code ended the limited-time credit raise for DeepSeek V4.1 Flash on the Pro plan — its monthly credits drop from \(110 back to **\)90**, and the estimated request counts drop back to 46,200 per 5 hours, 115,000 per week and 231,000 per month; GOAT still carries the raised $100 (through 2026-10-21) and Go stays at $10. The model's token prices (input $0.15 / output $0.60 / cache read $0.003 per 1M tokens), every other model's monthly credits, and the plan prices and tiers are unchanged
• 2026/10/20: Volcano Engine added DeepSeek-V4.1-Flash-Economy to both the Coding Plan and the Agent Plan: it uses exactly the same model weights as DeepSeek-V4.1-Flash with identical capability and results, at a lower price with slightly slower response generation, aimed at cost-sensitive workloads that do not need high generation speed; it supports multimodal input, defaults to deep thinking (which can be turned off), has a 1049k context window and 384k maximum output, and joins the 1M-context support list. In the Agent Plan its deduction coefficient is 2 (input and output identical), halved to 1 during the 2026-10-20 00:00 to 2026-12-30 23:59:59 promotion; in the Coding Plan its coefficient is likewise halved over the same window. All four Agent Plan tiers (Small, Medium, Large, Max) and both Coding Plan tiers (Lite, Pro) support it. Plan prices and tiers, and every other model's deduction coefficient and availability, are unchanged
• 2026/10/20: Command Code raised the monthly credits for DeepSeek V4.1 Flash for a limited time — GOAT from \(80 to **\)100** and Pro from \(90 to **\)110** (both marked as running through Oct 21st), with Go unchanged at $10. Estimated request counts rose accordingly: GOAT from 41,000 to 51,300 per 5 hours, 103,000 to 128,000 per week and 205,000 to 256,000 per month; Pro from 46,200 to 56,400, 115,000 to 141,000 and 231,000 to 282,000. The model's token prices (input $0.15 / output $0.60 / cache read $0.003 per 1M tokens), every other model's credits, and the plan prices and tiers are unchanged
• 2026/10/20: Command Code adjusted its model library (95 → 96 models; Go went from 57 to 58 listed models, GOAT from 70 to 71, Pro from 85 to 86): added MiniMax M3.1 Flash (1M context) — token prices $0.15 input / $0.60 output / $0.015 cache read per 1M tokens (matching the upstream international pricing), monthly credits Go $6 / GOAT $20 / Pro $30, estimated requests Go 1,900 per 5 hours, 3,810 per week and 6,350 per month, GOAT 4,230 / 10,600 / 21,200, Pro 6,350 / 15,900 / 31,700; a limited-time free variant was added alongside it (model ID minimax-m3-1-flash-free, Free on input, output and cache read, requests do not draw on credits, no entry in the estimated-request table). The limited-time free model Cat Jam was retired and MiniMax M3.1 Flash took its free slot: the limited-time free models are now Laguna S 2.1, Glyph Cluster, Beam 1.0 and MiniMax M3.1 Flash, the same on all five tiers (Go, GOAT, Pro, Max 10x and Max 20x). The plan prices (Go $1, GOAT $10, Pro $20, Max $100 and Provider $15 per month plus processing fee), the tiers, and every other model's token prices and monthly credits are unchanged
• 2026/10/19: OpenCode Go adjusted its model library (29 models, unchanged in count): Space Bunny was removed (its rows in the token-price table, both monthly-allowance tables, the estimated-request table, the endpoint table and the privacy table were deleted, along with its line in the per-request token estimates), and the limited-time free model MiniMax M3.1 Flash Free was added — input, output and cache read are all free, both monthly allowance tiers and the estimated request counts are unlimited (limited-time promotion), model ID minimax-m3.1-flash-free, endpoint https://opencode.ai/inference/go/openai/v1/chat/completions (@ai-sdk/openai-compatible), with Model training Not used and Data retention 0 days in the privacy table, and the note "MiniMax M3.1 Flash Free: Free for a limited time."; the model has no entry in the per-request token estimates. Both plan prices (Go $10 and Go Plus $40 per month) and every other model's token prices, monthly allowances and request limits are unchanged
• 2026/10/19: MiniMax released the text model MiniMax M3.1 Flash (general availability; the international site describes it as an open-weight model for everyday work) and retired MiniMax-M3.1-Flash-Preview, with requests using the old name served by MiniMax-M3.1-Flash — the models overview, the M Plan overview page and the subscription pricing page now all write the text model as M3.1 Flash, the name drops the Preview suffix and is no longer labelled as available only through M Plan and MiniMax Code, while the description and capabilities (natively multimodal, 1M context, tunable thinking depth) are unchanged; in the FAQ, "the thinking depth for M3.1 Flash Preview" became "a text model's thinking depth" and "credit packs support the M3.1 Flash Preview text model" became "credit packs support text models". The language-model price table on the pay-as-you-go page now lists MiniMax-M3.1-Flash: input 1.00, output 4.00 and cache read 0.10 RMB per 1M tokens (international $0.15 / $0.60 / $0.015); MiniMax-M3 keeps its unit prices (≤512K input tokens input 2.10 / output 8.40 / cache read 0.42, >512K 4.20 / 16.80 / 0.84, international 0.30 / 1.20 / 0.06 and 0.60 / 2.40 / 0.12), but the "permanent 50% off" label and struck-through list prices were removed and the discounted values became the standard prices. MiniMax-M2.7, M2.7-highspeed, M2.5, M2.5-highspeed, M2.1, M2.1-highspeed and MiniMax-M2 were simultaneously removed from the language-model table in the models overview and from the language-model price table on the pay-as-you-go page (the historical-models section for language models in the overview was dropped entirely), so language models now list only M3.1-Flash and M3; the 2026-11-18 retirement date of the M2.5 / M2.7 families is unchanged, and M Plan and Token Plan requests to those generations are routed to M3.1 Flash. The M Plan tier prices and usage multiples (Explore 3x, Build 12x on the Chinese site and 7.5x internationally), the model scope of all three tiers (text models on every tier, video only on Explore and Build) and the credit-pack rules are unchanged
• 2026/10/19: Alibaba Cloud Bailian Token Plan (Personal Edition) added deepseek-v4.1-flash-1017 to its supported models (capabilities listed as reasoning, visual understanding and text generation, placed after deepseek-v4.1-flash) and to the limited-time night 50%-off list — Credits consumption is halved every night from 22:00 to 08:00, so the list now reads deepseek-v4-pro-0813, deepseek-v4-flash-0731, deepseek-v4.1-flash and deepseek-v4.1-flash-1017; the Team Edition's supported-model list includes it as well, and the official OpenCode and OpenClaw integration docs add it to both the personal and team configuration examples (named DeepSeek V4.1 Flash 1017 in OpenCode; contextWindow 1,000,000, maxTokens 393,216, reasoning false and input text plus image in OpenClaw). Tiers and prices (Lite 60 / Essential 120 / Standard 180 / Pro 600 RMB per month, limited-time 39/79/139/499), Credits per tier, usage packs, deduction order and upgrade rules, the night 40% off for qwen3.8-max and qwen3.8-flash, and the limited-time free decision-model-preview are all unchanged
• 2026/10/19: Removed the per-model-credit entries for Command Code (11 entries from 10/15–10/18): the vendor's marketing page returns two alternating sets of "$X available for Y" values across requests (e.g. the GOAT tier alternates between $100 / $80 and $60 / $60), so they are not real changes; monthly credits should be taken from the Monthly credits tables on the docs pages /docs/plans/{go,goat,pro} (currently stable and mutually consistent across the Go / GOAT / Pro pages)

• 2026/10/19: Volcano Engine marked minimax-m3 as "being retired": the model name now carries that label in both the Coding Plan and the Agent Plan model lists, and so does minimax-m3 in the AFP deduction-coefficient table, where it shares a row with doubao-seed-evolving; the official changelog gained a 10.19 entry, "model retirement started: the minimax-m3 model starts being retired", with no concrete retirement date yet. Its deduction coefficient is still 2.5 and it is still available on every tier. The plan tiers and prices, every other model and its deduction coefficient, and the 1M-context support list are unchanged

• 2026/10/19: Alibaba Cloud Bailian added the DeepSeek model deepseek-v4.1-flash-1017 and extended its DeepSeek third-party models to the Hong Kong (China) region. The new model uses peak/off-peak pricing (off-peak 22:00–08:00 UTC+8, peak the remaining hours) at the same unit prices as deepseek-v4.1-flash: 2 CNY (peak) / 1 CNY (off-peak) per 1M input tokens and 8 / 4 CNY per 1M output tokens on the China site and the "Global" deployment, and 2.188 / 1.094 CNY input and 8.75 / 4.375 CNY output internationally, with a free quota of 1M tokens in the 华北2（北京）region. The Hong Kong (China) region currently offers this model alone among DeepSeek models (billed at the Global deployment's peak/off-peak prices). Its context-cache discount matches deepseek-v4.1-flash — cached input tokens are billed at 10% of the input price, in both the peak and off-peak hours of the six regions the section lists. The unit prices and peak/off-peak hours of deepseek-v4.1-flash, deepseek-v4-pro, deepseek-v4-pro-0813 and deepseek-v4-flash-0731, and the pricing rules of every other section and model, are unchanged; this is a version addition and a region extension in Bailian's general model catalogue, and the tiers, prices, quotas and supported-model lists of Token Plan (Personal and Team) and Coding Plan are all unchanged

• 2026/10/17: Command Code's limited-time free Beam 1.0 (model ID beam-free, 1M context, input / output / cache read all Free while capacity lasts) now covers every tier: GOAT and Max include the model too, and the GOAT model table lists 70 models (previously 69). The limited-time free models are now Laguna S 2.1, Glyph Cluster and Cat Jam (on Go, GOAT and Max) plus Beam 1.0 (on every tier — Go, GOAT, Pro, Max 10x and Max 20x). The plan prices and tiers and every other model's price and credits are unchanged

• 2026/10/17: DeepSeek updated the model version behind deepseek-flash to DeepSeek-V4.1-Flash-1017 (previously DeepSeek-V4.1-Flash): requests made with the old model names deepseek-v4-flash and deepseek-v4-flash-vision-exp are now served by DeepSeek-V4.1-Flash-1017 and are still billed at Flash prices, and the Tencent Cloud LLM Token Plan's Enterprise Professional Plan and Personal Universal Token Plan renamed the model from "DeepSeek-V4.1-Flash Official direct-supply" to "DeepSeek-V4.1-Flash-1017 Official direct-supply" (model ID still deepseek/deepseek-flash; the Enterprise plan's separate non-direct-supply version with model ID deepseek-v4.1-flash is unaffected). Token prices and peak/off-peak windows, plan tiers and allowances and every other model are unchanged

• 2026/10/17: OpenCode Go renamed its limited-time free model Cat Jam Free to Beam Free: the rows and notes for the model in the supported-model list, the token-price table (input / output / cache read all Free), both monthly-allowance tables (unlimited for a limited time), the estimated-request table, the endpoint table and the privacy table were renamed, and the model ID changed from cat-jam-free to beam-free. The model is still labelled "limited time, limited regions" with the same list of excluded regions, and its data retention is still 30 days (Model training Not used). The model library still has 29 models, and both plan prices and every other model's prices, allowances and request limits are unchanged

• 2026/10/17: The Tencent Cloud LLM Token Plan published model retirement dates: MiniMax-M2.7 is marked as retiring on 2026-11-17 in both the Personal Edition Universal Token Plan and the Enterprise Professional Plan, and the Enterprise Professional Plan's DeepSeek-V4-Flash 0731 Official (model ID deepseek-v4-flash-0731) is marked as retiring on 2026-10-31, while the Official direct-supply version of the same name is unaffected. The plan tiers and prices, the per-tier credit allowances and every other model's credit prices and availability are unchanged
• 2026/10/17: DeepSeek added separate billing for web search and fetch (Search, Fetch): both cost 5 RMB per 1,000 successful requests; when the DeepSeek API is used in DeepSeek Harness, Claude Code or Codex, the Search / Fetch calls made through server-side tool use are currently not billed and will be charged per request from 00:00 Beijing time on November 1, 2026. The charging rules now read "model usage fee = token consumption × model unit price; Search and Fetch are billed per successful request". The model prices, peak/off-peak windows and concurrency limits of deepseek-flash and deepseek-v4-pro are unchanged
• 2026/10/17: Command Code added a limited-time free model, Beam 1.0 (model ID beam-free, 1M context): input / output / cache read are all Free and it is labelled free while capacity lasts. Go and Pro now include the model — Go lists 57 of the 95 models (previously 56) and Pro lists 85 (previously 84), taking the catalogue from 94 to 95 models; GOAT does not include it and still lists 69 models. The limited-time free models are now Laguna S 2.1, Glyph Cluster and Cat Jam (on Go, GOAT and Max) plus Beam 1.0 (on Go and Pro). The plan prices and tiers and every other model's price and credits are unchanged
• 2026/10/16: OpenCode Go cut its model library (32 → 29 models): Grok 4.6, Kimi K2.6 and MiniMax M2.7 were removed — their rows disappear from the token-price table, both monthly-allowance tables, the estimated-request table, the endpoint table and the privacy table, while in the per-request token estimates the Grok 4.6 and Kimi K2.6 lines were folded into their successors ("Grok 4.7/4.6" → "Grok 4.7", "Kimi K2.7/K2.6" → "Kimi K2.7"), the MiniMax M2.7 line was dropped entirely and the ZDR note changed from "Grok 4.7/4.6" to "Grok 4.7". Plan prices (Go $10 and Go Plus $40 per month) and every remaining model's token prices, monthly allowances and request limits are unchanged
• 2026/10/16: Alibaba Cloud Bailian Token Plan (Personal Edition) updated its subscription and device rules: the device note changed from "for the subscriber's use on a single device" to allowing the same API Key to be configured on several of the subscriber's own devices (such as a home computer and an office computer) while remaining for the subscriber's own use (sharing it with others may be judged a violation and lead to a ban); when a subscription expires the API Key becomes unusable, and once a new subscription is purchased the original API Key works again with no reconfiguration needed (the previous wording said the API Key changes on repurchase and tools have to be reconfigured). The tiers and prices (Lite 60 / Essential 120 / Standard 180 / Pro 600 RMB per month, 39/79/139/499 for a limited time), the per-tier Credits allowances, the usage pack, the deduction order and upgrade rules, the supported models and the limited-time night discounts are all unchanged
• 2026/10/16: OpenCode Go's per-model call endpoints changed to protocol-prefixed paths — OpenAI-compatible https://opencode.ai/inference/go/openai/v1/{chat/completions,responses}, Anthropic-compatible https://opencode.ai/inference/go/anthropic/v1/messages and Google-compatible https://opencode.ai/inference/go/google/v1beta/models/<model-id> (Gemini 4 Argon Contributor); the model-list endpoint is still https://opencode.ai/inference/go/v1/models. Both plan prices, every model's token prices and allowances, and the supported-model list are unchanged
• 2026/10/16: OpenCode Go's limited-time free Step 5 Preview Free ended its free period and became a standard metered model, Step 5 Preview: token prices changed from Free to input $1.00 / output $2.70 / cache read \(0.10 per 1M tokens, the monthly usage allowance is Go ~~\)15~~ \(60** and Go Plus ~~\)60~~ $240 (both marked "4x · Limited time", i.e. a limited-time 4x boost), the estimated requests changed from unlimited to ~~430~~ 1,720 per 5 hours, ~~1,070~~ 4,280 per week and ~~2,130~~ 8,520 per month on Go and ~~1,720~~ 6,880 / ~~4,280~~ 17,120 / ~~8,520~~ 34,080 on Go Plus; the model ID changed from step-5-preview-free to step-5-preview, the per-request estimate is 1,000 input tokens, 55,000 cached tokens and 200 output tokens, and the note "Step 5 Preview Free:** Free for a limited time." was removed. The limited-time free models are now LongCat 2.5 Preview Free and Cat Jam Free, and no other model's price, allowance or request limit changed
• 2026/10/16: Command Code changed its model library (91 → 94 models; Go from 54 to 56, GOAT from 66 to 69 and Pro from 81 to 84): it removed the limited-time free Ling 3.0 Flash Sante and added the limited-time free Cat Jam (free during the stealth preview with requests not consuming credits, input / output / cache read all Free, 1M context), Muse Spark Open (input $1.25 / output $4.25 / cache read $0.15 per 1M tokens, 1M context), Nemotron 3.5 Super VL (0.20 / 0.50 / 0.04 per 1M tokens, 262K context) and Jev 1.14.0 (a decision model with 32K context at 0.042 / 0.00 / 0.00 per 1M tokens, usable only headless via cmd -p and the Provider API). Monthly credits: Muse Spark Open and Nemotron 3.5 Super VL get $6 on Go, $20 on GOAT and $30 on Pro, and Jev 1.14.0 gets $20 on GOAT and $30 on Pro; estimated requests (5 hours / week / month) are 193 / 385 / 642 on Go, 428 / 1,070 / 2,140 on GOAT and 642 / 1,600 / 3,210 on Pro for Muse Spark Open, 796 / 1,590 / 2,650 on Go, 1,770 / 4,420 / 8,850 on GOAT and 2,650 / 6,640 / 13,300 on Pro for Nemotron 3.5 Super VL, and 119,000 / 298,000 / 595,000 on GOAT and 179,000 / 446,000 / 893,000 on Pro for Jev 1.14.0. The limited-time free models are now Laguna S 2.1, Glyph Cluster and Cat Jam (on Go, GOAT and Max), the GOAT plan lists 33 further models beyond its high-credit ones (previously 31), and the plan prices and tiers and every other model's price and credits are unchanged
• 2026/10/15: Tencent Cloud LLM Token Plan completed its 2026-10-09 model retirements and removed GLM-5, GLM-5.1 and GLM-5-Turbo from its model library: the Enterprise Professional Plan's model table and credit-price table drop all three (model IDs glm-5/glm-5-0, glm-5.1/glm-5-1 and glm-5-turbo plus their credit-price rows — GLM-5 at 100/400/1800 for input [0,32k) and 150/600/2200 for 32k+ input, GLM-5.1 at 130/600/2400 and 200/800/2800, GLM-5-Turbo at 120/500/2200 and 180/700/2600, all as cached input / uncached input / output in credits per 1M tokens), and the Personal Edition Universal Token Plan drops GLM-5 and GLM-5.1 from its supported models. The Personal Edition Universal Token Plan now supports Auto, DeepSeek-V4.1-Flash Official direct-supply, DeepSeek-V4-Flash Official direct-supply, DeepSeek-V4-Pro Official direct-supply, MiniMax-M2.7, MiniMax-M3, GLM-5.2, GLM-5.3, GLM-5.3-Flash, Kimi K2.7 Code, Kimi K3, Hy4 preview and MiMo-V2.6-Flash; the Enterprise plan's remaining models, all other credit prices, the plan tiers and prices and every tier's credit allowance are unchanged. The Tencent Cloud LLM Coding Plan's model list likewise dropped GLM-5, leaving Auto (model parameter tc-code-latest) as its only listed model
• 2026/10/15: Command Code added Qwen 3.8 Max Prime (1M context) to the Pro and GOAT plans: token prices are input $4.00 / output $12.00 / cache read $0.50 / cache write $5.00 per 1M tokens, with monthly credits of $20 on GOAT and $30 on Pro; estimated requests are 131 per 5 hours, 327 per week and 654 per month on GOAT and 196 / 490 / 980 on Pro. The number of models covered rises from 90 to 91 (GOAT from 65 to 66, Pro from 80 to 81); every other model's price and credits and the plan prices and contents are unchanged
• 2026/10/15: Command Code's limited-time free Ling 3.1 Flash ended its free period and became a regular pay-as-you-go model: on Go, GOAT and Pro its input / output / cache-read prices changed from Free to $0.30 / $0.90 / $0.06 per 1M tokens (262K context), with monthly credits of $6 on Go, $20 on GOAT and $30 on Pro; estimated requests are 526 per 5 hours, 1,050 per week and 1,750 per month on Go, 1,170 / 2,920 / 5,850 on GOAT and 1,750 / 4,390 / 8,770 on Pro. The limited-time free models are now Laguna S 2.1, Ling 3.0 Flash Sante and Glyph Cluster; the plan tiers and prices and every other model's price and credits are unchanged
• 2026/10/15: OpenCode Go added an availability restriction to its limited-time free model Cat Jam Free: the model is labelled "limited time, limited regions" and its price note now lists the excluded regions — Angola, Belarus, Cambodia, China (including Hong Kong and Macau), Cuba, the Democratic Republic of the Congo, Equatorial Guinea, Iran, Iraq, Laos, Libya, Nigeria, North Korea, Russia, Syria, Turkmenistan, Uzbekistan, Venezuela, and the Crimea, Donetsk and Luhansk regions of Ukraine. The model remains in the supported-model list, the token-price table (input / output / cache read all Free) and the monthly-allowance table (unlimited for a limited time); its model ID cat-jam-free, its endpoint, and every other model's price, allowance and request limits are unchanged
• 2026/10/15: StepFun introduced time-of-day credit deduction for step-5-preview on Step Plan: during peak hours (Monday–Friday 09:00–12:00 and 14:00–18:00 Beijing time) the Credits consumed are twice those of off-peak hours, while all other times are off-peak and are deducted at the regular rate; some legacy subscriptions are exempt. The tiers and allowances are otherwise unchanged — Mini 400M / Plus 1,600M / Pro 8,000M / Max 40,000M Credits per month at 49 / 99 / 199 / 699 RMB per month, 129 / 269 / 539 / 1,889 quarterly and 456 / 936 / 1,860 / 6,666 RMB yearly (quarterly and yearly are paid upfront while Credits are still issued monthly, in 3 and 12 instalments); Credits convert at 1 RMB = 1,000,000 Credits, unused allowance is cleared when it expires and does not roll over, and the booster packs (Small 49 RMB / 400M, Large 99 RMB / 1600M, valid 30 days), the deduction order (whichever expires first), the payment methods (WeChat, Alipay, platform balance) and the supported models (9) are unchanged; the tiers are now named Mini / Plus / Pro / Max (previously Flash Mini / Flash Plus / Flash Pro / Flash Max); the legacy request-count-based Coding Plan is still closed to new buyers
• 2026/10/15: Added a Command Code (commandcode.ai) entry: five plans (all "+ processing fee"; credits are a per-model shared pool and model token prices match upstream official prices — the vendor calls it zero markup) — Go $1/month with $10 in credits (10x, ~9K requests; from 2026-09-28 new subscribers get per-model credits worth \(6–\)10 per model, existing subscribers switch automatically at renewal), GOAT $10/month with $80 in credits (8x, ~75K requests, includes API access, over $100 with deals), Pro $20/month with $80 in credits (45+ models, i.e. all of GOAT plus closed premium models such as Claude/GPT/Gemini), Max $100/month with $150 in credits (up to $300 equivalent with deals, ~219K requests) and the Provider API plan at $15/month pay-as-you-go with zero markup (OpenAI- and Anthropic-compatible endpoints, topped-up credits roll over and never expire); limited-time free models are Laguna S 2.1, Ling 3.0 Flash Sante, Ling 3.1 Flash and Glyph Cluster; the model library includes the vendor's own taste-1 and DeepSeek V4.1 Flash (following the official peak/off-peak pricing)

• 2026/10/14: OpenCode Go changed its model library (33 → 32 models): DeepSeek V4 Flash and DeepSeek V4 Flash Vision Exp were removed and Gemini 4 Argon Contributor was added. The new model's token prices are input $4.00 / output $20.00 / cache read \(0.20 per 1M tokens (no cache-write price), its monthly allowance is Go ~~\)30~~ **\(60** and Go Plus ~~\)120~~ $240 (both marked "2x · Limited time", i.e. a limited-time doubling), its estimated requests rise from 220 to 440 per 5 hours, 540 to 1,080 per week and 1,060 to 2,120 per month on Go and 880 → 1,760, 2,160 → 4,320, 4,240 → 8,480 on Go Plus, model ID gemini-4-argon-contributor, endpoint https://opencode.ai/inference/go/v1/models/gemini-4-argon-contributor (@ai-sdk/google, the only model in the doc using the /v1/models/<model-id> form), and a privacy row of Model training Yes with Data retention Not ZDR plus the note "Your prompts and completions may be used to train future Google models." The two removed DeepSeek models disappear from the supported-model list, the token-price table, both monthly-allowance tables, the estimated-request table, the endpoint table and the privacy table, their two lines are dropped from the per-request token estimates, and the DeepSeek peak/off-peak note changes from "DeepSeek V4.1 Flash / V4 Pro / V4 Flash / V4 Flash Vision Exp" to "DeepSeek V4.1 Flash / V4 Pro"; no other model's price, allowance or request limit changed

• 2026/10/14: MiniMax completed the M Plan migration of its subscription-pricing and pay-as-you-go pages (four pages across the Chinese and English sites). /docs/guides/pricing-token-plan was rewritten from the old Token Plan content (Plus ¥49 / Max ¥119 / Ultra ¥469 per month, internationally $22 / $55 / $132; credit packs ¥30 → 4,489, ¥150 → 22,460 and ¥500 → 74,900 credits, internationally $5 / $25 / $100, valid for 365 days) into an M Plan overview — available models split across the Go / Explore / Build tiers (the M3.1 Flash Preview text model on all three, the H3 video model on Explore and Build only, image and audio models on all three), usage of Go / Explore 3x / Build (12x on the Chinese site, 7.5x internationally), and supported products listing MiniMax Code (officially recommended: sign in to get plan benefits with no separate subscription or API Key) plus Claude Code, Codex, Cursor, OpenCode, Pi, Hermes Agent, OpenClaw and other tools — and the old Token Plan price table and credit-pack table have been removed. /docs/guides/pricing-paygo was reorganised from "pay as you go / API price" into "pricing overview / product pricing", split into model pricing (language, audio, video, image, music), tool pricing (MCP, server-side tools), packages (audio packages, video packages) and billing guides (payment-method comparison, pay-as-you-go billing, package usage rules, FAQ), and gained the audio packages (HD series ¥630 / ¥5,950 / ¥56,000 and Turbo series ¥360 / ¥3,400 / ¥32,000, valid for 1 month / 3 months / 1 year), the video packages, MCP and server-side tools and the billing guides, with every "Token Plan" mention becoming "M Plan" (e.g. the M Plan MCP plugin note for API-vlm). Existing API price figures are unchanged (MiniMax-M3 ≤512K input tokens permanently 50% off at 2.10 / 8.40 / 0.42 and >512K at 4.20 / 16.80 / 0.84, with cache reads discounted to the same degree), and the plan tiers, usage rules and M3 API pricing are unchanged

• 2026/10/14: The Alibaba Cloud Bailian Token Plan (Personal Edition) reworded the monthly quota from "a subscription period running 30 days forward from the subscription date" to "the quota is counted by subscription month", and in the FAQ "each 30 days starting from the subscription date counts as one subscription month" became "the quota auto-refreshes by subscription month", with the worked example of a Standard plan subscribed on 10 September (that subscription month running 10 September to 10 October) deleted. The rule itself is unchanged — still metered by subscription month, still resetting based on the subscription date rather than a fixed calendar date, still pausing service once the quota is exhausted with unused quota not rolling over (the official docs no longer state the specific "30 days"); the tiers and prices (Lite 60 / Essential 120 / Standard 180 / Pro 600 RMB per month, 39/79/139/499 for a limited time), the per-tier Credits allowances, the usage pack, the deduction order and upgrade rules, the supported models and the limited-time night discounts are all unchanged

• 2026/10/14: Volcano Engine extended both deduction-promotion windows: the deepseek-v4.1-flash 50%-off deduction promotion deadline moved from 2026-10-30 18:00 to 2026-12-30 23:59:59 (start unchanged — Agent Plan 2026-09-15 00:00, Coding Plan 2026-09-23 00:00; coefficient 2.5 → 1.25), and the kimi-k2.8-preview 40%-off deduction promotion (Agent Plan, coefficient 8 → 4.8) plus the Coding Plan campaign during which that model's available quota is "comparable to that during the Agent Plan 40%-off deduction promotion" both moved from 2026-10-14 23:59 to 2026-12-14 23:59:59 (starts unchanged — Agent Plan 2026-09-17 00:00, Coding Plan 2026-09-18 00:00). The old 10-30 / 10-14 deadlines expired today; the kimi-k3 50%-off campaign (2026-10-12 00:00 to 2026-10-25 23:59), every other model's deduction coefficient, the plan tiers and prices, the model library and the 1M-context support list are all unchanged

• 2026/10/14: OpenCode Go updated the data policy of its limited-time free model Cat Jam Free: its "Model training" column changed from Yes to Not used and its "Data retention" column from Not ZDR to 30 days, and the corresponding note "Cat Jam Free: During its free period, collected data may be used to improve the model." was removed, leaving only the "Cat Jam Free: Free for a limited time." label. The model remains in the supported-model list, the token-price table (input/output/cache read all Free) and the request/monthly-allowance tables (both unlimited), with the same model ID cat-jam-free and endpoint; the other models' privacy rows, prices and allowances are unchanged

• 2026/10/14: OpenCode Go added the limited-time free Cat Jam Free model: input, output and cache read are all listed as Free, and both the request limits and the monthly usage allowance are labelled unlimited (a limited-time promotion with no end date given by the vendor); model ID cat-jam-free, endpoint https://opencode.ai/inference/go/v1/chat/completions. The supported-model list (32 → 33 models), the token-price table, both monthly-allowance tables, the estimated-request table, the endpoint table and the privacy table all gained this model; in the privacy table its "Model training" column is Yes and its "Data retention" column is Not ZDR, and the doc adds the note "Cat Jam Free: During its free period, collected data may be used to improve the model." No other model's price, allowance or request limit changed

• 2026/10/14: Volcano Engine marked kimi-k2.7-code as "being retired": the model lists of the Coding Plan and Agent Plan all now append "being retired" to that model name (its deduction coefficient remains 4.5 and all tiers remain ticked; no retirement date has been published yet), and the changelog added a 10.13 entry, "model deprecation started: kimi-k2.7-code". Plan tiers and prices, all other models and their deduction coefficients, and the 1M-context support list are unchanged. The Coding Plan's OpenClaw integration doc swapped the model in its image-input configuration example from kimi-k2.7-code to doubao-seed-2.1-lite — an example-only change with no rule change

• 2026/10/13: The GLM Coding Plan added a plan upgrade and renewal rule: after a subscriber upgrades, the points allowance refreshes immediately at the new tier, while renewal does not trigger a points reset and the existing refresh cycle is unchanged. Nothing else changed: plan tiers and prices (Lite 118 / Pro 538 / Max 1078 RMB per month), the 5-hour and weekly points allowances (2000/10000, 12000/60000, 28000/140000), the model and MCP deduction coefficients, the supported models (GLM-5.3, GLM-5.3-Flash), the usage reference table, the off-peak 50% deduction rule, the compatible-tool list and the "save up to 92%" claim are all unchanged. That point-refresh mechanism (the dynamic 5-hour refresh, the weekly cycle and the upgrade/renewal rule above) was added to the main entry

• 2026/10/13: The OpenCode Go docs moved to https://opencode.ai/v2/docs/console/go/ and publish the full data set for all 32 models: token prices (including peak/off-peak windows and token tiers), monthly allowances, estimated requests (5-hour/week/month), per-request token estimates and data retention. The endpoint domain changed from opencode.ai/zen/go/v1/… to https://opencode.ai/inference/go/v1/… (the two domains are aliases), and models can now be referenced inside OpenCode as opencode-go/<model-id> with the model-list endpoint https://opencode.ai/inference/go/v1/models; apart from DeepSeek V4.1 Flash's \(80/\)160 (raised on 2026-10-12), the monthly allowances fall into 6 tiers — \(15/\)60, \(30/\)90, \(30/\)120, \(60/\)120, \(60/\)180 and \(60/\)240 — and the supported-model list is unchanged. Added a Validated clients list (Hermes, Claude Code, Codex, ZCode, Pi, jcode, Kilo Code CLI) and a Known problematic clients list (DeepSeek Harness, GitHub Copilot Chat, Kimi Code, MiMo Code), both about x-opencode-session header support
• 2026/10/13: MiniMax added Pi to the M Plan compatible-tool list: the tool list changed from Claude Code, Codex, Cursor, OpenCode, Hermes Agent, OpenClaw to the same list with Pi inserted between OpenCode and Hermes Agent, and the "MiniMax Code · Official recommendation" item (with the copy "use MiniMax's official agent app for local development and everyday work; sign in to access your M Plan benefits, with no separate subscription or API Key setup") was promoted to its own section; plan tiers and prices, usage rules, credit packs and migration rules are unchanged
• 2026/10/13: Volcano Engine added a limited-time 50%-off deduction coefficient for kimi-k3: from 2026-10-12 00:00 to 2026-10-25 23:59 its Agent Plan deduction coefficient is halved, i.e. 10 → 5, and the AFP coefficient table now reads "10 (5 at a limited-time discount)". The other Agent Plan models' deduction coefficients and the plan tiers and prices are unchanged, and the Coding Plan did not carry this campaign, so its promotions are still only the deepseek-v4.1-flash 50% off and the Kimi-K2.8-Preview quota campaign
• 2026/10/13: Volcano Engine removed three models previously marked "being retired" from its model lists: doubao-seed-2.1-turbo and doubao-seed-2.0-lite (both previously listed in the Coding Plan (Personal Edition) supported-model table, the Agent Plan (Personal Edition) model table and the AFP deduction-coefficient table; their rows are now deleted, and the doubao-seed-2.1-turbo reference in the Agent Plan billing text-deduction example was changed to doubao-seed-evolving) and doubao-seedream-5.0-lite (removed from the Agent Plan image-generation coefficient table along with its image-generation deduction example, leaving doubao-seedream-5-0-pro as the only image model). Plan tiers and prices, all other models and their deduction coefficients, and the 1M-context support list are unchanged
• 2026/10/13: MiniMax published a retirement notice for the M2.5 and M2.7 model families: from 2026-10-19 the models are no longer available to new users, and on 2026-11-18 they are retired. Existing pay-as-you-go API users may keep calling them until the retirement date, after which API requests to these models no longer work; for M Plan and Token Plan users, requests to M2.5 and M2.7 are routed to M3.1 Flash Preview from 2026-10-19, with the original model names kept as compatible entry points (no model-name changes needed) and plan usage entitlements unaffected. The M Plan tiers' supported models, prices and allowances are unchanged
• 2026/10/12: Alibaba Cloud Bailian Token Plan (Personal Edition) added wan3.0-video to its supported models (Wanxiang brand, capability listed as "video generation", placed after wan2.7-image and wan2.7-image-pro). Plan tiers and prices (Lite 60 / Essential 120 / Standard 180 / Pro 600 RMB per month, 39/79/139/499 for a limited time), the per-tier Credits allowances, the usage pack, the deduction order and upgrade rules, the limited-time night discounts (40% off qwen3.8-max/qwen3.8-flash and 50% off deepseek-v4-pro-0813/deepseek-v4-flash-0731/deepseek-v4.1-flash) and the limited-time free decision-model-preview are all unchanged; the Team Edition supported models still do not list wan3.0-video
• 2026/10/12: OpenCode Go raised the usage allowance for DeepSeek V4.1 Flash: the monthly usage allowance rose from $60 / \(120 to **\)80 / $160**, with its estimated 5-hour requests rising from 26,000 / 52,000 to 34,670 / 69,330 — both the allowance and the two tiers' request figures are exactly 4/3 of the old values, so the estimated per-request usage is unchanged. The other 12 featured models are unchanged: Kimi K3 $15 / $60, Kimi K2.7 Code $60 / $180, Space Bunny $30 / $120, MiniMax M3 $60 / $180, Claude Haiku 5.5 $15 / $60, GPT 6 Luna $15 / $60, Qwen3.7 Plus $60 / $180, GLM-5.3-Flash $60 / $180, MiMo-V2.6-Flash $60 / $120, Muse Spark 1.3 Contributor $60 / $120, and LongCat 2.5 Preview Free and Step 5 Preview Free with no limit
• 2026/10/11: Alibaba Cloud Bailian kept pruning legacy model entries, with the unit prices and billing rules of the remaining models unchanged: it dropped qwen-plus-2025-09-11, qwen-plus-2025-07-28, qwen3-omni-flash-2025-09-15, qwen3-omni-flash-realtime (the undated row, keeping qwen3-omni-flash-realtime-2025-09-15), qwen3-vl-flash-2026-01-22 (US), qwen3-vl-plus-2025-09-23 (Global and EU) along with the "current capabilities equivalent to qwen3-vl-plus-2025-12-19" note on the qwen3-vl-plus row (the row itself stays), qwen3-asr-flash-2025-09-08, fun-asr-2025-08-25, qwen3-livetranslate-flash-realtime and its 2025-09-22 version, plus the last two deepseek-v4-flash rows (Global and Japan) in the DeepSeek section; the "Text generation — Qwen open source" chapter dropped four whole sections — Qwen3 (qwen3-next-80b-a3b-thinking / -instruct, qwen3-235b-a22b-thinking-2507, qwen3-30b-a3b-thinking-2507 / -instruct-2507, qwen3-235b-a22b, qwen3-30b-a3b, qwen3-14b, qwen3-8b), Qwen3-Omni-Captioner (qwen3-omni-30b-a3b-captioner), Qwen-VL (qwen3-vl-235b-a22b-thinking, qwen3-vl-32b-thinking / -instruct, qwen3-vl-30b-a3b-thinking / -instruct, qwen3-vl-8b-thinking / -instruct) and Qwen-Coder (qwen3-coder-480b-a35b-instruct, qwen3-coder-30b-a3b-instruct) — so the open-source chapter now only keeps Qwen3.8, Qwen3.6, Qwen3.5 and Qwen-Audio; the Qwen-Omni free-quota note changed from "the Qwen3.5-Omni, Qwen3-Omni and Qwen-Omni-Turbo series" to "the Qwen3.5-Omni and Qwen3-Omni series". Everything dropped is a legacy version or legacy open-source model in Bailian's general model catalogue, and none of it was in the Token Plan Personal or Team Edition supported-model lists (deepseek-v4-flash-0731 remains in both), so there is no user-visible impact on coding plans
• 2026/10/11: The z.ai international release notes were tidied up, dropping a batch of older model entries: GLM-OCR, GLM-4.7-Flash, AutoGLM-Phone-Multilingual, GLM-ASR-2512, GLM-4.6V, GLM-4.5V, GLM Slide/Poster Agent (beta), the GLM-4.5 series and CogVideoX-3, leaving GLM-5.3-Flash, GLM-5.3, GLM-5.2, GLM-5.1, GLM-5, GLM-Image, GLM-4.7 and GLM-4.6. The Chinese site still lists every one of those entries, and neither the international DevPack overview page nor the bigmodel.cn pricing page changed, so this is a release-notes tidy-up rather than a model delisting and it alters no coding plan's supported models, with no user-visible impact
• 2026/10/11: The GLM Coding Plan changed its positioning copy from "only a small outlay covers the whole development flow of requirement understanding, code generation, debugging and fixing, codebase Q&A and automated task handling" to "only a small outlay covers the whole flow from code generation and debugging/fixing to autonomous task decomposition and delivery — Coding and Work in one plan", i.e. the claimed scope was widened from a coding workflow to "Coding and Work in one plan" (in line with the international site's 2026-10-09 change from "coding tools" to "agent tools" and its new Office Work section). Nothing else changed: plan tiers and prices (Lite 118 / Pro 538 / Max 1078 RMB per month), the 5-hour and weekly points allowances, the model and MCP deduction coefficients, the supported models (GLM-5.3, GLM-5.3-Flash, with GLM-5.2/5.1 auto-switching to GLM-5.3 and GLM-5-Turbo/GLM-4.7 to GLM-5.3-Flash), the usage reference table, the compatible-tool list (ZCode, AutoClaw, Claude Code, Codex, OpenCode, WorkBuddy) and the "save up to 92%" claim, so there is no user-visible impact
• 2026/10/10: Alibaba Cloud Bailian delisted a batch of older models: it dropped a large number of legacy entries with the unit prices and billing rules of the remaining models unchanged: the qwen3-max family (qwen3-max, qwen3-max-2026-01-23, qwen3-max-2025-09-23, qwen3-max-preview), qwen3.6-max-preview, qwen3-coder-plus, qwen3-coder-next, qwen-turbo, qwq-plus, qvq-max/qvq-plus, qwen-math-plus/qwen-math-turbo, qwen-long-latest/qwen-long-2025-01-25, the old Qwen-Omni series (qwen-omni-turbo and its versions, qwen3-omni-flash-2025-12-01/2025-09-15, the qwen-omni-turbo-realtime series), qwen3-vl-flash, qwen-vl-max, qwen-vl-plus, deepseek-v4-flash (the China-site and "Global"/"US"/"International" rows; only the "Global" and "Japan" deployment rows remain), deepseek-v3.2, deepseek-v3.2-exp, deepseek-v3.1, deepseek-v3, deepseek-r1, deepseek-r1-distill-qwen-7b/14b/32b and llama-8b (already marked discontinued), glm-4.7, glm-4.6, glm-4.5, glm-4.5-air, MiniMax-M2.1, kimi-k2-thinking, Moonshot-Kimi-K2-Instruct, the old qwen-image-max/qwen-image-plus and qwen-image-edit series plus legacy image sections such as "image background generation" and "image outpainting", and the China-site rows for open-source models such as qwen3-32b and qwen3-vl-32b/30b/8b; the context-cache supported lists likewise removed deepseek-v3.2, deepseek-v4-flash, qwen3-coder-plus, qwen-turbo, qwen3-vl-flash, qwen-vl-max/qwen-vl-plus, glm-4.6 and MiniMax-M2.1 from its supported-model lists. Impact on coding plans: the integration docs (OpenCode and OpenClaw) removed deepseek-v4-flash and deepseek-v3.2 from their bailian-token-plan/* model lists; the Token Plan Team Edition supported models no longer list either model and do include glm-5.3 and deepseek-v4.1-flash (the main entry has been updated); the Token Plan Personal Edition supported models are unchanged, as they already listed only deepseek-v4-flash-0731 and never deepseek-v4-flash or deepseek-v3.2
• 2026/10/10: The Alibaba Cloud Bailian Coding Plan cut back the Pro plan's supported models: the official docs dropped qwen3-max-2026-01-23, qwen3-coder-next, qwen3-coder-plus and glm-4.7 from the "more models" tier, which now lists qwen3.5-plus (image understanding) alone; the recommended models (qwen3.7-plus, qwen3.6-plus, kimi-k2.5, glm-5, MiniMax-M2.5), the price (¥200/month, ¥39.90 for the first month for new subscribers) and the request limits (6,000 per 5 hours, 45,000 per week, 90,000 per month) are unchanged. The rest of the docs were updated in step: the FAQ removed those four models from its context-length table (qwen3-max-2026-01-23 262,144, qwen3-coder-next 262,144, qwen3-coder-plus 1,000,000, glm-4.7 202,752) and dropped qwen3-coder-plus from its "switch model" advice, and the OpenClaw configuration example's model ID changed from qwen3-max-2026-01-23 to qwen3.7-max; the integration docs (OpenCode and OpenClaw) removed the same four models from their bailian-coding-plan/* list, which now contains qwen3.7-plus, qwen3.6-plus, qwen3.5-plus, MiniMax-M2.5, glm-5 and kimi-k2.5
• 2026/10/10: The CTCloud Programming Token Plan's previous token-metered plans (renewable by existing subscribers only) completed the delisting that had been scheduled for that day: GLM-5.0 and DeepSeek-V3.2 (written "DeepSeeV3.2" by the vendor), previously marked as "retiring 10 October", were dropped from the list while GLM-5.2 was added, leaving DeepSeek-V4-Flash-0731, GLM-5.1 and GLM-5.2. The Credits Edition's tiers and prices (29/89/199/399/699 RMB per month), credit allowances, supported models (DeepSeek-V4-Pro, DeepSeek-V4-Flash-0731, GLM-5.2, GLM-5.1, Kimi-K2.6, MiniMax-M3) and credit-conversion table are unchanged
• 2026/10/09: Alibaba Cloud Bailian added the image model qwen-image-2.1-turbo: 0.1 CNY per image on the China site and the "Global" deployment (10 free images) and 0.113362 CNY per image internationally, listed alongside qwen-image-2.1-pro (0.25 / 0.283404 CNY per image); the unit prices of the rest of the qwen-image-2.0 series and of all text models are unchanged. This change only concerns image-generation pricing in Bailian's general model catalogue and alters no coding plan's model library, tiers or quotas, the Token Plan included
• 2026/10/09: The Kimi Code API gained support for the OpenAI Responses protocol: the OpenAI-compatible interface now offers both the Chat Completions and Responses protocols, with the endpoint https://api.kimi.com/coding/v1/responses on the domestic domain (no overseas example given). The Base URLs, the Anthropic-compatible endpoints, model IDs and API prices are unchanged
• 2026/10/09: Infini (Wuwen Xinqiong) GenStudio took deepseek-v4-flash offline at 12:00 on 2026-10-09 as previously announced, with the recommended replacement model still deepseek-v4.1-flash. The platform's Infini Coding Plan was discontinued on 2026-06-27, so this change only affects GenStudio API calls
• 2026/10/09: Zhipu GLM Coding Plan's two limited-time campaigns both expired: the "GLM-5.3-Flash Usage Campaign" (2026-09-03 to 2026-10-07, unlimited GLM-5.3-Flash usage on ZCode/AutoClaw with doubled quota on other agents) and the "Double Festival" campaign (2026-09-25 to 2026-10-07, all-day usage billed at the off-peak rate). Both sites are back to the regular rule (off-peak hours consume points at 50% of the base rate; peak hours are weekdays 14:00–18:00 (UTC+8)), with no campaign running. The Chinese site changed its copy from "a subscription plan built for AI coding" to "a subscription plan for large-model usage", and rewrote the compatible-tool list from "Claude Code, Kilo Code, OpenClaw, OpenCode, TRAE, CodeBuddy" to "ZCode, AutoClaw, Claude Code, Codex, OpenCode, WorkBuddy". The international version changed "coding tools" to "agent tools", with the applicable tools changed from "Claude Code, Cline, OpenCode" to "ZCode, Claude Code, Codex, OpenCode, AutoClaw, OpenClaw", added an "Office Work" section (Deep Search & Research, Business Data Analysis, Creative Ideation & Brainstorming, Automated Task Execution), changed the two "Advantages" headings to "Access to High-Intelligence Models" and "Works with 20+ Agent Tools", and changed the FAQ quota-sharing wording from "All supported coding tools share the same usage quota" to "All supported tools share the same usage quota". Plan tiers and prices (from 18 USD per month), points allowances, deduction coefficients, model coverage and the "save up to 92%" claim are unchanged
• 2026/10/08: The Token Plan intro and FAQ pages on both the Chinese and English MiniMax sites (/docs/token-plan/intro and /docs/token-plan/faq on platform.minimaxi.com and platform.minimax.io — four pages) were rewritten from the old Token Plan content to M Plan content, effectively completing the site migration. The pages state that the Build tier's allowance is 12x Go on the Chinese site while the English site still says 7.5x (the two sites disagree; the main entry above records them separately). The tier model coverage (all three tiers include the M3.1 Flash Preview text model plus image/audio generation, web search and multimodal understanding; Explore and Build add the H3 video model while Go has no video) and the rules "non-video models are subject to 5-hour and weekly windows, video models only to the weekly window" and "1,000 credits = ¥7, valid for 1 year" are unchanged. Points added by the FAQ include: the Subscription Key works with any OpenAI- or Anthropic-compatible tool (Claude Code, Codex, Cursor, OpenCode, Hermes Agent and OpenClaw are listed), MiniMax Code needs no separate subscription or Subscription Key, downgrades are not supported (monthly plans upgrade to a higher monthly or annual tier; annual plans only to a higher annual tier), auto-renewal cannot be restored once disabled, both the 5-hour and weekly windows start on first use and refresh independently, exhausting the quota never charges the account balance automatically, and a 401 after login can be fixed by setting the region manually with mmx config set --key region. Meanwhile /docs/guides/pricing-token-plan (subscription pricing) and /docs/guides/pricing-paygo are still on the old Token Plan / pay-as-you-go content and have not been migrated yet
• 2026/10/08: Baidu Qianfan Coding Plan cut its model library down sharply and announced that model updates have stopped: the deduction-coefficient table and the configurable model list now contain only DeepSeek-V4-Pro (peak 5 / off-peak 4), GLM-5.1 (peak 4 / off-peak 3) and Baidu Search (10), removing Kimi-K2.5, DeepSeek-V3.2, DeepSeek-V4-Flash, GLM-5, MiniMax-M2.5 and ERNIE-4.5-Turbo-20260402 (the Model Names that can be set in the config file dropped from six to deepseek-v4-pro and glm-5.1); the previous "DeepSeek-V4-Flash and GLM-5.1 are trial versions with limited resources" sentence was replaced by the new notice "the supported model range will be adjusted dynamically with model iterations. Coding Plan has stopped model updates; users who need newer models are advised to migrate to Token Plan (Personal Edition)". Plan prices and limits (Lite ¥40, Pro ¥200 per month, 1,200 / 6,000 requests per 5 hours) are unchanged
• 2026/10/08: OpenCode Go added Claude Haiku 5.5 and the limited-time free Step 5 Preview Free. Claude Haiku 5.5 is tiered at 100K tokens (≤100K tokens input $0.10, output $0.50, cache read $0.01, cache write $0.125; >100K tokens input $0.50, output $2.50, cache read $0.05, cache write $0.625 per 1M tokens), with a monthly usage allowance of $15 on Go and $60 on Go Plus, estimated request limits of 3,850 / 5 hours, 9,620 / week and 19,230 / month on Go and 15,380 / 38,460 / 76,920 on Go Plus, a per-request usage estimate of 1,100 input tokens, 55,000 cached tokens and 240 output tokens, model ID claude-haiku-5-5, endpoint https://opencode.ai/zen/go/v1/messages (@ai-sdk/anthropic) and 30-day data retention under Anthropic's data policy. Step 5 Preview Free has free input/output/cache read with unlimited requests and monthly allowance (limited-time; no end date given), model ID step-5-preview-free, endpoint https://opencode.ai/zen/go/v1/chat/completions. The supported-models, token-price, request-limit, endpoint and data-retention tables all gained rows for the two models, while no other model's prices, allowances or request limits changed

• 2026/10/08: Volcengine Ark Agent Plan (Personal Edition) widened the scope of its daily limit (reset at 00:00:00 every day) from "visual models only" to "visual models, speech models and Harness only" (this matches what the KB already says, so no substantive rule change); the announcement "Agent Plan package free ArkClaw benefit adjustment notice" was swapped for "Agent Plan Personal Edition & Professional Dataset joint promotion". Plan prices, tier allowances and all model deduction coefficients are unchanged

• 2026/10/06: OpenCode Go's Space Bunny Free limited-time free offer ended and the model became the regular paid model Space Bunny: token prices are input $0.15, output $0.60 and cache read \(0.03 per 1M tokens (identical on Go and Go Plus), with a monthly usage allowance of **\)30** on Go and $120 on Go Plus (no longer unlimited); estimated request limits are 3,130 / 5 hours, 7,810 / week and 15,630 / month on Go, and 12,500 / 5 hours, 31,250 / week and 62,500 / month on Go Plus, with a per-request usage estimate of 1,000 input tokens, 55,000 cached tokens and 200 output tokens. The model ID changed from space-bunny-free to space-bunny, the endpoint is unchanged (https://opencode.ai/zen/go/v1/chat/completions) and the data-retention table was renamed accordingly; the model's "limited-time" marker and the "Space Bunny Free: limited-time free." note were removed, while no other model's prices, allowances or request limits changed

• 2026/10/03: Alibaba Cloud Bailian added the image model qwen-image-2.1-pro (text-to-image and image-to-image / image editing, billed per image), costing 0.25 CNY per image on the China site and the "Global" deployment (10 free images) and 0.283404 CNY per image internationally; the qwen-image-2.0 series (qwen-image-2.0-pro and its 2026-06-22/2026-04-22/2026-03-03 versions at 0.5 CNY per image, qwen-image-2.0 and its 2026-03-03 version at 0.2 CNY per image; internationally 0.550443 / 0.256873 CNY per image; 100 free images each) keeps its unit prices and free quotas unchanged. This change only concerns image-generation pricing in Bailian's general model catalogue and alters no coding plan's model library, tiers or quotas, the Token Plan included
• 2026/09/30: MiniMax launched M Plan to succeed Token Plan (announcement dated 2026-09-29): M Plan has three tiers — Go (¥49 / $22), Explore (¥119 / $55) and Build (¥469 / $132) — with the M3.1 Flash Preview text model and H3 video on Explore/Build; annual billing costs 10 months for 12; the first month is 50% off during the launch (through 2026-10-14); 1,000 credits = ¥7 (international $1). Token Plan is no longer sold; existing subscribers keep their plan and benefits if auto-renewal stays on (retaining historical perks such as unlimited quotas and the 150% weekly quota), and can upgrade to M Plan (Plus → Go/Explore/Build, Max → Explore/Build, Ultra → Build); after upgrading you cannot return to Token Plan
• 2026/09/30: Tencent Cloud LLM Token Plan expanded and reshuffled its model library: the Enterprise Professional Plan (Guangzhou/Singapore) added three models — Hy4 preview, MiMo-V2.6-Pro and MiMo-V2.6-Flash — removed the flat-credit-priced deepseek-v4-flash (the variant without the "0731 Official" suffix), and completed the two Official direct-supply model names to "DeepSeek-V4-Flash 0731 Official direct-supply" and "DeepSeek-V4-Pro 0813 Official direct-supply" (model IDs unchanged); credit prices were published for the three new models — Hy4 preview cached input 30 / uncached input 600 / output 1800 (identical in both regions, estimated blended price ~158, 500K credits covering roughly 3.165B tokens), MiMo-V2.6-Pro 2.5/300/600 in Guangzhou and 2.59/313.05/626.1 in Singapore (blended ~107 / ~112), MiMo-V2.6-Flash 2/100/200 in Guangzhou and 2.02/100.75/201.5 in Singapore (blended ~33), all in credits per 1M tokens with no peak/off-peak distinction. The Personal Edition Universal Token Plan added DeepSeek-V4.1-Flash Official direct-supply (model ID deepseek/deepseek-flash) and MiMo-V2.6-Flash to its supported models, with tier credit allowances and the Hy Token Plan unchanged. On peak-valley billing, the Singapore region is now unified to the same wording as Guangzhou ("peak hours are weekdays (Mon–Fri) 9:00–12:00 and 14:00–18:00 with all other times off-peak, weekends billed at off-peak rates all day; effective for Official direct-supply models from 2026-08-29 00:00 and for other DeepSeek models except deepseek-v4-flash and deepseek-v4-pro from 2026-09-26 00:00"); in the Guangzhou price table the Auto row was renamed from "Auto intelligent routing" to "Auto model" (matching Singapore), and the DeepSeek disclaimer changed from enumerating specific model names to "model services supplied directly by DeepSeek". Peak/off-peak unit prices, all other model credit prices and plan prices are unchanged
• 2026/09/30: MiniMax renamed "Token Plan" to "M Plan" in its official documentation: every "Token Plan" mention in the official docs (models overview and pay-as-you-go pricing, four pages across the Chinese and English sites) has been replaced by "M Plan" (e.g. "available only through M Plan and MiniMax Code for now", the "M Plan MCP" plugin, and "when API-vlm is called through M Plan, usage deducts from the included M Plan quota according to its pay-as-you-go price"), and the docs site's Pricing menu and documentation tab bar now list M Plan (pointing to /docs/m-plan/intro) with the old Token Plan tab hidden and the external link changed to https://www.minimax.cn/m-plan; the Token Plan FAQ and Token Plan intro pages still say "Token Plan" (as does the pay-as-you-go page's "resource coverage is the same as Token Plan" sentence and its link to the Token Plan pricing page), showing the rename was still in progress. (Re-checked on 2026-09-30: M Plan is in fact a new tier structure succeeding Token Plan — see the entry above.)
• 2026/09/29: Volcano Engine extended the kimi-k2.8-preview 40%-off deduction promotion window from 2026-09-30 23:59:59 to 2026-10-14 23:59:59: in the Agent Plan the limited-time 40% off (4.8) on the model's deduction coefficient of 8 now runs until the later date (start 2026-09-17 00:00 unchanged); in the Coding Plan the window during which this model's available quota is "comparable to that during the Agent Plan 40%-off deduction promotion" likewise moved from 2026-09-18 00:00 - 2026-09-30 23:59 to 2026-10-14 23:59. The Agent Plan (Personal Edition) billing, Agent Plan (Personal Edition) overview and Coding Plan (Personal Edition) overview were updated together; plan prices, tier quotas and every other model's deduction coefficient are unchanged
• 2026/09/29: The Alibaba Cloud Bailian Token Plan Personal Edition added one sentence below the upgrade proration formula — "the actual prorated amount is subject to the price breakdown shown on the payment page" — while the proration formula, the worked example and all tier prices are unchanged
• 2026/09/29: The Usage limits section of the OpenCode Go doc (zh-cn) dropped its illustrative example: the paragraph "e.g. if a model's monthly limit on Go is $60 and on Go Plus $120 …" and the sentence "when counting across models, the 5-hour, weekly and monthly allowances on Go are $12, $30 and $60 respectively; on Go Plus they are $48, $120 and $240" were removed entirely, leaving only "each model's 5 hours = 20% of the monthly limit, week = 50%, month = 100%" and "each model's monthly limit below determines how its usage counts toward these allowances"; the per-model monthly allowance table, the token price table and the request limit table are unchanged, so the cross-model totals are no longer stated in the doc
• 2026/09/28: The Volcengine Agent Plan Personal edition overview and billing doc (AFP deduction rules) mark doubao-seedream-5.0-lite as "being retired" (both the model-table row and the model name in the AFP deduction example; every tier is still ticked, and no retirement date has been given by the vendor)
• 2026/09/28: The MiniMax Token Plan FAQ gained two new sections ("Subscription Entitlement Adjustment" and "Token Plan Migration Guide"), the first official documentation of the tier migration and compensation rules: Max-hs (\(80/month) and Ultra-hs (\)150/month) are retired and migrate to Max / Ultra (monthly fee down $30 in both cases, with roughly $60 of equivalent credits granted each month; annual plans receive those grants month by month, each valid for 1 year and non-rolling); Starter and Plus-hs become existing-subscriber-only legacy tiers and are no longer sold to new users; benefits promised to users who subscribed before 2026-06-05 remain in effect and the validity of compensation credits is corrected automatically from 1 month to 1 year; Plus/Max keep their prices while M2.7 5-hour usage rises about 10% and M3 access plus multimodal quota are added; credits can be used across most platform models (MiniMax H3 not supported yet) and are shared across modalities. Note that the FAQ's migration section still quotes Plus $20 / Max $50 / new Ultra $120, which does not match the \(22/\)55/$132 on the international pricing page (the FAQ was not updated for the 2026-08-26 price increase)
• 2026/09/28: OpenCode Go added a **Go Plus (\(40/month)** plan alongside Go (\)10/month): token prices are identical on both plans and Go Plus only raises the per-model usage limits — each model's monthly allowance is generally 2–8x that of Go (mostly 4x, e.g. GLM-5.3 \(15→\)120, GLM-5.3-Flash \(60→\)180, Kimi K2.6 \(60→\)240, DeepSeek V4 Flash \(30→\)120), while the cross-model totals are \(12/\)30/$60 (5 hours/week/month) on Go and \(48/\)120/$240 on Go Plus; the subscription entry point was renamed from OpenCode Zen to OpenCode Console, and each workspace still allows only one member to subscribe to Go or Go Plus. The same update removed GLM-5.1, Qwen3.7 Max, Qwen3.6 Plus and MiniMax M2.5 from the supported models (Omen Alpha is no longer supported either; the kb no longer lists it as a supported model)
• 2026/09/27: OpenCode Go added the limited-time free LongCat 2.5 Preview Free model: input, output and cache read are all Free, with the request limits and the monthly usage allowance both listed as unlimited (a limited-time promotion with no end date given by the vendor); model ID longcat-2.5-preview-free, endpoint https://opencode.ai/zen/go/v1/chat/completions (the supported model list, token price table, request limit table, endpoint table and data retention table all gained this model; pricing and allowances of other models are unchanged)
• 2026/09/26: The 4x boost of the OpenCode Go DeepSeek V4.1 Flash quota has changed from a limited-time promotion into a standard value: in the pricing table the model's monthly usage allowance changed from "~~\(15~~ **\)60** 4x · ends Sep 27" to a plain $60, and the estimated-request table likewise changed "~~6,500~~ 26,000 (4x · ends Sep 27)" to 26,000 / 65,000 / 130,000 — the old $15 and 6,500/16,250/32,500 baselines and the promotion end-date annotation have been removed entirely, i.e. the boosted allowance and the raised request limits are now the model's regular quota; token pricing unchanged (off-peak input $0.15/1M, output $0.60/1M, cache read $0.003/1M; peak pricing is double)
• 2026/09/25: The Infini (Wuwen Xinqiong) GenStudio changelog published a "2026-10-09 release preview": deepseek-v4-flash will be retired at 12:00 on 9 October 2026, with deepseek-v4.1-flash recommended as the replacement model — migrate in advance (this platform's Infini Coding Plan was already discontinued on 2026-06-27; this change affects GenStudio API calls)
• 2026/09/25: Alibaba Cloud Bailian added the domain model decision-model-preview and brought it into the Token Plan Personal Edition: model pricing gained a "decision models" section (billed on input tokens, with decision-model-preview marked "limited-time free" as its input price, covering both China North 2 (Beijing) and Singapore), the "Choose a model" list gained a "decision models" category described as "a structured decision model for high-frequency business judgement that completes classification, yes/no decisions and scoring in a single forward pass and returns a probability distribution and confidence" (model detail page /zh/model-studio/decision-model-preview), and the Token Plan Personal Edition added to its benefits "decision-model-preview is free for a limited time: calls consume no Credits, see Connecting to the decision model for setup" plus a new row in the supported-model table "domain model / decision-model-preview / decision model"
• 2026/09/25: The Tencent Cloud Token Plan Enterprise Professional Plan rewrote its DeepSeek peak-valley billing rule and added a non-Official-direct-supply DeepSeek-V4.1-Flash: the notes changed from "Official direct-supply models are billed at off-peak rates all weekend; Official models have peak hours Mon–Sun" to a unified "all DeepSeek models have peak hours on weekdays (Mon–Fri) 9:00–12:00 and 14:00–18:00 with all other times off-peak, and weekends (Sat-Sun) are billed at off-peak rates all day", plus new effective dates — Official direct-supply models from 2026-08-29 00:00 Beijing time, and other DeepSeek models (except deepseek-v4-flash and deepseek-v4-pro, which are billed at flat credits and have no peak/off-peak split) from 2026-09-26 00:00 Beijing time; that means platform-hosted models such as DeepSeek-V4-Flash 0731 Official and DeepSeek-V4-Pro 0813 Official also get the all-day off-peak weekend rate from 26 September. This update was applied only to the Guangzhou region; the Singapore region still carries the old wording. The model library (both Guangzhou and Singapore) also added the non-Official-direct-supply DeepSeek-V4.1-Flash (model ID deepseek-v4.1-flash, coexisting with the official direct-supply deepseek/deepseek-flash), whose credit prices are identical to the Official direct-supply version — cached input 2 / uncached input 100 / output 400 (off-peak), 4 / 200 / 800 (peak) credits per 1M tokens, an estimated blended price of ~26 / ~51 credits per 1M tokens
• 2026/09/24: Alibaba Cloud Bailian added a peak/off-peak time definition to its DeepSeek third-party models: "busy hours are 08:00–22:00 Beijing time, idle hours are 22:00–08:00 the next day" — i.e. the DeepSeek models whose prices are split into peak/off-peak are charged with 08:00–22:00 as peak and 22:00–08:00 as off-peak each day (the same window as the Bailian Token Plan Personal Edition night discount). No prices or other billing rules changed
• 2026/09/24: OpenCode Go added GPT 6 Luna to its model list: billed in 272K-token tiers — up to 272K tokens input $0.10 / output $0.50 / cache read $0.01 / cache write $0.125 per 1M tokens, above 272K tokens \(0.20/\)0.75/\(0.02/\)0.25; the input and cache prices are exactly half of GPT 5.6 Luna's and the output price is lower (was $1.20), while GPT 5.6 Luna stays in both the model list and the pricing table. Monthly usage allowance $15, request limits 4,230 per 5 hours, 10,560 per week, 21,130 per month; model ID gpt-6-luna, endpoint https://opencode.ai/zen/go/v1/responses (the data-retention note was updated from "GPT 5.6 Luna" to "GPT 6 Luna / GPT 5.6 Luna")
• 2026/09/23: The Zhipu GLM Coding Plan "GLM-5.3-Flash Usage Campaign" extended its eligible clients from ZCode to ZCode and AutoClaw (autoclaw.zhipuai.cn): plan users get unlimited GLM-5.3-Flash usage on both clients, with the campaign period and other terms unchanged (2026-09-03 to 2026-10-07, daily 23:00–09:00; doubled quota on other agents)
• 2026/09/23: OpenCode Go added the limited-time free Space Bunny Free model: input, output and cache read are all Free, with the request limits and monthly usage allowance both listed as unlimited; model ID space-bunny-free, endpoint https://opencode.ai/zen/go/v1/chat/completions (the vendor gave no end date for this limited-time promotion)
• 2026/09/23: The Volcano Engine Coding Plan (Personal Edition) and Agent Plan (Personal Edition) model libraries were updated: added doubao-seed-2.1-pro (new-generation flagship model with all-round capability gains, 1024k context window / 256k output), doubao-seed-2.1-lite (lightweight and efficient, 1024k context window / 256k output), doubao-seed-2.0-mini (ultra-fast responses, 256k context window / 128k output) and deepseek-v4.1-flash (the lightweight flagship of DeepSeek's new-architecture series, 552B total-parameter MoE, natively capable of multimodal vision understanding, 1024k context window / 384k max output; it had already joined the Agent Plan and now joins the Coding Plan); doubao-seed-2.1-turbo and doubao-seed-2.0-lite are marked "being retired" (the official announcement calls it "model retirement initiated"), and doubao-seedance-1.5-pro was removed from the Agent Plan model table; the Agent Plan deduction coefficients were updated accordingly — doubao-seed-2.1-pro 2.5, doubao-seed-2.1-lite 0.5 (4.5 with audio input), and doubao-seed-2.0-mini refined to 0.25 without audio input / 2.5 with audio input; both the Coding Plan and Agent Plan 1M-context supported lists now include deepseek-v4.1-flash (Agent Plan list: doubao-seed-evolving, glm-5.3, glm-5.3-flash, kimi-k3, kimi-k2.8-preview, deepseek-v4.1-flash, deepseek-v4-flash, deepseek-v4-pro)
• 2026/09/23: The Volcano Engine deepseek-v4.1-flash limited-time 50%-off deduction window was extended and expanded to the Coding Plan: in the Agent Plan the promotion deadline moved from 2026-09-28 23:59 to 2026-10-30 18:00 (start unchanged at 2026-09-15 00:00, deduction coefficient 2.5 → 1.25), and the Coding Plan added the same promotion for 2026-09-23 00:00 to 2026-10-30 18:00
• 2026/09/23: The CTCloud Programming Token Plan switched to credit metering and gained a "Programming Token Plan (Credits Edition)": tiers and prices are unchanged (29/89/199/399/699 RMB per month) but the quota changed from a fixed token allowance to 3,000/10,000/25,000/50,000/100,000 credits per subscription month, and the supported models became DeepSeek-V4-Pro, DeepSeek-V4-Flash-0731, GLM-5.2, GLM-5.1, Kimi-K2.6 and MiniMax-M3 (GLM-5.0 and DeepSeek-V3.2 moved out). A "credit-to-model conversion" table was added (tokens per credit, input/output — DeepSeek-V4-Pro 1,111/370, DeepSeek-V4-Flash 3,333/1,111, GLM-5.2 1,250/357, GLM-5.1 input [0,32k] 1,667 (output 417) and input (32k,200k] 1,250 (output 357), Kimi-K2.6 1,538/370, MiniMax-M3 input [0,512k] 4,762 (output 1,190) and input (512k,1M] 2,381 (output 595)) plus a note that the model library is updated dynamically and no given model is guaranteed permanently. The previous token-metered plans are labelled "old plans being retired — only existing subscribers may renew, new purchases not supported", with their supported models now DeepSeek-V4-Flash-0731, GLM-5.1, GLM-5.0 (retiring 2026-10-10) and DeepSeek-V3.2 (written "DeepSeeV3.2" by the vendor, retiring 2026-10-10)
• 2026/09/23: The Kuaishou Wanqing (StreamLake/Vanchin, the platform behind the KwaiKAT Coding Plan) model list added DeepSeek-V4.1-Flash (listed in the multimodal section: deep thinking + image understanding, 1M context / 384K max output, native multimodal visual understanding, default rate limit RPM 10 / TPM 300,000); Wanqing's pay-as-you-go model catalog does not state whether the model is covered by the KwaiKAT Coding Plan quota
• 2026/09/23: Alibaba Cloud Bailian Token Plan (Personal Edition) abolished the weekly limit and switched to a subscription-month quota: the Personal Edition moved from a "fixed 7-day window quota" to a monthly quota — a subscription month runs 30 days from the subscription date, and once cumulative consumption within the subscription month reaches the plan quota, service is paused until the quota resets in the next subscription month (auto-refreshed based on the subscription date, not a fixed calendar date), with unused quota not rolling over; per-tier quotas were adjusted to Lite 11,500 / Essential 25,500 / Standard 45,000 / Pro 180,000 Credits per month (tiers and prices unchanged, limited-time prices 39/79/139/499 RMB per month), and the remaining quota of existing subscriptions was reset once to the full monthly quota of the corresponding plan on 2026-09-22 with the subscription cycle and expiry date unchanged; the previous "reset card / quota reset entitlement" (the "Reset quota" button and reset-count notes) was removed entirely, with quota resets now handled automatically each subscription month; the deduction order became "each request is deducted first from the current subscription month's plan quota, and once exhausted, from Usage Pack quota", and Usage Packs are no longer described as "not subject to the 7-day window limit" but rather as "neither occupying nor counting toward the plan monthly quota"; the upgrade rule changed so that the current subscription cycle is not reset — the price difference is paid as (new plan price − old plan price) × remaining days ÷ 30 (partial days counted as a full day), and the new quota for the current cycle is granted as remaining days ÷ 30 × (new monthly quota − old monthly quota), rounded up, with the new tier's monthly quota applying from the next subscription month; the 429 error message changed from insufficient_quota: Your token-plan 1-week quota has been exhausted. to insufficient_quota: Your token-plan quota has been exhausted.; the Team Edition FAQ comparison table's "Personal Edition quota mechanism" was updated to "monthly quota, auto-refreshed per subscription month", and the Team Edition overview table dropped the "7-day limit: unlimited" row
• 2026/09/22: The SenseTime SenseNova API docs (including the TokenPlan credits rules and model overview) changed their model library: DeepSeek V4 Pro was removed from the model overview and DeepSeek V4.1 Flash was added (model ID deepseek-flash, 1M context, image input support), while DeepSeek V4 Flash (deepseek-v4-flash) stays listed. The corresponding model sections were rewritten and gained an image-input section with limits (single image ≤50 MB, ≤200 images per request, ≤64 MB per request body, ≤200 MB total for URL-passed images; video input is only supported by the Chat Completions API), max_tokens now defaults to 131072 (range 1–393216, thinking is truncated when it exceeds the limit), reasoning_effort has native none/low/high/max levels with compatibility mappings, and explicit caching is stated as unsupported
• 2026/09/22: Zhipu GLM Coding Plan (announced on both the China site bigmodel.cn and the international z.ai DevPack) added two limited-time campaigns: the "GLM-5.3-Flash Usage Campaign" — from 2026-09-03 to 2026-10-07, daily 23:00–09:00, plan users get unlimited GLM-5.3-Flash usage via ZCode plus doubled quota on other agents; and the "Double Festival" campaign — from 2026-09-25 to 2026-10-07 all-day usage is charged at the off-peak rate (50% points consumption around the clock). The vendor notes that stacking the night campaign on top makes the actual available quota far higher than the allowance reference table suggests
• 2026/09/22: Alibaba Cloud Bailian model calling prices, model library and context cache updated: the Stepfun deployment added stepfun/step-5-preview (7 CNY input / 20 CNY output per million tokens, no free quota, alongside stepfun/step-3.7-flash at 1.35/8.1 CNY) and the Unisound section lists unisound/unisound-u2 (1 CNY input / 2 CNY output); a new "audio generation" billing section was added (qwen-audio-3.1-tts-next, billed on input and output tokens at 6/12 CNY); speech recognition added the Qwen-Audio-3.1 series and switched from per-second audio billing to per-token billing — qwen-audio-3.1-asr-flash-message and qwen-audio-3.1-asr-flash-streaming cost 6/4.5 CNY (international 6.781/5.104 CNY), qwen-audio-3.1-asr-flash-filetrans and qwen-audio-3.1-asr-flash cost 0.8/2.7 CNY (international 1.094/3.427 CNY), while the 3.0 series per-second tiers remain; the "Choose a model" list switched its speech-recognition recommendation from qwen-audio-3.0-asr-flash-streaming/-filetrans to the 3.1 versions; the context-cache Stepfun (StepFun deployment) list added stepfun/step-5-preview; qwen3.8-max-prime's fast-mode doc link changed from /fast-mode to /prime-mode; the Workspace ID link in the official OpenCode / OpenClaw integration docs changed from "Get Workspace ID" to the regions page (/zh/model-studio/regions#h2_migrate_domain)
• 2026/09/22: Alibaba Cloud Bailian Token Plan (Personal Edition) night discount changed: qwen3.8-max went from 50% off to 40% off and qwen3.8-flash was added at 40% off; deepseek-v4-pro-0813, deepseek-v4-flash-0731 and deepseek-v4.1-flash stay at 50% off (all are Credits-consumption discounts for calls between 22:00 and 08:00)
• 2026/09/22: OpenCode Go added three models — Grok 4.7, MiMo-V2.6-Flash and MiMo-V2.6-Pro. Grok 4.7 has the same pricing and request limits as Grok 4.6 (≤200K tokens: input $2.00 / output $6.00 / cache read $0.50; >200K tokens: \(4.00/\)12.00/$1.00 per 1M tokens; allowance \(15/month; request limits 169 per 5 hours, 423 per week, 845 per month; model ID grok-4.7). MiMo-V2.6-Flash/V2.6-Pro have pricing and request limits identical to the previous generations they replace, MiMo-V2.5/V2.5-Pro (\)0.14/\(0.28/\)0.0028 with a $60 allowance, and \(0.435/\)0.87/$0.003625 with a $15 allowance)
• 2026/09/22: The Xiaomi MiMo Token Plan was reworked into the "Personal Edition" and its supported models went from 9 to 8 — mimo-v2.6-pro and mimo-v2.6-flash were added (Credit conversion matches the previous generation: V2.6-Pro 2.5 cached / 300 uncached / 600 output, V2.6-Flash 2/100/200 Credits per token), while MiMo-V2-Pro, MiMo-V2-Omni and MiMo-V2-TTS were removed from the supported-model list and the Credit table; a notice states that mimo-v2.5-pro and mimo-v2.5 will be retired at 10:00 Beijing time on 2026-10-21. Plan prices and quotas are unchanged (39/99/329/659 RMB or 6/16/50/100 USD per month, 4.1B/11B/38B/82B Credits per month). The discount description was narrowed to "88% off first purchase, 88% off annual auto-renewal, 0.8x consumption at night", the earlier Token Plan upgrade "Credits usage reset" campaign (effective 2026-05-27) was removed, and the purchase note now reads "only one Personal Edition plan can be held at a time"
• 2026/09/21: Alibaba Cloud Bailian Token Plan (Personal Edition) added auto to its supported models (official description: "a platform-provided smart model that automatically matches the underlying model to the request, balancing quality and cost"; capability label "reasoning, text generation"; listed first under the Qwen brand in the model table). The official OpenCode / OpenClaw integration docs added an auto entry to both the Personal and Team Edition configurations (in OpenCode it only declares text input/output, with no reasoning or limit fields; in OpenClaw contextWindow 1,000,000, maxTokens 393,216, reasoning false) and changed OpenClaw's default model from bailian-token-plan/qwen3.8-flash to bailian-token-plan/auto
• 2026/09/21: Alibaba Cloud Bailian's model calling prices and context-cache supported model list added two models — ZHIPU/GLM-5.3-FlashX (Zhipu deployment, thinking mode only, 2 CNY input / 7 CNY output per million tokens, no free quota; cache-hit discount 28.5%, higher than the 25% of the other five models in the same series such as ZHIPU/GLM-5.3-Flash) and vanchin/deepseek-v4.1-flash (Kuaishou Wanqing deployment, 2 CNY input / 8 CNY output per million tokens; cache-hit discount 2%, lower than vanchin/deepseek-v4-pro's 8.33%)
• 2026/09/21: OpenCode Go extended its limited-time 4x quota boost for DeepSeek V4.1 Flash — the end date moved from 2026-09-20 to 2026-09-27 (the $60 monthly usage allowance, the request limits of 26,000 per 5 hours / 65,000 per week / 130,000 per month and the token pricing are all unchanged)
• 2026/09/20: StepFun Step Plan added step-5-preview to its supported models (next-generation flagship base model for real-world tasks) and removed step-image-edit-2 along with the previous image model retirement notice, so the plan no longer covers any text-to-image or image editing model; the official model description correspondingly changed from "flagship models covering text, reasoning, voice, image editing and intelligent routing" to "text, reasoning, voice and intelligent routing". The official docs also split the Base URL guidance per tool — Claude Code / Anthropic SDK use https://api.stepfun.com/step_plan while OpenAI SDK Chat Completions calls still use https://api.stepfun.com/step_plan/v1 — and clarified that the Step Plan channel consumes plan Credits and is independent of the regular API channel quota (the FAQ now likewise says to pick the address by tool)
• 2026/09/18: The Kimi Code docs added per-model ID membership tier requirements and introduced the Plus / Pro tier names for the first time — k3 / k3-256k require Moderato / Plus or above (1M context requires Allegretto / Pro or above); the wording for kimi-for-coding changed from "available to all members" to "available to Andante / Plus or above"; kimi-for-coding-highspeed requires Allegretto / Pro or above. It also added overseas API endpoint domains: Kimi Code overseas OpenAI-compatible https://api.kimi.ai/coding/v1 and Anthropic-compatible https://api.kimi.ai/coding/, and Kimi Open Platform overseas https://api.moonshot.ai/v1 (domestic endpoints are api.kimi.com/coding and api.moonshot.cn/v1)
• 2026/09/18: OpenCode Go removed the Union Alpha Free model (limited-time free period ended) — the model (model ID union-alpha) was removed from the supported model list, the token price table, the request limit table and the endpoint table
• 2026/09/18: Volcano Engine Coding Plan (Personal Edition) and Agent Plan (Personal Edition) added the kimi-k2.8-preview model (overall performance close to K3 with higher thinking efficiency, supports text and image input; 1M context window / 1M max output, supported by all plans); Agent Plan deduction coefficient 8, at 40% off (4.8) from 2026-09-17 00:00 to 2026-09-30 23:59; during the promotion from 2026-09-18 00:00 to 2026-09-30 23:59 the available quota of this model in the Coding Plan is comparable to that during the Agent Plan 40%-off deduction promotion; the model also joins the 1M-context supported list (now glm-5.3, glm-5.3-flash, deepseek-v4.1-flash, deepseek-v4-flash, deepseek-v4-pro, kimi-k3, kimi-k2.8-preview)
• 2026/09/18: Alibaba Cloud Bailian Token Plan Personal Edition added the Essential tier, expanding the personal tiers from three (Lite/Standard/Pro) to four: list price 120 RMB/month, 79 RMB/month for a limited time, 5,625 Credits every 7 days (2.25x Lite), supports 2-3 concurrent Agents, and its benefits are all Lite benefits; the vendor also moved the Usage Pack (100 RMB each/month, 20,000 Credits; requires an active subscription, up to 5 held at a time, not subject to the 7-day window limit) from a table row to a footnote
• 2026/09/17: OpenCode Go added the Union Alpha Free model (limited time): input/output/cache read are all Free, with unlimited requests and quota (limited time); model ID union-alpha, endpoint https://opencode.ai/zen/go/v1/messages (Anthropic-compatible)
• 2026/09/16: Alibaba Cloud Bailian Token Plan (Personal Edition) added glm-5.3 to its "Supported models" list (Zhipu AI, capability label "reasoning, text generation", coexisting with glm-5.2; glm-5.3 had already been added to the Bailian model catalog on 2026-09-15 but was not part of the Token Plan at that time); the official integration docs added the corresponding model config — OpenClaw with contextWindow 1,000,000, maxTokens 16,384, reasoning false, and OpenCode with thinking enabled (budgetTokens 8192); the Personal Edition limited-time night 50%-off list is unchanged (qwen3.8-max, deepseek-v4-pro-0813, deepseek-v4-flash-0731, deepseek-v4.1-flash)
• 2026/09/15: Kuaishou Wanqing (StreamLake/Vanchin, the platform behind the KwaiKAT Coding Plan) model list added three models — GLM-5.3, GLM-5.3-Flash and DeepSeek-V4-Pro-0813; Wanqing's pay-as-you-go model catalog does not state whether these models are covered by the KwaiKAT Coding Plan quota
• 2026/09/15: Alibaba Cloud Bailian model calling prices added the GLM model glm-5.3 (non-thinking and thinking modes, no token tiers, 8 CNY input / 28 CNY output per million tokens, the same price for China-site regions such as China North 2 (Beijing) and the "global" deployment; 10.208/32.084 CNY on the international site) with 1 million free tokens; the list of GLM models supported by context caching (deployed on Alibaba Cloud Bailian) also added glm-5.3 (25% cache-hit discount, the same tier as glm-5.2 and glm-5.2-fast-preview); meanwhile the mode of ZHIPU/GLM-5.3 (GLM deployed by Zhipu) was corrected from "non-thinking and thinking modes" to "thinking mode only" (price unchanged at 8 CNY input / 28 CNY output, no free quota)
• 2026/09/15: Volcano Engine Agent Plan (Personal Edition) added the deepseek-v4.1-flash model (supported by all plans; 1M context window / 384K max output, natively capable of multimodal vision understanding) with a deduction coefficient of 2.5, at 50% off (1.25) from 2026-09-15 00:00 to 2026-09-28 23:59; the model also joins the 1M-context supported list (now glm-5.3, glm-5.3-flash, deepseek-v4.1-flash, deepseek-v4-flash, deepseek-v4-pro, kimi-k3)
• 2026/09/14: In the Alibaba Cloud Bailian Token Plan (Personal Edition) supported-model list, deepseek-v4.1-flash's capability label changed from "reasoning, text generation" to "reasoning, vision understanding, text generation"; the official integration doc (OpenClaw) also changed that model's config input from ["text"] to ["text", "image"], confirming the model accepts image input directly within the Token Plan
• 2026/09/14: Volcano Engine Agent Plan (Personal Edition) added two multimodal models: doubao-seedream-5-0-pro (image generation, all plans; input images are free for the first image and 10 AFP per image thereafter, output images cost 150 AFP for ≤2.61M pixels and 300 AFP above that for single-image generation, and 75/150 AFP for layer separation) and doubao-seedance-2.5 (video generation, Large/Max; 210 per token when the input contains video and 350 when it does not for 480p/720p, 230/385 for 1080p); doubao-seedance-1.5-pro is marked as being retired
• 2026/09/14: Alibaba Cloud Bailian Token Plan (Personal Edition) added deepseek-v4.1-flash to its supported models (it had previously only been added to the Bailian model library, not to the Token Plan); the model also joined the Personal Edition limited-time night discount (50% off Credits from 22:00 to 08:00), whose list is now qwen3.8-max, deepseek-v4-pro-0813, deepseek-v4-flash-0731, deepseek-v4.1-flash
• 2026/09/14: Tencent Cloud Token Plan Enterprise Professional Plan (Guangzhou/Singapore) added DeepSeek-V4.1-Flash Official direct-supply (model ID deepseek/deepseek-flash) to its model library; the Official direct-supply Flash-series credit prices were lowered across the board — DeepSeek-V4-Flash 0731 Official direct-supply (previously ~39 off-peak / ~77 peak credits per 1M tokens) and DeepSeek-V4-Flash-Vision-Exp Official direct-supply (previously ~35 / ~70) both dropped to match the new model (cached 2 / uncached 100 / output 400 off-peak, 4/200/800 peak; estimated blended ~26 / ~51), following DeepSeek's upstream move of routing the legacy model names to V4.1-Flash billing; it also removed the GLM-5.3-Flash 50%-off credit-price promotion that had expired on 2026-09-10
• 2026/09/14: OpenCode Go temporarily boosted the DeepSeek V4.1 Flash limits 4x: monthly usage allowance raised from $15 to $60 (promotion ends 2026-09-20), request limits raised from 6,500 per 5 hours / 16,250 per week / 32,500 per month to 26,000 per 5 hours / 65,000 per week / 130,000 per month; token pricing unchanged
• 2026/09/14: Alibaba Cloud Bailian added deepseek-v4.1-flash to its model library: China North 2 (Beijing) / global pricing is peak input 2 RMB, off-peak input 1 RMB, peak output 8 RMB, off-peak output 4 RMB per 1M tokens (with a 1M-token free quota); international site peak 2.188/8.75 RMB, off-peak 1.094/4.375 RMB. Context-cache hits cost 10% of the input price (peak 0.2 RMB, off-peak 0.1 RMB), a better discount than the 20% applied to other Bailian models but still pricier than DeepSeek's official API cache-hit price (0.04/0.02 RMB). The "Choose a model" list also swapped its featured slot from deepseek-v4-flash-0731 to this model; it is not yet in the Bailian Token Plan (Personal/Team Edition) supported-model lists
• 2026/09/12: OpenCode Go renamed the DeepSeek V4.1 Flash model ID from deepseek-flash to deepseek-v4.1-flash
• 2026/09/12: Kimi Code's standard tier moved from K2.7 Code to K2.8 Preview (model name kimi-for-coding now maps to K2.8 Preview, supporting up to 1M context and low/high/max thinking levels); the High Speed tier remains K2.7 Code HighSpeed
• 2026/09/12: DeepSeek reversed its V4 Pro retirement plan: the vendor will keep providing the DeepSeek V4 Pro API service after 2026-09-14 with unchanged billing
• 2026/09/10: Added DeepSeek-V4.1-Flash to the model parameters comparison table (552B total parameters, 8B input / 16B output activation, multimodal support)
• 2026/09/10: DeepSeek released DeepSeek-V4.1-Flash (new model name deepseek-flash, 1M context, supports image understanding) with significantly lower pricing (off-peak: cached 0.02, uncached 1, output 4 RMB; peak 0.04/2/8 RMB per 1M tokens); old model names deepseek-v4-flash and deepseek-v4-flash-vision-exp are discontinued (requests served by V4.1-Flash at Flash pricing); V4 Pro is planned for orderly retirement — after 2026-09-14 12:00 all deepseek-v4-pro requests route to V4.1 Flash at Flash pricing
• 2026/09/10: Zhipu GLM-5.3-Flash limited-time 50% off promotion ended, reverting to standard pricing (uncached input 0.8, output 2.8, cached input 0.23 RMB per 1M tokens); Alibaba Cloud Bailian also removed the "50% off (limited time)" label for the same model; Tencent Cloud Token Plan (Personal Edition Universal Plan and Enterprise Professional Plan) marked GLM-5, GLM-5.1 and GLM-5-Turbo for discontinuation on 2026-10-09; OpenCode Go billing limits redefined as per-model monthly amounts (5 hours = 20% of monthly, week = 50%, month = 100%), with differing monthly limits per model (e.g. GLM-5.3 $15, GLM-5.3-Flash $60)
• 2026/09/09: Volcano Engine Coding Plan (Personal Edition) added the Kimi-K3 model (1M context / 128K max output, native visual understanding, high deduction coefficient, recommended only for Pro plan users); iFlytek Astron Token Plan Team Edition added the Spark-X2.5 model (256K, input 320 / cache 48 / output 1200 / thinking 1200 credits per 1M tokens), Spark-X2 and Spark-X2-Agent discontinued
• 2026/09/04: StepFun Step Plan announced that the step-image-edit-2 model will be retired on 2026-10-10, and the Step Plan text-to-image and image editing APIs will stop serving requests simultaneously
• 2026/09/04: OpenCode Go added support for the Omen Alpha model (input $0.20/1M, output $0.66/1M, cache read $0.04/1M, usage allowance $100/month; request limits 11,600 per 5 hours, 29,000 per week, 57,900 per month; model ID omen-alpha)
• 2026/09/04: Tencent Cloud LLM Token Plan expanded its model library: both the Universal Token Plan (Personal Edition) and the Enterprise Professional Plan added the GLM-5.3-Flash and Kimi K3 models; the Enterprise Professional Plan also published the credit prices for these two models (Guangzhou GLM-5.3-Flash 23/80/280, Kimi K3 200/2000/10000; Singapore GLM-5.3-Flash 21.5898/107.949/359.83, credits per 1M tokens)
• 2026/09/03: Kimi Code revised its "Core Advantages" section: it now explicitly states the plan is powered by the flagship K3 model (~2.8 trillion parameters) with the K2.7 Code in two modes (standard / High Speed), with a maximum inference speed of 260 Tokens/s (previously described as 100 Tokens/s) and a 1M Token context window; it removed the statements "High Speed version is 5–6x the standard version" and "approx. 300–1200 requests per 5 hours, max concurrency 30"
• 2026/09/03: Alibaba Cloud Bailian Token Plan (Personal Edition) usage policy tightened: the official guide changed from "you may configure the same API Key on multiple of your own devices (e.g., home and office computers)" to "for the subscriber's own use on a single device."
• 2026/09/03: OpenCode Go added support for the Muse Spark 1.3 Contributor model (Meta Contributor tier: allows Meta to use prompts and completions for training future models in exchange for heavily discounted token pricing; input $0.10/1M, output $0.20/1M, cache read $0.002/1M, usage allowance $60; request limits 45,300 per 5 hours, 113,300 per week, 226,600 per month; model ID muse-spark-1.3-contributor; only available in regions permitted by Meta's Geographic Use Policy)
• 2026/09/02: Tencent Cloud LLM Token Plan Personal Edition Hy Token Plan Pro Plan corrected its credits per subscription month from 1,560 to 4,760 (238 RMB/month price unchanged; 1,560 was a vendor mislabel/typo inconsistent with the price × 20 pattern of the other tiers)
• 2026/09/01: Volcano Engine Agent Plan (Personal Edition) deduction coefficient rule adjustment: the input and output deduction coefficients for text-generation/embedding models are now determined solely by the model and no longer vary with input length (previously input coefficient = model coefficient × input segment factor: ×0.67 for ≤32k, ×1 for 32k–128k, ×2 for >128k; the length segmentation has been removed). Input/output deduction coefficients per model: doubao-seed-2.0-mini 0.25, doubao-seed-2.0-lite/deepseek-v4-flash 0.5, glm-5.3-flash 0.5 (0.25 for the first two weeks at 50% off), doubao-seed-2.1-turbo/doubao-seed-evolving/minimax-m3 2.5, kimi-k2.7-code 4.5, glm-5.3 (glm-latest) 4.5, deepseek-v4-pro 5.5, kimi-k3 10, doubao-embedding-vision 0.5
• 2026/09/01: OpenCode Go Qwen3.7 Max model allowance reduced: request limits lowered from 340 per 5 hours, 840 per week, 1,690 per month to 170 per 5 hours, 420 per week, 840 per month, and the monthly usage allowance lowered from $60 to $30 (pricing input $2.50/1M, output $7.50/1M, cache read $0.50/1M, cache write $3.125/1M unchanged)
• 2026/08/31: Tencent Cloud LLM Token Plan switched to credit-based deduction: the Personal Edition changed from token quotas to credits effective 2026-08-31 17:00 (Universal Token Plan Lite/Standard/Pro/Max = 39/99/299/599 RMB/month, 780/1,980/5,980/11,980 credits/month; Hy Token Plan Lite/Standard/Pro/Max = 28/78/238/468 RMB/month, 560/1,560/1,560 (as-is in source doc, likely a typo)/9,360 credits/month); Universal Token Plan supported models updated to Auto, DeepSeek-V4-Flash/Pro Official direct-supply, MiniMax-M2.7, MiniMax-M3, GLM-5/5.1/5.2/5.3, Kimi K2.7 Code, Hy4 preview (Kimi-K2.5 discontinued), Hy Token Plan supports Hy3 and Hy4 preview (Hy3 preview auto-routes to Hy3); Enterprise Professional Plan added DeepSeek-V4-Flash-Vision-Exp Official direct-supply (multimodal/visual understanding, text capability on par with V4-Flash Official, multimodal Agent performance approaching Claude Opus-4.8) and removed Kimi-K2.5; DeepSeek V4 Official direct-supply peak-valley billing adjusted from 2026-08-29 to weekdays only (weekends all off-peak), DeepSeek V4 Official peak hours are Mon–Sun 9:00–12:00 and 14:00–18:00
• 2026/08/31: Volcano Engine Coding Plan (Personal Edition) and Agent Plan (Personal Edition) removed the GLM-5.2 model (previously marked as "phasing out"); GLM-5.2 is no longer listed among supported models or in the 1M-context supported list; the GLM-5.3 deduction coefficient description changed from "same as GLM-5.2" to "high"
• 2026/08/31: Alibaba Cloud Bailian model pricing added ZHIPU/GLM-5.3-Flash (thinking-only mode, input 0.8 RMB, output 2.8 RMB per 1M tokens, supports context-cache hit discount at 25%) and qwen-flash-character (0.25/1.5 RMB); qwen3-vl-rerank price lowered (text 0.7→0.5 RMB, image 1.8→0.5 RMB); Token Plan (Personal Edition) limited-time night discount added deepseek-v4-flash-0731
• 2026/08/29: OpenCode Go added the Hy4 preview model (input $0.834/1M, output $2.501/1M, cache read $0.042/1M, usage allowance $30; request limits 1,350 per 5 hours, 3,380 per week, 6,770 per month; model ID hy4-preview)
• 2026/08/29: Volcano Engine Coding Plan (Personal Edition) and Agent Plan (Personal Edition) added the glm-5.3-flash model (Zhipu's first natively multimodal model, 320B total params / 18B active, supports image input, 1M context / 128K max output; first two weeks deduction coefficient at 50% off, promotion ends 2026-09-11 23:59:59); Agent Plan's Agent Evolution changed to first 50 files free
• 2026/08/28: Zhipu International (Z.ai DevPack) GLM Coding Plan model change: all plans now support {GLM-5.3, GLM-5.3-Flash} (was {GLM-5.3, GLM-5-Flash}); requests for GLM-5.2/GLM-5.1 auto-routed to GLM-5.3, GLM-4.7 auto-routed to GLM-5.3-Flash (GLM-5-Turbo no longer a routing target); release notes removed the GLM-5V-Turbo and GLM-5-Turbo model entries
• 2026/08/28: OpenCode Go added support for Qwen3.8 Flash model (input $0.15/1M, output $0.47/1M, cache read $0.016/1M, cache write $0.20/1M, usage limit $30; request limits 5,400 per 5 hours, 13,500 per week, 27,000 per month; model ID qwen3.8-flash)
• 2026/08/28: Infini-AI GenStudio changelog: a batch of models were discontinued on 2026-08-28 (deepseek-r1, deepseek-v3 series, deepseek-v3.2/v3.2-thinking, glm-4.5/4.5-air/4.6/4.7/5/4.5v/4.6v, minimax-m2.1/m2.5, kimi-k2.5), recommended migration to deepseek-v4-flash/v4-pro, glm-5.2, kimi-k2.6, minimax-m2.7; DeepSeek V4 series (deepseek-v4-flash-0731, deepseek-v4-pro-0813) launched on 2026-08-18
• 2026/08/27: Alibaba Cloud Bailian Token Plan (Personal Edition) added model qwen3.8-flash
• 2026/08/27: Volcano Engine Coding Plan (Personal Edition) and Agent Plan DeepSeek-V4-Pro changed from "early-access preview" to officially released (significantly enhanced Agent capabilities, accessible via model name and console selection)
• 2026/08/27: Alibaba Cloud Bailian model pricing adjustments: qwen3.8-flash China input dropped from 1 to 0.8 RMB and output from 3 to 2.7 RMB (international input dropped from 1.167 to 1.094 RMB, output unchanged); added kimi-k3 (thinking-only mode, global 20/100 RMB, international 21.875/109.376 RMB per 1M tokens); tongyi-xiaomi-analysis-flash/pro now support context cache discounts; added kling/kling-v3-turbo video generation model (audio video 720P 0.8 RMB/sec, 1080P 1.0 RMB/sec)
• 2026/08/27: Alibaba Cloud Bailian context cache rule adjustments: implicit cache minimum token count raised from 256 to 1,024 (same as explicit cache, but meaning differs — reaching 1,024 only qualifies for a hit, does not guarantee one); qwen3.8-flash added to cached_token discount exceptions (no longer billed at 20% of input); added tongyi-xiaomi-analysis-pro/flash industry models; added DeepSeek (Kuaishou Wanqing deployment) cache pricing (vanchin/deepseek-v4-pro 8.33%, vanchin/deepseek-v3.2-think 10%, etc.)
• 2026/08/27: Tencent Cloud Token Plan (Personal Edition) Universal Plan Kimi-K2.5 discontinuation date changed from 2026-07-31 to 2026-08-31 (and removed the peak-hour rate-limit notice)
• 2026/08/26: Zhipu added GLM-5.3-Flash API pricing (bigmodel.cn): cached input 0.115/0.23 RMB, uncached input 0.4/0.8 RMB, output 1.4/2.8 RMB per 1M tokens, 1M context, currently 50% off for two weeks
• 2026/08/26: Zhipu GLM Coding Plan supported models changed from {GLM-5.3, GLM-5-Turbo, GLM-4.7} to {GLM-5.3, GLM-5.3-Flash}; GLM-5.3-Flash (320B total params / 18B active, hybrid linear+sparse attention, native vision) launched for Coding Plan with deduction coefficients Input 2.3 / Cached Input 0.56 / Output 8 (including visual understanding MCP); GLM-5-Turbo/GLM-4.7 requests auto-routed to GLM-5.3-Flash; token allowance reference table restructured to show per-model breakdowns at 95%/96%/98% cache hit rates; "save up to 92%" claim restored
• 2026/08/26: OpenCode Go added GLM-5.3-Flash model, removed Ox Alpha Free model (limited-time free ended)
• 2026/08/26: Qwen3.8-Flash-Next and GLM-5.3-Flash released
• 2026/08/26: MiniMax Token Plan price adjustment: International edition Plus/Max/Ultra plans increased from \(20/\)50/$120/month to \(22/\)55/$132/month; Chinese edition prepaid credits packages adjusted — ¥30 for 4,489 credits (was 4,285), ¥150 for 22,460 credits (was 21,430), ¥500 for 74,900 credits (was 71,435); Chinese subscription plan prices unchanged
• 2026/08/26: OpenCode Go upgraded Grok model from 4.5 to 4.6: rate limits increased (169/5hr, 423/week, 845/month, previously 120/300/600), pricing changed to tiered (≤200K tokens: input $2.00, output $6.00, cache $0.50; >200K tokens: input $4.00, output $12.00, cache $1.00, previously flat \(2.00/\)6.00/$0.30), model ID changed from grok-4.5 to grok-4.6
• 2026/08/25: Tencent Cloud Token Plan Enterprise Professional Plan lowered minimum purchase from 100K to 50K Credits, added DeepSeek-V4-Flash 0731 Official and DeepSeek-V4-Pro 0813 Official models (peak-valley pricing, off-peak rates same as direct-supply versions)
• 2026/08/25: OpenCode Go added support for LongCat-2.0 model (input $0.30/1M, output $1.20/1M, cache read $0.006/1M)
• 2026/08/24: OpenCode Go removed first-month discount, pricing changed from "$5 first month, then $10/month" to a flat $10/month
• 2026/08/23: DeepSeek API peak-valley weekend rule now in effect: peak hours are explicitly Monday to Friday 9:00-12:00, 14:00-18:00 Beijing time; weekends are now charged at off-peak rates all day
• 2026/08/22: DeepSeek API peak-valley pricing rule adjustment: starting 2026-08-23 (Sunday) 00:00 Beijing time, weekends (Saturday and Sunday) will no longer distinguish peak/off-peak — all day will be charged at off-peak rates (previously weekends still followed peak/off-peak schedule)
• 2026/08/21: Volcano Engine Coding Plan (Personal Edition) added support for Doubao-Seed-Evolving model (for Coding & Agent scenarios, weekly upgrades, 1M context window, 256K max output); OpenCode Go added support for DeepSeek V4 Flash Vision Exp model (pricing Off-Peak \(0.22/\)0.66, Peak \(0.44/\)1.32 per 1M tokens, images converted to tokens based on size); Tencent Cloud Token Plan (Personal Edition) Universal Plan removed discontinued models (Tencent HY 2.0 Instruct, Tencent HY 2.0 Think, Hunyuan-T1, Hunyuan-TurboS, MiniMax-M2.5)
• 2026/08/21: DeepSeek added new vision model deepseek-v4-flash-vision-exp (experimental), priced same as deepseek-v4-flash, FIM completion not supported, concurrency limit 2500, images converted to tokens based on size; Tencent Cloud Token Plan Enterprise Professional Plan removed MiniMax-M2.5 model; Volcano Engine Agent Plan (Personal Edition) updated quota rules: image/video generation models, voice models, and Harness merged into a single daily quota category (no longer separated as "vision models" and "voice models"), daily quota uniformly set to half of monthly plan quota; OpenCode Go added Ox Alpha Free model (limited-time free)
• 2026/08/20: CTCloud Programming Token Plan updated supported models: added GLM-5.1, DeepSeek-V4-Flash-0731; renamed GLM-5 to GLM-5.0 (Official); DeepSeek-V3.2 labeled as Flagship
• 2026/08/19: Alibaba Cloud Bailian added open-source model qwen3.8-27b, priced at Input 3 RMB / Output 12 RMB per 1M tokens (context cache discount available), international pricing Input 3.646 RMB / Output 21.875 RMB per 1M tokens; Tencent Cloud Token Plan (Personal Edition) and Enterprise Professional Plan renamed DeepSeek-V4-Pro 原厂直供 to DeepSeek-V4-Pro 正式版 原厂直供，added model IDs deepseek/deepseek-v4-pro-0813 and deepseek/deepseek-v4-pro; MiniMax Token Plan coverage narrowed from "all models" to "flagship models", music APIs (Music-3.0, Music-2.6, Lyrics Generation, etc.) discontinued and removed from Token Plan quota
• 2026/08/19: Zhipu released GLM-5.3 model with 50% coding improvement over GLM-5.2 and cybersecurity capabilities matching Mythos 5; GLM Coding Plan token allowance estimates updated to show multiple cache hit rates (90.9%, 95%, 98%); GLM-5.3 API pricing matches GLM-5.2
• 2026/08/18: Volcano Engine Coding Plan (Personal Edition) and Agent Plan removed MiniMax-M2.7 and Kimi-K2.6 models (previously marked as phasing out)
• 2026/08/17: Volcano Engine Coding Plan (Personal Edition) and Agent Plan removed Doubao-Seed-2.0-Code, Doubao-Seed-2.0-pro, Doubao-Seed-Code models (previously marked as phasing out); GLM-5.2 marked as phasing out; GLM-5.3 replaced GLM-5.2 as the default glm-latest target
• 2026/08/14: Volcano Engine Coding Plan (Personal Edition) and Agent Plan added support for the GLM-5.3 model (1M context window, 1024K context / 128K max output, thinking enabled by default and cannot be disabled, deduction coefficient same as GLM-5.2)
• 2026/08/14: Zhipu GLM Coding Plan flagship model upgraded from GLM-5.2 to GLM-5.3: all plans support GLM-5.3, GLM-5-Turbo and GLM-4.7; requests for previous models (GLM-5.2/GLM-5.1) are automatically routed to GLM-5.3; model deduction coefficients unchanged (Input 6.9 / Cached Input 1.7 / Output 24); the official docs also removed the "save up to 92%" claim; the international edition (Z.ai DevPack) was upgraded to GLM-5.3 accordingly
• 2026/08/13: DeepSeek API will adopt peak-valley pricing starting 2026-08-17 00:00: peak hours (9:00-12:00, 14:00-18:00 Beijing time) are charged at 2x the off-peak price, with overall prices significantly increased (e.g., deepseek-v4-pro output price rises from 6 RMB to 27 RMB peak / 13.5 RMB off-peak per 1M tokens)
• 2026/07/31: GLM Coding Plan switched to credit-based limits
• 2026/07/20: Kimi Code separated from Kimi membership, now available as a dedicated new Kimi Code subscription
• 2026/07/16: Kimi-K3 model released
• 2026/07/13: Baidu Qianfan Token Plan (Personal Edition) launched
• 2026/06/27: Infini Coding Plan discontinued
• 2026/06/13: GLM-5.2 model released
• 2026/06/12: Kimi K2.7-Code model released
• 2026/06/10: GLM Coding Plan Team Edition launched
• 2026/06/08: Volcano Engine Coding Plan and Agent Plan added MiniMax-M3
• 2026/06/08: MiniMax M3 API price permanently halved
• 2026/06/07: Alibaba Cloud Bailian Coding Plan added qwen3.7-plus model
• 2026/06/05: Huawei Cloud MaaS Token Plan launched
• 2026/06/01: MiniMax M3 released
• 2026/05/29: StepFun Coding Plan added support for step-3.7-flash model
• 2026/05/27: Xiaomi MiMo Token Plan quota massively increased
• 2026/05/22: Baidu Qianfan Coding Plan added support for DeepSeek-V4-Pro model
• 2026/05/22: Alibaba Cloud Token Plan added support for qwen3.7-max model
• 2026/05/08: Baidu Qianfan Coding Plan added support for DeepSeek-V4-Flash and GLM-5.1 models
• 2026/05/07: Volcano Engine Agent Plan (Personal Edition) launched
• 2026/04/30: Tencent Cloud Token Plan (Personal Edition) added support for GLM-5.1 and MiniMax-M2.7 models
• 2026/04/30: StepFun Coding Plan removed deepseek-v4-pro model, must access indirectly through step-router-v1 model
• 2026/04/28: StepFun Coding Plan added deepseek-v4-pro and step-router-v1 models
• 2026/04/27: GLM Coding Plan extended the limited-time discount benefit deadline from end of April to end of June
• 2026/04/24: Alibaba Cloud Bailian Token Plan halved the Credits required for cached input tokens
• 2026/04/23: MiMo-V2.5 series models launched
• 2026/04/23: StepFun Coding Plan added support for stepaudio-2.5-asr model
• 2026/04/23: GLM Coding Plan will uniformly disable auto-renewal for legacy plans (no weekly limit version) on April 30, 2026. Current active billing cycles are not affected. Meanwhile, the system will automatically gift affected users 2 months of equivalent new plan, which will take effect after the current plan expires, with no manual claim required. See Legacy Plan Migration and Compensation Notice.
• 2026/04/22: Volcano Engine Coding Plan added MiniMax-M2.7, Kimi-K2.6, GLM-5.1
• 2026/04/21: Alibaba Cloud Bailian Token Plan (Team Edition) launched
• 2026/04/21: Kimi officially released Kimi-K2.6 model
• 2026/04/14: Kimi Code launched K2.6-code-preview model
• 2026/04/12: Zhipu International GLM Coding Plan starting price increased from 10 USD/month to 18 USD/month
• 2026/04/11: Alibaba Cloud Bailian Coding Plan Lite Plan will stop accepting renewals and upgrades from April 13, 2026. New purchases were already suspended on March 19, 2026
• 2026/04/11: Added CTCloud Coding Plan
• 2026/04/09: Infini-AI Coding Plan added support for glm-5.1 model
• 2026/04/09: Zhipu Coding Plan removed GLM-5, GLM-4.6, GLM-4.5 models
• 2026/04/08: iFlytek Astron Coding Plan launched new Updated Edition plans; old First Month Edition plans retired
• 2026/04/08: Alibaba Cloud Bailian Coding Plan added recommended model qwen3.6-plus (with image understanding), available only on the Pro plan. qwen3.5-plus was moved from recommended to more models
• 2026/04/07: Baidu Qianfan Coding Plan removed GLM-4.7 and MiniMax-M2.1, added ERNIE-4.5-Turbo-20260402
• 2026/04/03: Added Xiaomi MiMo Token Plan
• 2026/04/03: Added JD Cloud Coding Plan
• 2026/04/03: Added StepFun Coding Plan
• 2026/03/27: GLM-5.1 launched in GLM Coding Plan
• 2026/03/27: Added Tencent Cloud LLM Token Plan, which uses token-based limits instead of request counts compared to the Coding Plan
• 2026/03/26: GLM-5-Turbo is now available on all GLM Coding Plan tiers; previously only available on Max
• 2026/03/21: MiniMax Token Plan has brought back the Starter Plan, with the same pricing and limits. Additionally, a weekly limit has been introduced, which is 10 times the limit per 5 hours.
• 2026/03/19: Alibaba Cloud Bailian Coding Plan Release Announcement, new purchases of the Coding Plan Lite will be suspended from 2026-03-20 00:00:00 Beijing Time.
• 2026/03/19: Infini-AI Coding Plan added support for third-party model minimax-m2.7
• 2026/03/18: MiniMax Token Plan removed the statement that the MiniMax-M2.7-highspeed version consumes double the requests.
• 2026/03/18: MiniMax-M2.7 launched; meanwhile, MiniMax Coding Plan was renamed to MiniMax Token Plan, supporting non-text LLMs (e.g., audio and video). The Token Plan removed the Starter Plan and changed the description from "prompts" to "requests" though the actual limits remain unchanged (previously, the limit was also calculated as 1 prompt equaling 15 requests)
• 2026/03/17: Added iFlytek MaaS Astron Coding Plan
• 2026/03/16: Zhipu launched the GLM-5-Turbo model, described as follows:
  • A base model deeply optimised for the OpenClaw lobster scenario
  • Strengthened calling of external tools and various Skills, more stable and reliable in multi-step tasks
  • Stronger decomposition of complex instructions — it identifies goals precisely, plans steps, and supports coordination and division of labour across multiple agents
  • Better understanding of temporal requirements, maintaining execution continuity in long, complex tasks
  • Further improved execution efficiency and response stability for lobster tasks with high data throughput and long logic chains
  • GLM-5-Turbo plan availability: already supported on Max; expected on Pro by the end of March and on Lite within April
  • GLM-5 plan availability: already supported on both Max and Pro; expected on Lite by the end of March
  • GLM-5 and GLM-5-Turbo are advanced models benchmarked against Claude Opus, consuming quota at "3x during peak hours, 2x during off-peak hours"; we recommend switching to GLM-5 for complex tasks and continuing with GLM-4.7 for ordinary tasks to avoid burning through the plan quota too quickly. (As a limited-time benefit, GLM-5-Turbo consumes only 1x during off-peak hours, through the end of April.) Note: peak hours are 14:00–18:00 (UTC+8) daily
• 2026/03/08: Tencent Cloud LLM Coding Plan launched
• 2026/03/07: Zhipu issued a 15-day compensation credit for GLM Coding Plan. The translated email text is as follows (original was in Chinese):

  Dear GLM Coding Plan User,
  
  
  Thank you for your continued support and trust.
  
  
  To address the recent service issues some users experienced and to express our sincere apologies, we have credited your account with compensation equivalent to 15 days of your current subscription fee (with no expiration). You can view the credit details in your account dashboard under "Zhipu Open Platform Console - Billing - Transaction History", and it will be automatically applied to your future usage.
  
  
  Thank you again for your understanding and patience, as well as your ongoing support. We remain committed to improving our product capabilities and service quality to deliver a more stable and efficient development experience.
  
  
  Best regards,
  
  
  Zhipu AI Platform Team
  
  March 7, 2026
  

• 2026/03/06: Volcano Engine Coding Plan added support for third-party model MiniMax-M2.5
• 2026/02/25: Alibaba Bailian Coding Plan added support for third-party model minimax-m2.5
• 2026/02/24: Alibaba Bailian Coding Plan added support for third-party model glm-5
• 2026/02/21: Observed that Alibaba Bailian Coding Plan added support for third-party models glm-4.7 and kimi-k2.5; previously only Qwen's own models were available
• 2026/02/18: Kimi Code billing has changed:
  • Previously, the weekly limit was changed from 50M input + output tokens to 4M uncached input + output tokens, while the per-5-hour limit remained 10M input + output tokens
  • Now the per-5-hour limit has been changed to 1M uncached input + output tokens
  • Therefore, there is now a 4x relationship between the per-5-hour limit and the weekly limit
  • Assuming 99.5% input (95% cached, 5% uncached) + 0.5% output ratio, old vs new limit comparison:
    • Old weekly limit 50M input + output tokens: 50M*0.5%=250K output tokens
    • New weekly limit 4M uncached input + output tokens: 4M*0.5%/(0.5%+99.5%*5%)=365K output tokens
    • Old per-5-hour limit 10M input + output tokens: 10M*0.5%=50K output tokens
    • New per-5-hour limit 1M uncached input + output tokens: 1M*0.5%/(0.5%+99.5%*5%)=91K output tokens
  • Assuming 99.5% input (90% cached, 10% uncached) + 0.5% output ratio, old vs new limit comparison:
    • Old weekly limit 50M input + output tokens: 50M*0.5%=250K output tokens
    • New weekly limit 4M uncached input + output tokens: 4M*0.5%/(0.5%+99.5%*10%)=191K output tokens
    • Old per-5-hour limit 10M input + output tokens: 10M*0.5%=50K output tokens
    • New per-5-hour limit 1M uncached input + output tokens: 1M*0.5%/(0.5%+99.5%*10%)=48K output tokens
  • As can be seen, whether the new or old limit is more restrictive depends on the cache hit rate
• 2026/02/16: GLM Coding Plan increased weekly limits from 4x the per-5-hour limit (320/1600/6400 prompts) to 5x (400/2000/8000 prompts). Meanwhile, GLM-5 consumption rate changed from 3x to 3x during peak hours and 2x during off-peak hours (peak hours: 14:00-18:00 UTC+8 daily).
• 2026/02/16: Recently discovered some changes in Kimi Code billing:
  • The Andante plan's per-5-hour limit remains unchanged at 10M input + output tokens, but the weekly limit observed when opening a new Code Session depletes faster, clearly not being 20% of the per-5-hour usage (previous calculation showed weekly limit was 5x the per-5-hour limit). However, with continued use, the ratio stays around 20%. Calculated using the previous method, weekly usage is approximately 48M input + output tokens rather than the original 50M—a rather odd number.
  • This question was explained by LLM Inference Systems, Code Agents, and Power Grids - Xu Xinran: cached tokens are not counted in usage.
  • If calculated by uncached input + output tokens, then weekly usage is 4M uncached input + output tokens; the 5-hour limit should still use the old calculation of 10M input + output tokens.
  • The purpose is that if Kimi Code is used for non-Vibe Coding scenarios with low cache hit rates, the weekly limit will be consumed quickly.
  • Further reading: suspiciously precise floats, or, how I got Claude's real limits
• 2026/02/15: MiniMax Coding Plan added Plus/Max/Ultra High Speed versions
• 2026/02/14: GLM Coding Plan added weekly limits at 4x the per-5-hour limit (Kimi is 5x, Volcano and Alibaba are 7.5x). Meanwhile, GLM-5 consumes quota at 3x the rate of GLM-4.7.
  • Unserious comment: Looks like at Zhipu, you only work 4 days a week, 5 hours a day, while at Moonshot you work 5 days a week, and at ByteDance and Alibaba you work 7.5 days a week. Which company has more overtime is clear at a glance, lol. (But ByteDance and Alibaba only work for two weeks a month; the other two weeks are off, this is the "big week small weeks" system?)
  • Serious comment: The new GLM Coding Plan's cost-effectiveness dropped from "夯"(S-level) to "NPC"(C-level), making Kimi/MiniMax's value stand out. The solution is to continue renewing the old plan and stick with GLM-4.7.
  • If calculated using the new plan at 2/3 of the old quota limit, using GLM-4.7, the Lite plan can use 40M*2/3*4*30/7=457M tokens per month (30 days); using GLM-5, it would be 40M*2/3*4*30/7/3=152M tokens.
• 2026/02/12: GLM Coding Plan prices changed from 40/200/400 RMB/month to 49/149/469 RMB/month; meanwhile, usage quotas were reduced to 2/3 of the original:
  • Lite Plan: Maximum ~80 prompts per 5 hours (was 120), equivalent to 3x Claude Pro plan usage
  • Pro Plan: Maximum ~400 prompts per 5 hours (was 600), equivalent to 5x Lite plan usage
  • Max Plan: Maximum ~1600 prompts per 5 hours (was 2400), equivalent to 4x Pro plan usage
  • If using the 2/3 ratio, the Lite plan limit would be 40/3*2=27M tokens per 5 hours. The new version also has weekly limits (specific rules published on 2026/02/14, see above). After switching to the new plan (I am not planning to), need to test what the new usage limits correspond to in tokens (interested readers can test and provide feedback).
• 2026/02/12: Added description for Kimi Allegro plan
• 2026/02/12: With the release of GLM-5, GLM Coding Plan's quota/limit API no longer returns specific token counts—presumably preparing for GLM-5 and GLM-4.7 to consume usage at different rates (based on API pricing, guessing there might be a 2x coefficient? Awaiting further testing). However, current testing shows GLM-4.7 usage limits remain unchanged; Lite plan is still 40M input + output tokens per 5 hours. Since there's only a per-5-hour limit, calculated at 30 days per month, theoretically maximum monthly usage could be 30*24/5*40=5760M tokens.
• 2026/01/30: Through actual testing, speculated that GLM Coding Plan's Lite plan usage limit is that the sum of all requests' input + output tokens does not exceed 40M per 5 hours (meaning each prompt corresponds to 40M/120=333K tokens), which is consistent with the results returned by the https://open.bigmodel.cn/api/monitor/usage/quota/limit API (after 2026/02/12, this API only returns percentages, not token counts).

Cite This

Comments