/ Docs
Documentation
The Galoro API is fully compatible with the OpenAI SDK. Integrate in minutes.
Quickstart
The Galoro API is fully compatible with the OpenAI SDK. Just change the Base URL and API key.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.galoro.ai/v1",
apiKey: "glr_your_key",
});
// Switch models by changing the model field
const res = await client.chat.completions.create({
model: "deepseek-flash", // or kimi-k3 / glm-5.3 / qwen3.7-plus / minimax-m3
messages: [{ role: "user", content: "Hello" }],
});
console.log(res.choices[0].message.content);API compatibility
Supported endpoints:
GET /v1/models— list modelsPOST /v1/chat/completions— chat completionsPOST /v1/responses— Responses API
Credits & billing
1,000 Credits = $1 at official API reference prices. Each request is billed at the price version in effect when it starts, using that model's official price. All models share one Credits pool. When Credits run out, the API returns 429.
Streaming
const stream = await client.chat.completions.create({
model: "deepseek-flash",
messages: [{ role: "user", content: "Write a short poem" }],
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}Real SSE streaming. The provider never switches after the first token, and the upstream request is cancelled if the client disconnects.
Rate limits
Burst traffic is controlled with RPM, TPM and concurrency limits. There are no restrictions on when you use your Credits.
Error codes
| HTTP | code | Meaning |
|---|---|---|
| 401 | invalid_api_key | Invalid API key |
| 403 | no_subscription | No active subscription |
| 404 | model_not_found | Model not found or disabled |
| 429 | insufficient_quota | Out of Credits |
| 429 | rate_limit_exceeded | RPM/TPM limit exceeded |
| 502 | upstream_error | All upstream providers failed |