Guide · OpenAI SDK

Connect OpenAI SDK to Synap

2 steps · about a minute

  1. Get a free key

    Sign in with Google at synap.linkrra.com — no card. Your key starts with sk-pool-.

  2. Point the SDK at Synap

    The official SDKs work unchanged — the base URL and the key are the only arguments that differ. Pass stream=True for server-sent events; tool calling uses the standard fields.

    from openai import OpenAI
    
    client = OpenAI(base_url="https://synap.linkrra.com/v1", api_key="sk-pool-...")
    r = client.chat.completions.create(
        model="qwen3-coder-30b",
        messages=[{"role": "user", "content": "Write a haiku about diffs"}],
    )
    print(r.choices[0].message.content)
    import OpenAI from "openai";
    
    const client = new OpenAI({ baseURL: "https://synap.linkrra.com/v1", apiKey: process.env.SYNAP_API_KEY });
    const r = await client.chat.completions.create({
      model: "qwen3-coder-30b",
      messages: [{ role: "user", content: "Write a haiku about diffs" }],
    });
    console.log(r.choices[0].message.content);
Notes, prices and limits

The official SDKs work unchanged. Recommended model: qwen3-coder-30b — $0.0675 in and $0.27 out per 1M tokens, 98,304-token context.

Pass stream=True for server-sent events. Tool calling uses the standard tools and tool_choice fields.

On the free tier: every request counts input and output against 100,000 free tokens a day, and answers stop at 4,096 output tokens. Coding agents send long prompts, so the free tier covers a short session; credits cover the rest.

Field names from OpenAI Python and Node SDKs, run against this API, checked 2026-10-31 22:40 UTC. Prices refresh from /v1/models when this page loads.