Models

The models Standards offers, published from a Standards workspace.

Published 2026-11-12 23:50 UTC

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 · standardwriting · standardcoding · standardanalysis · standardextraction · standard1.1M$0.10 / $0.50
  • Opus 5.5anthropic/claude-opus-5.5Autoconversation · heavywriting · heavycoding · heavyanalysis · heavyextraction · standard1M$4 / $20
  • Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-liteAutoconversation · lightwriting · lightcoding · lightanalysis · lightextraction · light1M$0.30 / $2.50
  • Gemini 3.8 FlashRecommendedgoogle/gemini-3.8-flashAutoconversation · standardwriting · standardcoding · heavyanalysis · standardextraction · standard1M$0.75 / $3.75
  • Grok 4.7spacexai/grok-4.7Autoconversation · standardwriting · heavycoding · heavyanalysis · heavyextraction · standard500K$2 / $6
  • DeepSeek V4.1 FlashRecommendeddeepseek/deepseek-v4.1-flashAutoconversation · standardwriting · standardcoding · heavyanalysis · standardextraction · standard1.0M$0.30 / $1.20
  • DeepSeek V4 Prodeepseek/deepseek-v4-proAutoconversation · standardwriting · standardcoding · standardanalysis · standardextraction · standard1M$0.66 / $1.98
  • Qwen 3.8 Flashalibaba/qwen3.8-flashAutomanual only991K$0.15 / $0.47
  • Qwen 3.8 Maxalibaba/qwen3.8-max-0902Autoconversation · lightwriting · heavycoding · heavyanalysis · heavyextraction · standard991K$2 / $6
  • Ministral 14Bmistral/ministral-14bAutoconversation · lightwriting · lightcoding · lightanalysis · lightextraction · light262.1K$0.20 / $0.20
  • Medium 3.5mistral/mistral-medium-3.5Autoconversation · lightwriting · lightcoding · lightanalysis · lightextraction · light262.1K$1.50 / $7.50
  • Large 3mistral/mistral-large-3Autowriting · lightcoding · lightanalysis · lightextraction · light262.1K$0.50 / $1.50
  • MiniMax M3minimax/minimax-m3Autoconversation · standardwriting · lightcoding · standardanalysis · lightextraction · standard512K$0.30 / $1.20
  • Scoutmeta/llama-4-scoutAutoconversation · lightwriting · lightcoding · lightanalysis · lightextraction · light128K$0.17 / $0.66
  • Maverickmeta/llama-4-maverickAutoconversation · lightwriting · lightcoding · lightanalysis · lightextraction · light128K$0.24 / $0.97
  • GLM 5.3 Flashzai/glm-5.3-flashAutoconversation · standardwriting · standardcoding · heavyanalysis · standardextraction · standard1M$0.15 / $0.50
  • GLM 5.3zai/glm-5.3Autoconversation · standardwriting · heavycoding · heavyanalysis · heavyextraction · standard1M$1.40 / $4.40
  • Sol 6.1openai/gpt-6.1-solAutoconversation · standardwriting · heavycoding · heavyanalysis · heavyextraction · standard1.1M$2 / $10
  • Sonnet 5.5anthropic/claude-sonnet-5.5Autoconversation · heavywriting · heavycoding · standardanalysis · heavyextraction · standard1M$2 / $10
  • Muse Spark 1.3meta/muse-spark-1.3Autoconversation · standardwriting · heavycoding · heavyanalysis · heavyextraction · standard1.0M$1.25 / $4.25
  • Muse Glimmermeta/muse-glimmer-30bAutoconversation · lightwriting · lightcoding · lightanalysis · lightextraction · light131.1K$0.35 / $1.50
  • Haiku 5.5DefaultUtilityRecommendedanthropic/claude-haiku-5.5Autoconversation · standardwriting · heavycoding · standardanalysis · heavyextraction · standard1M$0.10 / $0.50
  • Kimi K3.1moonshotai/kimi-k3.1-proAutoconversation · standardwriting · standardcoding · standardanalysis · standardextraction · standard1.0M$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