# BurnRate

> Plans, usage limits and a dated changelog for agentic coding tools. Data updated 2026-10-22. Canonical: https://burnratehq.dev/ · JSON: https://burnratehq.dev/api/tools.json

## Changes in the last 7 days

- 2026-10-22 · OpenCode · limit: OpenCode Go's limited-time 4x boost on Step 5 Preview has ended: its monthly limit is back to $15 on Go and $60 on Go Plus (was $60 and $240). The 'Use balance' fallback is now called Extra usage. (source: https://opencode.ai/v2/docs/console/go/)
- 2026-10-20 · Kiro CLI · feature: Kiro CLI 2.33.0 adds workspace trust: interactive V3 sessions ask before loading a folder's hooks, agents, MCP servers, steering or workflows. Model fallback is back in V3 sessions. (source: https://kiro.dev/changelog/)
- 2026-10-19 · GitHub Copilot CLI · model: Copilot deprecates Gemini 3.7 Flash, GPT-5.5, GPT-5.4, GPT-5.4 mini, GPT-5 mini and Grok 4.5 (announced Sep 18). (source: https://github.blog/changelog/2026-10-19-github-copilot-models-deprecated-on-october-19-2026/)
- 2026-10-18 · OpenClaw · model: OpenClaw 2026.10.5 adds Gemini 4 Argon (Google and Vertex) and Gemini 3.8 Flash; rerunning Google API-key setup picks Argon as the primary model. (source: https://github.com/openclaw/openclaw/blob/main/CHANGELOG/2026.10.5.md)
- 2026-10-16 · OpenCode · model: OpenCode Go drops Grok 4.6, Kimi K2.6 and MiniMax M2.7; Step 5 Preview no longer free on Go ($15 monthly allowance, temporarily $60). (source: https://github.com/anomalyco/opencode/pull/55761)
- 2026-10-16 · Cline · model: Cline extension 4.1.25: with no model chosen, the Cline provider uses Gemini 4 Argon instead of Claude Sonnet 5.5; OpenRouter stays on Sonnet 5.5. (source: https://github.com/cline/cline/releases/tag/v4.1.25)

## Tools

### Claude Code (Anthropic)
- Page: https://burnratehq.dev/tools/claude-code/
- Type: cli · Open source: no · BYOK: yes · MCP: client · Headless: claude -p
- Plan Free: $0/mo; No Claude Code on Free (source: https://claude.com/pricing, checked 2026-10-20)
- Plan Pro: $20/mo; Rolling 5-hour session window + weekly limit, shared with claude.ai; no fixed message count (source: https://claude.com/pricing, checked 2026-10-20)
- Plan Max 5x: $100/mo; 5x Pro usage per 5-hour session + weekly limit; includes $100/mo API credits (not usable for interactive Claude Code) (source: https://claude.com/pricing, checked 2026-10-20)
- Plan Max 20x: $200/mo; 20x Pro usage per 5-hour session + weekly limit; includes $200/mo API credits (source: https://claude.com/pricing, checked 2026-10-20)
- Change 2026-10-14 (feature): Claude Code 2.1.299 waits 300s instead of 180s for a stream through a custom base URL. (source: https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md#21299)
- Change 2026-10-07 (price): Max and Team plans now include monthly API credits ($100 Max 5x, $200 Max 20x); plan prices and usage limits unchanged. (source: https://support.claude.com/en/articles/15036540-use-the-claude-agent-sdk-with-your-claude-plan)
- Change 2026-10-07 (model): Claude Code 2.1.293 makes Haiku 5.5 the default Haiku on the API ($0.10/$0.50 per 1M tokens; $0.50/$2.50 on prompts over 100K). (source: https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md#21293)

### OpenAI Codex (CLI) (OpenAI)
- Page: https://burnratehq.dev/tools/codex/
- Type: hybrid · Open source: yes · BYOK: yes · MCP: client+server · Headless: codex exec
- Plan ChatGPT Free: $0/mo; GPT-6 Luna in desktop app only, subject to rollout (source: https://developers.openai.com/codex/pricing, checked 2026-10-20)
- Plan ChatGPT Go: $8/mo; GPT-6 Luna in desktop app only, subject to rollout (source: https://developers.openai.com/codex/pricing, checked 2026-10-20)
- Plan ChatGPT Plus: $20/mo; 5-hour window (vendor estimate 15-160 local msgs/5h on GPT-6.1 Sol) + weekly limits may apply (source: https://developers.openai.com/codex/pricing, checked 2026-10-20)
- Plan ChatGPT Pro: $100/mo; No 5-hour limit; weekly limit. Also $200 and $500 tiers; Ultrafast mode on Pro $500 only (source: https://developers.openai.com/codex/pricing, checked 2026-10-20)
- Change 2026-10-14 (model): GPT-5.5 retired from Codex with ChatGPT sign-in (API-key sessions unaffected). (source: https://developers.openai.com/codex/pricing)
- Change 2026-10-08 (price): Ultrafast mode for GPT-6.1 Sol: Pro $500 only in Codex, uses 8x included usage (6x on purchased credits). (source: https://developers.openai.com/codex/pricing)
- Change 2026-10-07 (model): Codex CLI 0.161.0 makes GPT-6.1 Sol the default model. (source: https://github.com/openai/codex/releases/tag/rust-v0.161.0)
- Community pulse (UNCONFIRMED, community reported): Many posts Oct 16-19 report 5-hour and weekly limits draining far faster than expected; an OpenAI Codex lead posted on Oct 16 that changes increase effective usage. Community reported, unconfirmed.

### Cursor (Anysphere (sold via The X Subscription))
- Page: https://burnratehq.dev/tools/cursor/
- Type: ide · Open source: no · BYOK: ? · MCP: client · Headless: unknown
- Plan Free: $0/mo; Limited agent requests (source: https://cursor.com/help/account-and-billing/pricing, checked 2026-10-20)
- Plan Plus: $8/mo; Base weekly pool shared with Grok; Grok models only, fixed settings (source: https://cursor.com/help/account-and-billing/pricing, checked 2026-10-20)
- Plan Premium: $30/mo; 4x Plus weekly pool; third-party models (Claude, GPT, Gemini) billed at API list price from top-up credit (source: https://cursor.com/help/account-and-billing/pricing, checked 2026-10-20)
- Plan Super: $100/mo; 15x Plus weekly pool; priority at peak (source: https://cursor.com/help/account-and-billing/pricing, checked 2026-10-20)
- Plan Ultra: $200/mo; 50x Plus weekly pool (source: https://cursor.com/help/account-and-billing/pricing, checked 2026-10-20)
- Change 2026-10-12 (price): Pro ($20), Pro+ and old Ultra closed to new signups. New plans via The X Subscription: Plus $8 (Grok only), Premium $30, Super $100, Ultra $200, with weekly (not monthly) allowances. Existing subscribers keep their plan until they switch. (source: https://forum.cursor.com/t/introducing-the-x-subscription/174450)
- Community pulse (UNCONFIRMED, community reported): X post volume about Cursor's new X Subscription pricing peaked Oct 13 (about 180 posts that day in our count query) and stayed at 45-60/day after. Sample post not captured this run. Community reported, unconfirmed.

### OpenCode (Anomaly (SST))
- Page: https://burnratehq.dev/tools/opencode/
- Type: cli · Open source: yes · BYOK: yes · MCP: client · Headless: opencode run
- Plan Free (BYOK): $0/mo; No limits of its own; you pay your model provider (75+ providers) (source: https://caprock.dev/guides/ai-coding-agents/, checked 2026-10-20)
- Plan Go: $10/mo; Per-model dollar caps: 5h = 20% and weekly = 50% of each model's monthly limit (source: https://opencode.ai/v2/docs/console/go/, checked 2026-10-22)
- Plan Go Plus: $40/mo; Same models with 2-8x higher per-model monthly limits; same 20%/50% windows (source: https://opencode.ai/v2/docs/console/go/, checked 2026-10-22)
- Change 2026-10-22 (limit): OpenCode Go's limited-time 4x boost on Step 5 Preview has ended: its monthly limit is back to $15 on Go and $60 on Go Plus (was $60 and $240). The 'Use balance' fallback is now called Extra usage. (source: https://opencode.ai/v2/docs/console/go/)
- Change 2026-10-16 (model): OpenCode Go drops Grok 4.6, Kimi K2.6 and MiniMax M2.7; Step 5 Preview no longer free on Go ($15 monthly allowance, temporarily $60). (source: https://github.com/anomalyco/opencode/pull/55761)
- Change 2026-10-11 (feature): OpenCode 1.19.0: updates are no longer installed automatically (use /update), and `opencode upgrade --major` moves to OpenCode 2. (source: https://github.com/anomalyco/opencode/releases/tag/v1.19.0)

### OpenClaw (OpenClaw Foundation (501(c)(3)))
- Page: https://burnratehq.dev/tools/openclaw/
- Type: self-hosted agent · Open source: yes · BYOK: yes · MCP: unknown · Headless: unknown
- Plan Self-hosted (free): $0/mo; No paid tier, hosted service or token; you pay model API usage and hosting (source: https://github.com/openclaw/openclaw, checked 2026-10-20)
- Change 2026-10-18 (model): OpenClaw 2026.10.5 adds Gemini 4 Argon (Google and Vertex) and Gemini 3.8 Flash; rerunning Google API-key setup picks Argon as the primary model. (source: https://github.com/openclaw/openclaw/blob/main/CHANGELOG/2026.10.5.md)
- Change 2026-10-12 (feature): OpenClaw 2026.10.2 makes provider-managed compaction the default for eligible direct OpenAI Responses and Anthropic API-key chats. (source: https://github.com/openclaw/openclaw/blob/main/CHANGELOG/2026.10.2.md)
- Change 2026-10-08 (model): OpenClaw 2026.9.9 points the `haiku` alias and Anthropic utility-model default at Haiku 5.5 (costs more on prompts over 100K). (source: https://github.com/openclaw/openclaw/blob/main/CHANGELOG/2026.9.9.md)

### Antigravity CLI (ex-Gemini CLI) (Google)
- Page: https://burnratehq.dev/tools/antigravity-cli/
- Type: hybrid · Open source: ? · BYOK: ? · MCP: unknown · Headless: unknown
- Plan Individual (free): $0/mo; Basic weekly rate limit ('a meaningful quota, refreshed weekly'); no numeric limit published (source: https://antigravity.google/docs/plans/, checked 2026-10-20)
- Plan Google AI Pro: $20/mo; Quota refreshed every 5 hours until weekly limit; separate weekly-only Gemini 4 Argon quota (source: https://antigravity.google/docs/plans/, checked 2026-10-20)
- Plan Google AI Ultra: $100/mo; 5x Pro tokens (source: https://antigravity.google/blog/changes-to-antigravity-plans/, checked 2026-10-20)
- Plan Google AI Ultra (top): $200/mo; 20x Pro tokens; third-party models (source: https://antigravity.google/blog/changes-to-antigravity-plans/, checked 2026-10-20)
- Change 2026-11-02 (model): Claude 4.6 models and GPT-OSS-120b to be removed from the free Individual tier (announced). (source: https://antigravity.google/docs/models/)
- Change 2026-10-15 (limit): Gemini 4 Argon rolled out to paid Google AI Pro subscribers with a separate weekly-only Argon quota on top of the 3.8 Flash bucket. (source: https://x.com/antigravity/status/2110866531932316011)
- Change 2026-10-09 (price): Gemini Code Assist Standard and Enterprise no longer sold to new customers; existing annual plans can renew until Jan 31, 2027 and monthly until Dec 31, 2027. Google points customers to Antigravity via Gemini Enterprise. (source: https://docs.cloud.google.com/gemini/docs/codeassist/sunset)
- Community pulse (UNCONFIRMED, community reported): Spike of quota complaints around Oct 16 after Argon reached Pro (about 240 posts that day in our count query); paid users report hitting limits after a few prompts. Community reported, unconfirmed.

### GitHub Copilot CLI (GitHub (Microsoft))
- Page: https://burnratehq.dev/tools/copilot-cli/
- Type: cli · Open source: no · BYOK: ? · MCP: client · Headless: copilot -p
- Plan Free: $0/mo; Limited; auto model selection only; 2,000 completions/mo (source: https://docs.github.com/en/copilot/concepts/billing-and-usage/individuals/billing, checked 2026-10-20)
- Plan Pro: $10/mo; 1,500 AI credits/mo (1 credit = $0.01), resets on the 1st (UTC); no premium models (source: https://docs.github.com/en/copilot/concepts/billing-and-usage/individuals/billing, checked 2026-10-20)
- Plan Pro+: $39/mo; 7,000 AI credits/mo; premium models (source: https://docs.github.com/en/copilot/concepts/billing-and-usage/individuals/billing, checked 2026-10-20)
- Plan Max: $100/mo; 20,000 AI credits/mo; premium models (source: https://docs.github.com/en/copilot/concepts/billing-and-usage/individuals/billing, checked 2026-10-20)
- Change 2026-10-19 (model): Copilot deprecates Gemini 3.7 Flash, GPT-5.5, GPT-5.4, GPT-5.4 mini, GPT-5 mini and Grok 4.5 (announced Sep 18). (source: https://github.blog/changelog/2026-10-19-github-copilot-models-deprecated-on-october-19-2026/)
- Change 2026-10-15 (model): Copilot will retire Claude Opus 4.8, Claude Opus 5 and GPT-5.6 Terra on Nov 16 (Opus 4.8 stays for individual annual plans). (source: https://github.blog/changelog/2026-10-15-upcoming-deprecation-of-selected-github-copilot-models-in-mid-november/)
- Change 2026-10-13 (model): Gemini 4 Argon added to Copilot Pro+, Max, Business and Enterprise at provider list price; not on Pro. (source: https://github.blog/changelog/2026-10-13-gemini-4-argon-in-github-copilot/)

### Kiro CLI (AWS)
- Page: https://burnratehq.dev/tools/kiro-cli/
- Type: cli · Open source: no · BYOK: ? · MCP: client · Headless: kiro-cli chat --no-interactive
- Plan Free: $0/mo; 50 credits/mo (source: https://kiro.dev/pricing/, checked 2026-10-20)
- Plan Pro: $20/mo; 1,000 credits/mo (source: https://kiro.dev/pricing/, checked 2026-10-20)
- Plan Pro+: $40/mo; 2,000 credits/mo (source: https://kiro.dev/pricing/, checked 2026-10-20)
- Plan Pro Max: $100/mo; 5,000 credits/mo (source: https://kiro.dev/pricing/, checked 2026-10-20)
- Plan Power: $200/mo; 10,000 credits/mo; add-on credits $0.04 each (source: https://kiro.dev/pricing/, checked 2026-10-20)
- Change 2026-10-20 (feature): Kiro CLI 2.33.0 adds workspace trust: interactive V3 sessions ask before loading a folder's hooks, agents, MCP servers, steering or workflows. Model fallback is back in V3 sessions. (source: https://kiro.dev/changelog/)
- Change 2026-10-15 (feature): Kiro CLI 2.32.0: folder-wide write approvals in V3 sessions, V3 cloud sessions runnable from non-interactive commands, and workflow plan previews before any step runs. (source: https://kiro.dev/changelog/)
- Change 2026-10-12 (feature): Kiro CLI 2.30.0 starts a gradual prompt to switch to the V3 harness; Kiro says V3 becomes the default with CLI 3.0 at the end of October. (source: https://kiro.dev/changelog/)

### Goose (Goose project (originally Block))
- Page: https://burnratehq.dev/tools/goose/
- Type: cli · Open source: yes · BYOK: yes · MCP: client · Headless: goose run
- Plan Free (BYOK): $0/mo; Free and open source; you pay your model provider (source: https://hidekazu-konishi.com/entry/cli_coding_agents_comparison.html, checked 2026-10-20)

### Aider (Aider-AI (open source))
- Page: https://burnratehq.dev/tools/aider/
- Type: cli · Open source: yes · BYOK: yes · MCP: none documented · Headless: aider --message
- Plan Free (BYOK): $0/mo; Free and open source; you pay your model provider (source: https://hidekazu-konishi.com/entry/cli_coding_agents_comparison.html, checked 2026-10-20)

### Cline (Cline)
- Page: https://burnratehq.dev/tools/cline/
- Type: hybrid · Open source: yes · BYOK: yes · MCP: client · Headless: unknown
- Plan Free (BYOK): $0/mo; Extension/CLI free; BYOK or pay-as-you-go Cline credits (source: https://docs.cline.bot/getting-started/clinepass, checked 2026-10-20)
- Plan ClinePass: $9.99/mo; Curated open-weight models; rolling 5-hour, weekly and monthly caps (source: https://docs.cline.bot/getting-started/clinepass, checked 2026-10-20)
- Change 2026-10-16 (model): Cline extension 4.1.25: with no model chosen, the Cline provider uses Gemini 4 Argon instead of Claude Sonnet 5.5; OpenRouter stays on Sonnet 5.5. (source: https://github.com/cline/cline/releases/tag/v4.1.25)
- Change 2026-10-13 (model): With no model chosen, Cline and OpenRouter providers default to Claude Sonnet 5.5. (source: https://github.com/cline/cline/releases/tag/v4.1.24)
- Change 2026-09-24 (model): ClinePass drops GLM-5.2, Kimi K2.6, Kimi K2.7 Code and DeepSeek V4 Flash; adds DeepSeek V4.1 Flash and Muse Spark 1.3. Price unchanged. (source: https://standardcompute.com/ai-coding-plan-changes)

### Qwen Code (Alibaba (Qwen team))
- Page: https://burnratehq.dev/tools/qwen-code/
- Type: cli · Open source: yes · BYOK: yes · MCP: client · Headless: qwen -p
- Plan Free (BYOK): $0/mo; Qwen OAuth free tier discontinued 2026-04-15; use an API key, Alibaba Cloud Coding Plan, OpenRouter, etc. (source: https://qwenlm.github.io/qwen-code-docs/en/users/configuration/auth/, checked 2026-10-20)
- Plan Alibaba Cloud Coding Plan: price unknown; unknown (source: https://qwenlm.github.io/qwen-code-docs/en/users/configuration/auth/, checked 2026-10-20)
- Change 2026-04-15 (price): Qwen OAuth free tier discontinued (cut from 1,000 to 100 requests/day on Apr 13, then ended). (source: https://github.com/QwenLM/qwen-code/pull/3291)

### Warp (Warp)
- Page: https://burnratehq.dev/tools/warp/
- Type: terminal · Open source: no · BYOK: yes · MCP: client · Headless: unknown
- Plan Free: $0/mo; No included AI usage; pay-as-you-go or BYOK (source: https://www.warp.dev/pricing, checked 2026-10-20)
- Plan Build: $20/mo; $20 of agent usage at API rates included per month; add-on usage purchasable (source: https://www.warp.dev/pricing, checked 2026-10-20)

### Kimi Code CLI (Moonshot AI)
- Page: https://burnratehq.dev/tools/kimi-code/
- Type: cli · Open source: ? · BYOK: ? · MCP: unknown · Headless: unknown
- Plan Plus: $19/mo; Shared monthly credit pool (CLI, VS Code, desktop, API key); rolling 5-hour limit, no weekly limit on new plans (source: https://www.kimi.com/code/docs/en/kimi-code/membership, checked 2026-10-20)
- Plan Pro: $39/mo; Larger pool; same window rules (source: https://www.kimi.com/en/help/membership/membership-pricing, checked 2026-10-20)
- Plan Max: $99/mo; Larger pool (source: https://www.kimi.com/en/help/membership/membership-pricing, checked 2026-10-20)
- Plan Ultra: $199/mo; Largest pool (source: https://www.kimi.com/en/help/membership/membership-pricing, checked 2026-10-20)

### Grok Build (xAI (SpaceXSI))
- Page: https://burnratehq.dev/tools/grok-build/
- Type: cli · Open source: no · BYOK: yes · MCP: client · Headless: grok -p
- Plan Free: $0/mo; Limited Grok Build access (source: https://cursor.com/pricing, checked 2026-10-20)
- Plan Plus: $8/mo; Shared weekly pool with Grok and Cursor (base) (source: https://docs.x.ai/x-subscription/pricing, checked 2026-10-20)
- Plan Premium: $30/mo; 4x Plus (source: https://docs.x.ai/x-subscription/pricing, checked 2026-10-20)
- Plan Super: $100/mo; 15x Plus (source: https://docs.x.ai/x-subscription/pricing, checked 2026-10-20)
- Plan Ultra: $200/mo; 50x Plus (source: https://docs.x.ai/x-subscription/pricing, checked 2026-10-20)
- Plan API key: price unknown; grok-build-0.1: $1/M input, $0.20/M cached, $2/M output (source: https://docs.x.ai/developers/pricing, checked 2026-10-20)
- Change 2026-10-12 (price): Grok Build bundled into The X Subscription (Plus $8 / Premium $30 / Super $100 / Ultra $200) with a weekly usage pool shared with Grok and Cursor. (source: https://x.ai/news/x-subscription)