Beta
Download

Models

The models AutoRouter adds to Codex and Claude Code, with each one's list price and the plan it runs on.

All models

ModelMakerGood forRuns onPrice
Claude Fable 5.2AnthropicEspecially demanding, long-horizon coding, research and reasoning.Claude plan$8 / $40
GPT-6 AstraOpenAIDifficult architecture, security, science and computer-use work.ChatGPT plan$10 / $50
GPT-6.1 SolOpenAIDefault for general implementation, grounded research and analysis.ChatGPT plan$2 / $10
Claude Opus 5.5AnthropicBroad refactoring and demanding creative or editorial work.Claude plan$4 / $20
Claude Sonnet 5.5AnthropicUI implementation, writing, and a faster Claude option.Claude plan$2 / $10
Claude Haiku 5.5AnthropicLower-priced Claude option for bounded everyday work.Claude plan$0.10 / $0.50
GPT-6.1 TerraOpenAILower-priced everyday coding, writing and screen or image work.ChatGPT plan
GPT-6 SolOpenAIA faster-turnaround alternative to GPT-6.1 Sol.ChatGPT plan$2 / $10
GPT-6 LunaOpenAIRoutine extraction, text processing and simple tasks.ChatGPT plan$0.10 / $0.50
Gemini 4 CarbonGoogleSustained agentic engineering and complex coding.AutoRouter Pro
Gemini 4 ArgonGoogleGoogle's frontier model at a fifth of Astra's price.AutoRouter Pro$2 / $10
Kimi K3.1 ProMoonshot AIOpen-weight reasoning and coding across long supplied documents.AutoRouter Pro
Muse WonderMetaMeta's frontier model; priced above Gemini 4 Argon.AutoRouter Pro$4 / $20
Muse Spark 1.3MetaMetered choice for medium tasks when no subscription has allowance.AutoRouter Pro$1.25 / $4.25
Muse EmberMetaLow-cost reasoning for agent sub-tasks and bounded coding.AutoRouter Pro
Grok 4.7xAIA second opinion when you ask for one.AutoRouter Pro
Tencent Hy4TencentLong-context analysis and bounded frontend or game-development tasks.AutoRouter Pro
Qwen3.8 Max 0902AlibabaQwen alternative for bounded UI implementation and long-document code analysis.AutoRouter Pro
DeepSeek V4.1 Flash 1017DeepSeekBounded, well-specified code changes that are easy to verify.AutoRouter Pro$0.30 / $1.20
GLM 5.3Z.aiHigher-capability open-weight coding.AutoRouter Pro$1.40 / $4.40
MiMo V2.6 ProXiaomiStrong open-weight generalist at a low price.AutoRouter Pro$0.435 / $0.87
MiniMax M3.1 FlashMiniMaxLow-cost open-weight option for easy tasks.AutoRouter Pro$0.15 / $0.60
GLM 5.3 FlashZ.aiCheap structured extraction, counts and checklists.AutoRouter Pro$0.15 / $0.50
MiMo V2.6 FlashXiaomiCheapest open-weight option for simple tasks.AutoRouter Pro$0.14 / $0.28
Muse Spark OpenMetaMeta's open-weight Muse, served through Ramp.AutoRouter Pro$1.25 / $4.25
Kimi K3Moonshot AIOpen-weight reasoning across long supplied documents.AutoRouter Pro$3 / $15
GPT-5.6 SolOpenAIAn older alternative kept for compatibility.ChatGPT plan$4 / $20
GPT-5.6 LunaOpenAIAn older alternative kept for compatibility.ChatGPT plan$0.20 / $1.20
Crouton AlphaUnnamedFree stealth model for high-volume, repeated agent sub-tasks; its developer is unnamed.AutoRouter Pro

This is the set AutoRouter's team curates. You can add more models, older versions among them, in the app's Models tab. In Claude Code, Claude models run on your Claude plan. In Codex, OpenAI models run on your ChatGPT plan. Every other model comes with AutoRouter Pro and bills at the provider's price plus 10%. Prices are list prices in US dollars per million tokens, input then output, at each model's short-prompt rate: the makers' API prices for Anthropic and OpenAI, and the hosts' prices for the other models.