Models
The models Standards offers, published from a Standards workspace.
Conversation models
Auto is the routing mode that picks a model per turn. A chip names a task the model is qualified for and the highest demand it serves — light, standard or heavy, each a ceiling that includes the levels below.
- Luna 6Recommendedopenai/gpt-6-lunaAutoconversation · lightwriting · lightcoding · lightanalysis · lightextraction · light1.1M$0.10 / $0.50
- Opus 5.5anthropic/claude-opus-5.5Autoconversation · standardwriting · heavycoding · heavyanalysis · heavyextraction · heavy1M$4 / $20
- Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-liteAutomanual only1M$0.30 / $2.50
- Grok 4.7spacexai/grok-4.7Autoconversation · standardwriting · heavycoding · lightanalysis · standardextraction · standard500K$2 / $6
- DeepSeek V4.1 FlashRecommendeddeepseek/deepseek-v4.1-flashAutoconversation · standardwriting · standardcoding · standardanalysis · standardextraction · standard1.0M$0.30 / $1.20
- DeepSeek V4 Prodeepseek/deepseek-v4-proAutoconversation · lightcoding · lightanalysis · lightextraction · light1.0M$1.32 / $3.96
- GLM 5.3 Flashzai/glm-5.3-flashAutoconversation · lightwriting · lightcoding · standardanalysis · lightextraction · light1M$0.15 / $0.50
- GLM 5.3zai/glm-5.3Autoconversation · standardwriting · standardcoding · standardanalysis · standardextraction · standard1M$1.40 / $4.40
- Sonnet 5.5anthropic/claude-sonnet-5.5Autoconversation · heavywriting · heavycoding · heavyanalysis · heavyextraction · heavy1M$2 / $10
- Haiku 5.5DefaultUtilityRecommendedanthropic/claude-haiku-5.5Autoconversation · standardwriting · standardcoding · standardanalysis · standardextraction · standard1M$0.10 / $0.50
- Kimi K3.1moonshotai/kimi-k3.1-proAutoconversation · lightwriting · heavycoding · heavyanalysis · standardextraction · standard1M$2 / $10
- Mistral Large 4mistral/mistral-large-4Autoconversation · lightwriting · lightcoding · lightanalysis · lightextraction · light1.0M$0.70 / $2.10
- Muse Spark 1.3meta/muse-spark-1.3Automanual only1.0M$1.25 / $4.25
- Qwen 4 Maxalibaba/qwen4-maxAutoconversation · standardwriting · heavycoding · standardanalysis · standardextraction · standard1M$1.50 / $4.50
- Muse Embermeta/muse-emberAutoconversation · standardwriting · standardcoding · standardanalysis · standardextraction · standard1.0M$0.10 / $0.50
- Terra 6.1openai/gpt-6.1-terraAutoconversation · heavywriting · lightcoding · heavyanalysis · heavyextraction · heavy1.1M$1 / $5
- Gemini 4 Hydrogengoogle/gemini-4-hydrogenAutoconversation · heavywriting · standardcoding · standardanalysis · heavyextraction · heavy1M$1.50 / $7.50
- Sol 6.2openai/gpt-6.2-solAutoconversation · standardwriting · heavycoding · heavyanalysis · heavyextraction · heavy1.1M$2 / $10
Image models
- GPT Image 2Defaultopenai/gpt-image-2square · landscape · portrait
- GPT Image 1.5openai/gpt-image-1.5square · landscape · portrait
- GPT Image 1 Miniopenai/gpt-image-1-minisquare · landscape · portrait
- Grok Imagine Image 2.0spacexai/grok-imagine-image-2.0square · landscape · portrait
Embedding
voyage/voyage-41024 dimensions