synthetic
    /Dev
    • Back to app
    Usage-based pricing
    • Usage & Billing
    API Documentation
    API
    • Overview
    • Getting Started
    • Models
    Agents
    • Octofriend by Synthetic
    • Claude Code
    • Crush
    • Opencode
    • GitHub Copilot
    • OpenClaw
    • Xcode Intelligence
    OpenAI Reference
    • /models
    • /chat/completions
    • /completions
    • /embeddings
    Anthropic Reference
    • /messages
    • /messages/count_tokens
    Synthetic Reference
    • /quotas
    • /search

    API Overview

    Welcome to the Synthetic API docs!

    Synthetic provides an OpenAI-compatible API and Anthropic-compatible API for all models we support.

    Contributing

    This is a living document, and we're working on making it easy for users like you to contribute.

    Until then, if you have any feedback or suggestions, let us know via Discord or email.

    API Key

    Your API Key:
    Log in to see your API key.

    Supported Models

    For a list of supported models, see the Models page.

    Supported Endpoints

    OpenAI-compatible endpoints:

    Base Url:
    https://api.synthetic.new/openai/v1
    • /models - List all always-on models
    • /chat/completions - Chat-based completions with conversation history
    • /completions - Traditional text completions
    • /embeddings - Transform text into vector embeddings.

    Anthropic-compatible endpoints:

    Base Url:
    https://api.synthetic.new/anthropic/v1
    • /messages - Send and receive messages.
    • /messages/count_tokens - Count tokens in messages.

    Synthetic endpoints:

    • /quotas - Check your current Subscription usage.
    • /search - Search the web.

    Rate Limits

    Rate limits vary by subscription tier:

    • Standard: 135 messages every 5 hours
    • Pro: 1350 messages every 5 hours
    • Usage Based: No rate limits
    Subscriptions last longer!

    Small requests with less than 2048 input tokens and less than 2048 output tokens only count as 0.2 requests. And tool call messages count for even less: only 0.1 requests (up to 12x your five hour limit)

    For more details, see our Pricing page.

    Getting Help

    • Check out our Getting Started Guide
    • Browse the API Reference
    • Join our Discord Server!