Get started

Models

19 models from 8 providers. One API.

Compare context windows, capabilities and per-token rates. To use a model, pass its ID as the model parameter.

Showing all 19 models

Prices in USD per 1 million tokens

  1. OpenAI

    GPT-6 Astra

    gpt-6-astra

    OpenAI's largest model, for complex reasoning and long multi-step work.

    Class
    Most capable
    Context
    1M tokens
    Max output
    128K tokens
    Input
    Text, Image
    Input
    $10.00
    Cached input
    $1.00
    Output
    $50.00
    • Tool calling
    • Reasoning
    • Image input
    • Prompt caching
    • Structured output

  2. OpenAI

    GPT-6.1 Sol

    gpt-6.1-sol

    General-purpose model balancing capability, speed and cost.

    Class
    Balanced
    Context
    1M tokens
    Max output
    128K tokens
    Input
    Text, Image
    Input
    $2.00
    Cached input
    $0.20
    Output
    $10.00
    • Tool calling
    • Reasoning
    • Image input
    • Prompt caching
    • Structured output

  3. OpenAI

    GPT-6 Luna

    gpt-6-luna

    Small, fast model for classification, extraction and high-volume tasks.

    Class
    Fast, low cost
    Context
    400K tokens
    Max output
    64K tokens
    Input
    Text, Image
    Input
    $0.10
    Cached input
    $0.01
    Output
    $0.50
    • Tool calling
    • Image input
    • Prompt caching
    • Structured output

  4. Anthropic

    Claude Fable 5.1

    claude-fable-5-1

    Anthropic's most capable model, for demanding reasoning and long-horizon agents.

    Class
    Most capable
    Context
    1M tokens
    Max output
    128K tokens
    Input
    Text, Image
    Input
    $10.00
    Cached input
    $0.25
    Output
    $50.00
    • Tool calling
    • Reasoning
    • Image input
    • Prompt caching
    • Structured output

  5. Anthropic

    Claude Opus 5.5

    claude-opus-5-5

    High-capability model for coding, agents and complex analysis.

    Class
    Most capable
    Context
    1M tokens
    Max output
    128K tokens
    Input
    Text, Image
    Input
    $4.00
    Cached input
    $0.20
    Output
    $20.00
    • Tool calling
    • Reasoning
    • Image input
    • Prompt caching
    • Structured output

  6. Anthropic

    Claude Sonnet 5.5

    claude-sonnet-5-5

    Fast, capable model for everyday coding, agent and production workloads.

    Class
    Balanced
    Context
    1M tokens
    Max output
    128K tokens
    Input
    Text, Image
    Input
    $2.00
    Cached input
    $0.20
    Output
    $10.00
    • Tool calling
    • Reasoning
    • Image input
    • Prompt caching
    • Structured output

  7. Anthropic

    Claude Haiku 5.5

    claude-haiku-5-5

    Anthropic's fastest model, for latency-sensitive and high-volume work.

    Class
    Fast, low cost
    Context
    1M tokens
    Max output
    128K tokens
    Input
    Text, Image
    Input
    $0.10
    Cached input
    $0.01
    Output
    $0.50
    • Tool calling
    • Reasoning
    • Image input
    • Prompt caching
    • Structured output

  8. Google

    Gemini 3.1 Pro

    gemini-3.1-pro

    Google's most capable model, with long context and multimodal input.

    Class
    Most capable
    Context
    1M tokens
    Max output
    66K tokens
    Input
    Text, Image, Audio, Video
    Input
    $2.00
    Cached input
    $0.20
    Output
    $12.00
    • Tool calling
    • Reasoning
    • Image input
    • Prompt caching
    • Structured output

  9. Google

    Gemini 3.8 Flash

    gemini-3.8-flash

    Fast multimodal model for production workloads at moderate cost.

    Class
    Balanced
    Context
    1M tokens
    Max output
    66K tokens
    Input
    Text, Image, Audio, Video
    Input
    $0.75
    Cached input
    $0.075
    Output
    $3.75
    • Tool calling
    • Reasoning
    • Image input
    • Prompt caching
    • Structured output

  10. Google

    Gemini 3.5 Flash-Lite

    gemini-3.5-flash-lite

    Lowest-cost Gemini model, for simple tasks at very high volume.

    Class
    Fast, low cost
    Context
    1M tokens
    Max output
    66K tokens
    Input
    Text, Image
    Input
    $0.30
    Cached input
    $0.03
    Output
    $2.50
    • Tool calling
    • Image input
    • Prompt caching
    • Structured output

  11. DeepSeek

    DeepSeek V4 Pro

    deepseek-v4-pro

    Open-weight reasoning model, strong on code and mathematics.

    Class
    Most capable
    Context
    256K tokens
    Max output
    64K tokens
    Input
    Text
    Input
    $1.74
    Cached input
    $0.145
    Output
    $3.48
    • Tool calling
    • Reasoning
    • Prompt caching
    • Structured output

  12. DeepSeek

    DeepSeek V4.1 Flash

    deepseek-v4.1-flash

    Fast, low-cost open-weight model for general text tasks.

    Class
    Fast, low cost
    Context
    256K tokens
    Max output
    64K tokens
    Input
    Text
    Input
    $0.30
    Cached input
    $0.03
    Output
    $1.20
    • Tool calling
    • Prompt caching
    • Structured output

  13. Z.ai

    GLM-5.2

    glm-5.2

    Z.ai's flagship model, tuned for coding and agentic tool use.

    Class
    Most capable
    Context
    200K tokens
    Max output
    128K tokens
    Input
    Text
    Input
    $1.40
    Cached input
    $0.26
    Output
    $4.40
    • Tool calling
    • Reasoning
    • Prompt caching
    • Structured output

  14. Z.ai

    GLM-5.3 Flash

    glm-5.3-flash

    Lightweight GLM model for fast, inexpensive text generation.

    Class
    Fast, low cost
    Context
    200K tokens
    Max output
    32K tokens
    Input
    Text
    Input
    $0.15
    Cached input
    —
    Output
    $0.50
    • Tool calling
    • Structured output

  15. Moonshot AI

    Kimi K3

    kimi-k3

    Moonshot AI's largest model, built for long-context agentic work.

    Class
    Most capable
    Context
    256K tokens
    Max output
    64K tokens
    Input
    Text, Image
    Input
    $3.00
    Cached input
    $0.30
    Output
    $15.00
    • Tool calling
    • Reasoning
    • Image input
    • Prompt caching
    • Structured output

  16. Moonshot AI

    Kimi K2.6

    kimi-k2.6

    Open-weight mixture-of-experts model for coding and tool use.

    Class
    Balanced
    Context
    256K tokens
    Max output
    64K tokens
    Input
    Text
    Input
    $0.95
    Cached input
    $0.16
    Output
    $4.00
    • Tool calling
    • Prompt caching
    • Structured output

  17. MiniMax

    MiniMax M3

    minimax-m3

    Long-context open-weight model for agents and document work.

    Class
    Balanced
    Context
    1M tokens
    Max output
    128K tokens
    Input
    Text
    Input
    $0.60
    Cached input
    $0.06
    Output
    $2.40
    • Tool calling
    • Reasoning
    • Prompt caching
    • Structured output

  18. Qwen

    Qwen3.8 Max

    qwen3.8-max

    The largest Qwen model, for complex reasoning and multilingual work.

    Class
    Most capable
    Context
    262K tokens
    Max output
    66K tokens
    Input
    Text, Image
    Input
    $2.00
    Cached input
    $0.40
    Output
    $6.00
    • Tool calling
    • Reasoning
    • Image input
    • Prompt caching
    • Structured output

  19. Qwen

    Qwen3.8 Flash

    qwen3.8-flash

    Fast, inexpensive Qwen model with a long context window.

    Class
    Fast, low cost
    Context
    1M tokens
    Max output
    33K tokens
    Input
    Text
    Input
    $0.15
    Cached input
    $0.03
    Output
    $0.47
    • Tool calling
    • Prompt caching
    • Structured output

Model availability and rates can change. Applications should read the current list fromGET /v1/models. Model names are trademarks of their respective owners.

One account. One balance. One API.

Create an account, add balance and make your first request with the client you already use.

Get startedRead the documentation