# QuotaBurn

> Agent cost & usage-limit tracker: plans, usage limits and per-token API prices for AI coding agents, each with an official source URL and last-verified date (data verified 2026-10-13).

## Data
- [Full dataset (JSON)](https://quotaburn.com/data.json)
- [Model API prices](https://quotaburn.com/models/)

## Tools
- [Claude Code pricing & limits](https://quotaburn.com/tools/claude-code/)
- [Cursor pricing & limits](https://quotaburn.com/tools/cursor/)
- [OpenAI Codex pricing & limits](https://quotaburn.com/tools/openai-codex/)
- [GitHub Copilot pricing & limits](https://quotaburn.com/tools/github-copilot/)
- [Windsurf (now Devin Desktop) pricing & limits](https://quotaburn.com/tools/windsurf-devin-desktop/)
- [Devin pricing & limits](https://quotaburn.com/tools/devin/)
- [Gemini CLI pricing & limits](https://quotaburn.com/tools/gemini-cli/)

## Guides
- [Cut your agent bill](https://quotaburn.com/cut-your-agent-bill/)
- [Claude Code usage limits explained](https://quotaburn.com/claude-code-usage-limits/)
- [Cursor pricing 2026 (with Grok plans)](https://quotaburn.com/cursor-pricing/)
- [Cheapest model for coding agents](https://quotaburn.com/cheapest-model-for-coding-agents/)
- [Codex vs Claude Code cost](https://quotaburn.com/codex-vs-claude-code-cost/)
- [How to stop hitting AI usage limits](https://quotaburn.com/stop-hitting-ai-usage-limits/)
- [Prompt caching savings calculator](https://quotaburn.com/prompt-caching-calculator/)
- [Methodology](https://quotaburn.com/methodology/)

## Quick facts
- Claude Fable 5.1 (Anthropic): $10 input / $50 output per 1M tokens (verified 2026-10-13, https://claude.com/pricing)
- Claude Opus 5.5 (Anthropic): $4 input / $20 output per 1M tokens (verified 2026-10-13, https://claude.com/pricing)
- Claude Sonnet 5.5 (Anthropic): $2 input / $10 output per 1M tokens (verified 2026-10-13, https://claude.com/pricing)
- Claude Haiku 5.5 (Anthropic): $0.5 input / $2.5 output per 1M tokens (verified 2026-10-13, https://claude.com/pricing)
- Claude Opus 5 (legacy) (Anthropic): $5 input / $25 output per 1M tokens (verified 2026-10-13, https://claude.com/pricing)
- Claude Sonnet 4.6 (legacy) (Anthropic): $3 input / $15 output per 1M tokens (verified 2026-10-13, https://claude.com/pricing)
- GPT-6 Astra (OpenAI): $10 input / $50 output per 1M tokens (verified 2026-10-13, https://platform.openai.com/docs/pricing)
- GPT-6.1 Sol (OpenAI): $2 input / $10 output per 1M tokens (verified 2026-10-13, https://platform.openai.com/docs/pricing)
- GPT-6 Luna (OpenAI): $0.1 input / $0.5 output per 1M tokens (verified 2026-10-13, https://platform.openai.com/docs/pricing)
- GPT-5.6 Sol (OpenAI): $4 input / $20 output per 1M tokens (verified 2026-10-13, https://platform.openai.com/docs/pricing)
- GPT-5.3 Codex (OpenAI): $1.75 input / $14 output per 1M tokens (verified 2026-10-13, https://platform.openai.com/docs/pricing)
- Gemini 4 Argon (Google): $2 input / $10 output per 1M tokens (verified 2026-10-13, https://ai.google.dev/gemini-api/docs/pricing)
- Gemini 3.8 Flash (Google): $0.75 input / $3.75 output per 1M tokens (verified 2026-10-13, https://ai.google.dev/gemini-api/docs/pricing)
- Gemini 3.1 Pro Preview (Google): $2 input / $12 output per 1M tokens (verified 2026-10-13, https://ai.google.dev/gemini-api/docs/pricing)
- Gemini 3.5 Flash-Lite (Google): $0.3 input / $2.5 output per 1M tokens (verified 2026-10-13, https://ai.google.dev/gemini-api/docs/pricing)
- Grok 4.7 (xAI): $2 input / $6 output per 1M tokens (verified 2026-10-13, https://docs.x.ai/docs/models)
- Grok Build 0.1 (xAI): $1 input / $2 output per 1M tokens (verified 2026-10-13, https://docs.x.ai/docs/models)
- Grok 4.3 (xAI): $1.25 input / $2.5 output per 1M tokens (verified 2026-10-13, https://docs.x.ai/docs/models)