prices.yaml

# Prices in USD per 1M tokens.
# Last verified: May 2026

providers:
  openai:
    name: OpenAI
    url: https://openai.com/api/pricing
    models:
      gpt-5-4-nano:
        name: GPT-5.4 Nano
        input: 0.20
        output: 1.25
        context: 200000
        efficiency_tier: budget
      gpt-5-4-mini:
        name: GPT-5.4 Mini
        input: 0.75
        output: 4.50
        context: 400000
        efficiency_tier: standard
      gpt-5:
        name: GPT-5
        input: 1.25
        output: 10.00
        context: 400000
        efficiency_tier: standard
      o4-mini:
        name: o4 Mini
        input: 1.10
        output: 4.40
        context: 200000
        efficiency_tier: advanced
      gpt-5-4:
        name: GPT-5.4
        input: 2.50
        output: 15.00
        context: 1050000
        efficiency_tier: advanced
      gpt-5-5:
        name: GPT-5.5
        input: 5.00
        output: 30.00
        context: 1000000
        efficiency_tier: flagship
      o3:
        name: o3
        input: 10.00
        output: 40.00
        context: 200000
        efficiency_tier: flagship
      gpt-5-4-pro:
        name: GPT-5.4 Pro
        input: 30.00
        output: 180.00
        context: 400000
        efficiency_tier: flagship
      gpt-5-5-pro:
        name: GPT-5.5 Pro
        input: 30.00
        output: 180.00
        context: 1000000
        efficiency_tier: flagship

  anthropic:
    name: Anthropic
    url: https://www.anthropic.com/pricing
    models:
      claude-haiku-4-5:
        name: Claude Haiku 4.5
        input: 1.00
        output: 5.00
        context: 200000
        efficiency_tier: standard
      claude-sonnet-4-6:
        name: Claude Sonnet 4.6
        input: 3.00
        output: 15.00
        context: 1000000
        efficiency_tier: advanced
      claude-opus-4-6:
        name: Claude Opus 4.6
        input: 5.00
        output: 25.00
        context: 1000000
        efficiency_tier: flagship
      claude-opus-4-7:
        name: Claude Opus 4.7
        input: 5.00
        output: 25.00
        context: 1000000
        efficiency_tier: flagship

  google:
    name: Google
    url: https://ai.google.dev/gemini-api/docs/pricing
    models:
      gemini-2-5-flash-lite:
        name: Gemini 2.5 Flash-Lite
        input: 0.10
        output: 0.40
        context: 1000000
        efficiency_tier: budget
      gemini-3-flash:
        name: Gemini 3 Flash
        input: 0.50
        output: 3.00
        context: 1000000
        efficiency_tier: standard
      gemini-2-5-flash:
        name: Gemini 2.5 Flash
        input: 0.30
        output: 2.50
        context: 1000000
        efficiency_tier: standard
      gemini-2-5-pro:
        name: Gemini 2.5 Pro
        input: 1.25
        output: 10.00
        context: 1000000
        efficiency_tier: advanced
      gemini-3-1-pro:
        name: Gemini 3.1 Pro
        input: 2.00
        output: 12.00
        context: 1000000
        efficiency_tier: advanced

  mistral:
    name: Mistral AI
    url: https://mistral.ai/technology
    models:
      mistral-small-3-2:
        name: Mistral Small 3.2
        input: 0.06
        output: 0.18
        context: 131072
        efficiency_tier: budget
      mistral-large-3:
        name: Mistral Large 3
        input: 0.50
        output: 1.50
        context: 256000
        efficiency_tier: standard
      mistral-medium-3-5:
        name: Mistral Medium 3.5
        input: 1.00
        output: 3.00
        context: 256000
        efficiency_tier: standard

  deepseek:
    name: DeepSeek
    url: https://api-docs.deepseek.com/quick_start/pricing
    models:
      deepseek-v4-flash:
        name: DeepSeek V4 Flash
        input: 0.14
        output: 0.28
        context: 1000000
        efficiency_tier: budget
      deepseek-v4-pro:
        name: DeepSeek V4 Pro
        input: 1.74
        output: 3.48
        context: 1000000
        efficiency_tier: standard
      deepseek-r1:
        name: DeepSeek R1
        input: 0.55
        output: 2.19
        context: 1000000
        efficiency_tier: advanced

  xai:
    name: xAI
    url: https://x.ai/api
    models:
      grok-4-1-fast:
        name: Grok 4.1 Fast
        input: 0.20
        output: 0.50
        context: 2000000
        efficiency_tier: budget
      grok-4:
        name: Grok 4
        input: 3.00
        output: 15.00
        context: 2000000
        efficiency_tier: advanced

  meta:
    name: Meta (via Groq)
    url: https://groq.com/pricing
    models:
      llama-4-maverick:
        name: Llama 4 Maverick
        input: 0.27
        output: 0.85
        context: 1000000
        efficiency_tier: budget
      llama-3-3-70b:
        name: Llama 3.3 70B
        input: 0.59
        output: 0.79
        context: 128000
        efficiency_tier: budget

  cohere:
    name: Cohere
    url: https://cohere.com/pricing
    models:
      command-r7b:
        name: Command R7B
        input: 0.04
        output: 0.15
        context: 128000
        efficiency_tier: budget
      command-r-plus:
        name: Command R+
        input: 3.00
        output: 15.00
        context: 128000
        efficiency_tier: standard

  zai:
    name: Z.AI
    url: https://docs.z.ai/guides/overview/pricing
    models:
      glm-5-1:
        name: GLM-5.1
        input: 1.40
        output: 4.40
        context: 200000
        efficiency_tier: standard

  kimi:
    name: Kimi
    url: https://platform.kimi.ai/docs/pricing/chat-k26
    models:
      kimi-k2-6:
        name: Kimi K2.6
        input: 0.95
        output: 4.00
        context: 262144
        efficiency_tier: standard

  minimax:
    name: MiniMax
    url: https://platform.minimax.io/docs/guides/pricing-paygo
    models:
      minimax-m2-7:
        name: MiniMax M2.7
        input: 0.30
        output: 1.20
        context: 196608
        efficiency_tier: budget