{"object":"catalog","generated_at":1793169252,"data":[{"id":"gemini-3.5-flash","displayName":"Gemini 3.5 Flash","provider":"google","family":"Gemini 3.5","releaseDate":"2026-05-19","contextWindow":1000000,"maxOutputTokens":32000,"capabilities":["tools","streaming","vision","json_mode","reasoning","tool_choice"],"description":"Coding quality close to Gemini Pro at Flash-tier speed and cost. Strong tool use, high cache efficiency, 14× premium multiplier on Copilot. Pro / Pro+ / Business / Enterprise."},{"id":"claude-opus-4.7","displayName":"Claude Opus 4.7","provider":"anthropic","family":"Claude 4","releaseDate":"2026-04-16","contextWindow":192000,"maxOutputTokens":128000,"capabilities":["tools","streaming","vision","reasoning","tool_choice"],"description":"Anthropic's newest Opus. Long-horizon reasoning, multi-step tool execution, replaces 4.5/4.6 on Pro+. 15× premium multiplier (post-promo)."},{"id":"gpt-5.5","displayName":"GPT-5.5","provider":"openai","family":"GPT-5","releaseDate":"2026-04-15","contextWindow":400000,"maxOutputTokens":128000,"capabilities":["tools","streaming","vision","json_mode","reasoning","tool_choice"],"description":"OpenAI's newest flagship. Strongest reasoning + tool reliability in the GPT-5 line. Premium 7.5× multiplier on Copilot. Responses-API only.","supportedEndpoints":["responses"]},{"id":"claude-opus-4.6","displayName":"Claude Opus 4.6","provider":"anthropic","family":"Claude 4","releaseDate":"2026-04-10","contextWindow":200000,"maxOutputTokens":64000,"capabilities":["tools","streaming","vision","reasoning","tool_choice"],"description":"Prior flagship Opus. Being phased out on Pro+ in favour of 4.7, still listed for Business/Enterprise and the Claude coding agent."},{"id":"claude-opus-4.6-fast","displayName":"Claude Opus 4.6 (fast mode)","provider":"anthropic","family":"Claude 4","releaseDate":"2026-04-10","contextWindow":200000,"maxOutputTokens":64000,"capabilities":["tools","streaming","vision","tool_choice"],"description":"Preview fast-mode variant of Opus 4.6. Lower latency at the cost of some reasoning depth. Preview only."},{"id":"claude-sonnet-4.6","displayName":"Claude Sonnet 4.6","provider":"anthropic","family":"Claude 4","releaseDate":"2026-04-10","contextWindow":200000,"maxOutputTokens":64000,"capabilities":["tools","streaming","vision","reasoning","tool_choice"],"description":"Daily-driver Claude. Pairs with Opus 4.6 for cost-balanced agent fleets — excellent edit precision."},{"id":"raptor-mini","displayName":"Raptor mini","provider":"xai","family":"Raptor","releaseDate":"2026-04-01","contextWindow":256000,"maxOutputTokens":32000,"capabilities":["tools","streaming","vision"],"description":"xAI's compact Raptor model. Preview-only in Copilot. Built for high-throughput coding with very low latency."},{"id":"gemini-3.1-pro-preview","displayName":"Gemini 3.1 Pro (Preview)","provider":"google","family":"Gemini 3","releaseDate":"2026-03-20","contextWindow":2000000,"maxOutputTokens":64000,"capabilities":["tools","streaming","vision","json_mode","reasoning"],"description":"2M-context flagship Gemini. Preview only on Copilot. Native multimodal, structured-output strong."},{"id":"gpt-5.4","displayName":"GPT-5.4","provider":"openai","family":"GPT-5","releaseDate":"2026-03-01","contextWindow":400000,"maxOutputTokens":128000,"capabilities":["tools","streaming","vision","json_mode","reasoning","tool_choice"],"description":"Step over 5.3-Codex with stronger general reasoning. Solid daily driver for whole-repo refactors."},{"id":"gpt-5.4-mini","displayName":"GPT-5.4 mini","provider":"openai","family":"GPT-5","releaseDate":"2026-03-01","contextWindow":400000,"maxOutputTokens":64000,"capabilities":["tools","streaming","vision","json_mode","reasoning"],"description":"Mid-tier 5.4 — faster than 5.4 base with similar context. Responses-API only on Copilot.","supportedEndpoints":["responses"]},{"id":"gpt-5.4-nano","displayName":"GPT-5.4 nano","provider":"openai","family":"GPT-5","releaseDate":"2026-03-01","contextWindow":200000,"maxOutputTokens":64000,"capabilities":["tools","streaming","vision","json_mode","reasoning"],"description":"Compact 5.4 sibling. Copilot Pro+ exclusive, currently surfaced only in the Codex VS Code extension."},{"id":"gemini-3-flash-preview","displayName":"Gemini 3 Flash (Preview)","provider":"google","family":"Gemini 3","releaseDate":"2026-02-10","contextWindow":1000000,"maxOutputTokens":32000,"capabilities":["tools","streaming","vision","json_mode"],"description":"Fast Gemini 3 tier. 1M context with low latency. Preview only on Copilot."},{"id":"gpt-5.3-codex","displayName":"GPT-5.3 Codex","provider":"openai","family":"GPT-5","releaseDate":"2026-02-01","contextWindow":400000,"maxOutputTokens":128000,"capabilities":["tools","streaming","vision","json_mode","reasoning","tool_choice"],"description":"Code-tuned 5.3. Specialised for diff-shaped output and multi-file edits. Responses-API only.","supportedEndpoints":["responses"]},{"id":"claude-sonnet-4.5","displayName":"Claude Sonnet 4.5","provider":"anthropic","family":"Claude 4","releaseDate":"2026-02-01","contextWindow":200000,"maxOutputTokens":64000,"capabilities":["tools","streaming","vision","reasoning","tool_choice"],"description":"Workhorse Sonnet. Mature tool protocol; the most predictable Claude for code-edit benchmarks."},{"id":"claude-opus-4.5","displayName":"Claude Opus 4.5","provider":"anthropic","family":"Claude 4","releaseDate":"2026-01-20","contextWindow":200000,"maxOutputTokens":64000,"capabilities":["tools","streaming","vision","reasoning","tool_choice"],"description":"Prior-gen Opus. Still strong for deep refactors when latency or cost matter more than raw frontier capability."},{"id":"claude-haiku-4.5","displayName":"Claude Haiku 4.5","provider":"anthropic","family":"Claude 4","releaseDate":"2026-01-20","contextWindow":200000,"maxOutputTokens":32000,"capabilities":["tools","streaming","vision","tool_choice"],"description":"Smallest, fastest Claude 4. Cheap completions, autocomplete loops, and high-volume agent fan-out."},{"id":"gpt-5.2","displayName":"GPT-5.2","provider":"openai","family":"GPT-5","releaseDate":"2025-12-01","contextWindow":400000,"maxOutputTokens":128000,"capabilities":["tools","streaming","vision","json_mode","reasoning","tool_choice"],"description":"Mid-cycle 5.x. Balances cost and reasoning, popular in agent loops."},{"id":"gpt-5.2-codex","displayName":"GPT-5.2 Codex","provider":"openai","family":"GPT-5","releaseDate":"2025-12-01","contextWindow":400000,"maxOutputTokens":128000,"capabilities":["tools","streaming","vision","json_mode","reasoning","tool_choice"],"description":"5.2 fine-tuned for code edits. Strong at staying in-protocol over long agent sessions. Responses-API only.","supportedEndpoints":["responses"]},{"id":"grok-code-fast-1","displayName":"Grok Code Fast 1","provider":"xai","family":"Grok","releaseDate":"2025-11-15","contextWindow":256000,"maxOutputTokens":32000,"capabilities":["tools","streaming"],"description":"Code-tuned Grok. 0× premium multiplier on Copilot — effectively free for high-volume experimentation. Zero data-retention upstream."},{"id":"gpt-5.1","displayName":"GPT-5.1","provider":"openai","family":"GPT-5","releaseDate":"2025-10-15","contextWindow":400000,"maxOutputTokens":128000,"capabilities":["tools","streaming","vision","json_mode","reasoning","tool_choice"],"description":"First incremental over GPT-5. Improved tool-call reliability and lower latency."},{"id":"gpt-5.1-codex","displayName":"GPT-5.1 Codex","provider":"openai","family":"GPT-5","releaseDate":"2025-10-15","contextWindow":400000,"maxOutputTokens":128000,"capabilities":["tools","streaming","vision","json_mode","reasoning","tool_choice"],"description":"5.1 Codex variant. Stronger refactor and bug-fix benchmarks than 5.1 base."},{"id":"gpt-5.1-codex-max","displayName":"GPT-5.1 Codex Max","provider":"openai","family":"GPT-5","releaseDate":"2025-10-15","contextWindow":400000,"maxOutputTokens":128000,"capabilities":["tools","streaming","vision","json_mode","reasoning","tool_choice"],"description":"Heavyweight 5.1 Codex. Built for very long agentic sessions and architectural review."},{"id":"gpt-5.1-codex-mini","displayName":"GPT-5.1 Codex Mini","provider":"openai","family":"GPT-5","releaseDate":"2025-10-15","contextWindow":200000,"maxOutputTokens":64000,"capabilities":["tools","streaming","vision","json_mode","reasoning"],"description":"Compact 5.1 Codex. High throughput, low latency for autocomplete-style loops."},{"id":"gpt-5","displayName":"GPT-5","provider":"openai","family":"GPT-5","releaseDate":"2025-08-07","contextWindow":400000,"maxOutputTokens":128000,"capabilities":["tools","streaming","vision","json_mode","reasoning","tool_choice"],"description":"Initial GPT-5 release. Long context, tool-aware, strong code synthesis. Baseline reference for the 5.x series."},{"id":"gpt-5-mini","displayName":"GPT-5 mini","provider":"openai","family":"GPT-5","releaseDate":"2025-08-07","contextWindow":400000,"maxOutputTokens":128000,"capabilities":["tools","streaming","vision","json_mode","reasoning"],"description":"Lighter, faster GPT-5 sibling. Excellent default for high-throughput coding agents."},{"id":"claude-sonnet-4","displayName":"Claude Sonnet 4","provider":"anthropic","family":"Claude 4","releaseDate":"2025-05-22","contextWindow":200000,"maxOutputTokens":64000,"capabilities":["tools","streaming","vision","tool_choice"],"description":"First-gen Claude 4 Sonnet. Stable tool-use protocol, broadly tested across coding agents."},{"id":"gpt-4.1","displayName":"GPT-4.1","provider":"openai","family":"GPT-4","releaseDate":"2025-04-14","contextWindow":1000000,"maxOutputTokens":32000,"capabilities":["tools","streaming","vision","json_mode","tool_choice"],"description":"1M-context successor to GPT-4o. Best in class for whole-repo grounding and long-form refactors."},{"id":"gpt-4.1-2025-04-14","displayName":"GPT-4.1 (2025-04-14 snapshot)","provider":"openai","family":"GPT-4","releaseDate":"2025-04-14","contextWindow":1000000,"maxOutputTokens":32000,"capabilities":["tools","streaming","vision","json_mode","tool_choice"],"description":"Pin GPT-4.1 to its launch-day weights. Use when you need bit-identical replay of older runs."},{"id":"gemini-2.5-pro","displayName":"Gemini 2.5 Pro","provider":"google","family":"Gemini 2.5","releaseDate":"2025-03-25","contextWindow":1000000,"maxOutputTokens":64000,"capabilities":["tools","streaming","vision","json_mode","reasoning"],"description":"Prior flagship Gemini. 1M context, mature tool-use, dependable for structured output."},{"id":"gpt-4o-2024-11-20","displayName":"GPT-4o (2024-11-20 snapshot)","provider":"openai","family":"GPT-4","releaseDate":"2024-11-20","contextWindow":128000,"maxOutputTokens":16384,"capabilities":["tools","streaming","vision","json_mode","tool_choice"],"description":"Most recent GPT-4o snapshot. Pin when you need stable output across deploys."},{"id":"gpt-4o-2024-08-06","displayName":"GPT-4o (2024-08-06 snapshot)","provider":"openai","family":"GPT-4","releaseDate":"2024-08-06","contextWindow":128000,"maxOutputTokens":16384,"capabilities":["tools","streaming","vision","json_mode","tool_choice"],"description":"Mid-2024 GPT-4o snapshot. Introduced structured outputs / strict JSON mode."},{"id":"gpt-4o-mini","displayName":"GPT-4o mini","provider":"openai","family":"GPT-4","releaseDate":"2024-07-18","contextWindow":128000,"maxOutputTokens":16384,"capabilities":["tools","streaming","vision","json_mode","tool_choice"],"description":"Lighter GPT-4o for high-volume completions. Same 128K context, much cheaper per token."},{"id":"gpt-4o-mini-2024-07-18","displayName":"GPT-4o mini (2024-07-18 snapshot)","provider":"openai","family":"GPT-4","releaseDate":"2024-07-18","contextWindow":128000,"maxOutputTokens":16384,"capabilities":["tools","streaming","vision","json_mode","tool_choice"],"description":"GPT-4o mini snapshot. Cheaper batch jobs and high-throughput agents."},{"id":"gpt-4o","displayName":"GPT-4o","provider":"openai","family":"GPT-4","releaseDate":"2024-05-13","contextWindow":128000,"maxOutputTokens":16384,"capabilities":["tools","streaming","vision","json_mode","tool_choice"],"description":"OpenAI's omni-model. Fast, multimodal, broadly supported across legacy coding tools."},{"id":"gpt-4o-2024-05-13","displayName":"GPT-4o (2024-05-13 launch)","provider":"openai","family":"GPT-4","releaseDate":"2024-05-13","contextWindow":128000,"maxOutputTokens":4096,"capabilities":["tools","streaming","vision","json_mode","tool_choice"],"description":"Original GPT-4o launch weights. Lower output cap (4K) and no structured outputs."},{"id":"gpt-4","displayName":"GPT-4","provider":"openai","family":"GPT-4","releaseDate":"2023-03-14","contextWindow":8192,"maxOutputTokens":4096,"capabilities":["tools","streaming","json_mode","tool_choice"],"description":"Original GPT-4. Kept for backwards-compatibility with older agents pinned to this id."},{"id":"gpt-3.5-turbo","displayName":"GPT-3.5 Turbo","provider":"openai","family":"GPT-3.5","releaseDate":"2023-03-01","contextWindow":16385,"maxOutputTokens":4096,"capabilities":["tools","streaming","json_mode"],"description":"Legacy chat model. Cheap and fast; useful for trivial routing/classification work."}]}