kdeps-models-cloud

# Cloud model catalog: model IDs kdeps knows per provider, with their
# context window and output limits. Hand-maintained; bump version on change.
version: 1.0.0
models:
  # anthropic
  - id: "claude-opus-4-8"
    backend: anthropic
    desc: "most capable"
    envVar: ANTHROPIC_API_KEY
    thinking: true
    images: true
    contextWindow: 1000000
    maxOutputTokens: 128000
  - id: "claude-sonnet-4-6"
    backend: anthropic
    desc: "balanced speed/intelligence"
    envVar: ANTHROPIC_API_KEY
    thinking: true
    images: true
    contextWindow: 1000000
    maxOutputTokens: 64000
  - id: "claude-haiku-4-5-20251001"
    backend: anthropic
    desc: "fast and lightweight"
    envVar: ANTHROPIC_API_KEY
    thinking: true
    images: true
    contextWindow: 200000
    maxOutputTokens: 64000
  # google
  - id: "gemini-2.5-pro"
    backend: google
    desc: "most capable, best reasoning"
    envVar: GOOGLE_API_KEY
    thinking: true
    images: true
    contextWindow: 1048576
    maxOutputTokens: 8192
  - id: "gemini-2.5-flash"
    backend: google
    desc: "fast multimodal"
    envVar: GOOGLE_API_KEY
    thinking: true
    images: true
    contextWindow: 1048576
    maxOutputTokens: 8192
  - id: "gemini-2.0-flash"
    backend: google
    desc: "balanced"
    envVar: GOOGLE_API_KEY
    images: true
    contextWindow: 1048576
    maxOutputTokens: 8192
  - id: "gemini-1.5-pro"
    backend: google
    desc: "long context"
    envVar: GOOGLE_API_KEY
    images: true
    contextWindow: 2097152
    maxOutputTokens: 8192
  # openai
  - id: "gpt-4o"
    backend: openai
    desc: "flagship multimodal"
    envVar: OPENAI_API_KEY
    images: true
    contextWindow: 128000
    maxOutputTokens: 16384
  - id: "gpt-4o-mini"
    backend: openai
    desc: "fast and cheap"
    envVar: OPENAI_API_KEY
    images: true
    contextWindow: 128000
    maxOutputTokens: 16384
  - id: "o4-mini"
    backend: openai
    desc: "fast reasoning"
    envVar: OPENAI_API_KEY
    thinking: true
    images: true
    contextWindow: 200000
    maxOutputTokens: 16384
  - id: "o3"
    backend: openai
    desc: "advanced reasoning"
    envVar: OPENAI_API_KEY
    thinking: true
    images: true
    contextWindow: 200000
    maxOutputTokens: 16384
  - id: "o1"
    backend: openai
    desc: "reasoning"
    envVar: OPENAI_API_KEY
    thinking: true
    contextWindow: 200000
    maxOutputTokens: 16384
  # xai
  - id: "grok-3"
    backend: xai
    desc: "most capable"
    envVar: XAI_API_KEY
    contextWindow: 131072
    maxOutputTokens: 4096
  - id: "grok-3-fast"
    backend: xai
    desc: "fast"
    envVar: XAI_API_KEY
    contextWindow: 131072
    maxOutputTokens: 4096
  - id: "grok-3-mini"
    backend: xai
    desc: "small and cheap"
    envVar: XAI_API_KEY
    thinking: true
    contextWindow: 131072
    maxOutputTokens: 4096
  - id: "grok-2"
    backend: xai
    desc: "previous generation"
    envVar: XAI_API_KEY
    contextWindow: 131072
    maxOutputTokens: 4096
  # deepseek
  - id: "deepseek-v4-pro"
    backend: deepseek
    desc: "flagship"
    envVar: DEEPSEEK_API_KEY
    contextWindow: 64000
    maxOutputTokens: 8192
  - id: "deepseek-v4-flash"
    backend: deepseek
    desc: "fast"
    envVar: DEEPSEEK_API_KEY
    contextWindow: 64000
    maxOutputTokens: 8192
  # groq
  - id: "llama-3.3-70b-versatile"
    backend: groq
    desc: "fast Llama 3.3 70B"
    envVar: GROQ_API_KEY
    contextWindow: 128000
    maxOutputTokens: 8192
  - id: "llama-3.1-8b-instant"
    backend: groq
    desc: "fastest, smallest"
    envVar: GROQ_API_KEY
    contextWindow: 128000
    maxOutputTokens: 8192
  - id: "gemma2-9b-it"
    backend: groq
    desc: "Google Gemma 2"
    envVar: GROQ_API_KEY
    contextWindow: 8192
    maxOutputTokens: 4096
  # mistral
  - id: "mistral-large-latest"
    backend: mistral
    desc: "most capable"
    envVar: MISTRAL_API_KEY
    contextWindow: 131072
    maxOutputTokens: 8192
  - id: "mistral-small-latest"
    backend: mistral
    desc: "fast and cheap"
    envVar: MISTRAL_API_KEY
    contextWindow: 32768
    maxOutputTokens: 8192
  - id: "codestral-latest"
    backend: mistral
    desc: "code specialist"
    envVar: MISTRAL_API_KEY
    contextWindow: 256000
    maxOutputTokens: 8192
  # cohere
  - id: "command-r-plus"
    backend: cohere
    desc: "most capable"
    envVar: COHERE_API_KEY
    contextWindow: 128000
    maxOutputTokens: 4096
  - id: "command-r"
    backend: cohere
    desc: "balanced"
    envVar: COHERE_API_KEY
    contextWindow: 128000
    maxOutputTokens: 4096
  # together
  - id: "meta-llama/Llama-3-70b-chat-hf"
    backend: together
    desc: "Llama 3 70B"
    envVar: TOGETHER_API_KEY
    contextWindow: 8192
    maxOutputTokens: 4096
  - id: "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo"
    backend: together
    desc: "Llama 3.1 8B fast"
    envVar: TOGETHER_API_KEY
    contextWindow: 128000
    maxOutputTokens: 4096
  # perplexity
  - id: "llama-3.1-sonar-large-128k-online"
    backend: perplexity
    desc: "with web search"
    envVar: PERPLEXITY_API_KEY
    contextWindow: 128000
    maxOutputTokens: 4096
  - id: "llama-3.1-sonar-small-128k-online"
    backend: perplexity
    desc: "fast with web search"
    envVar: PERPLEXITY_API_KEY
    contextWindow: 128000
    maxOutputTokens: 4096
  # m365
  - id: "m365-copilot"
    backend: m365
    desc: "default - service picks the model"
    contextWindow: 128000
    maxOutputTokens: 16384
  - id: "quick"
    backend: m365
    desc: "fast, lower-latency responses"
    contextWindow: 128000
    maxOutputTokens: 16384
  - id: "think-deeper"
    backend: m365
    desc: "extended reasoning"
    thinking: true
    contextWindow: 128000
    maxOutputTokens: 16384
  - id: "claude-sonnet"
    backend: m365
    desc: "Claude Sonnet via M365"
    contextWindow: 200000
    maxOutputTokens: 64000
  - id: "claude-sonnet-think-deeper"
    backend: m365
    desc: "Claude Sonnet, extended reasoning"
    thinking: true
    contextWindow: 200000
    maxOutputTokens: 64000
  - id: "claude-opus"
    backend: m365
    desc: "Claude Opus via M365"
    contextWindow: 200000
    maxOutputTokens: 128000
  - id: "gpt-5.6-think-deeper"
    backend: m365
    desc: "GPT-5.6, extended reasoning (reasoning only for now)"
    thinking: true
    contextWindow: 200000
    maxOutputTokens: 16384
  - id: "gpt-5.5"
    backend: m365
    desc: "GPT-5.5"
    contextWindow: 200000
    maxOutputTokens: 16384
  - id: "gpt-5.5-quick"
    backend: m365
    desc: "GPT-5.5, fast"
    contextWindow: 200000
    maxOutputTokens: 16384
  - id: "gpt-5.5-think-deeper"
    backend: m365
    desc: "GPT-5.5, extended reasoning"
    thinking: true
    contextWindow: 200000
    maxOutputTokens: 16384
  - id: "gpt-5.4"
    backend: m365
    desc: "GPT-5.4"
    thinking: true
    contextWindow: 200000
    maxOutputTokens: 16384
  - id: "gpt-5.4-quick"
    backend: m365
    desc: "GPT-5.4, fast"
    contextWindow: 200000
    maxOutputTokens: 16384
  - id: "gpt-5.4-think-deeper"
    backend: m365
    desc: "GPT-5.4, extended reasoning"
    thinking: true
    contextWindow: 200000
    maxOutputTokens: 16384
  - id: "gpt-5.3"
    backend: m365
    desc: "GPT-5.3"
    contextWindow: 128000
    maxOutputTokens: 16384
  - id: "gpt-5.3-quick"
    backend: m365
    desc: "GPT-5.3, fast"
    contextWindow: 128000
    maxOutputTokens: 16384
  - id: "gpt-5.3-think-deeper"
    backend: m365
    desc: "GPT-5.3, extended reasoning"
    thinking: true
    contextWindow: 128000
    maxOutputTokens: 16384
  - id: "gpt-5.2"
    backend: m365
    desc: "GPT-5.2"
    contextWindow: 128000
    maxOutputTokens: 16384
  - id: "gpt-5.2-quick"
    backend: m365
    desc: "GPT-5.2, fast"
    contextWindow: 128000
    maxOutputTokens: 16384
  - id: "gpt-5.2-think-deeper"
    backend: m365
    desc: "GPT-5.2, extended reasoning"
    thinking: true
    contextWindow: 128000
    maxOutputTokens: 16384