GamraDocs
FR
Browse documentation

Getting started

Quickstart

One key, one request, one response — in under five minutes.

Gamra exposes an OpenAI-compatible gateway. If your tool can talk to OpenAI's API, it can already talk to Gamra: change the base URL and the key.

1. Create a key#

Sign in at gamra.dev, open API keys, and create one. It starts with gm_live_ and is shown once — the server keeps only its SHA-256 hash and a display prefix.

2. Send a request#

The base URL is https://api.gamra.dev/v1, and every request carries an Authorization header.

curl https://api.gamra.dev/v1/chat/completions \
  -H "Authorization: Bearer $GAMRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": false
  }'

3. From an OpenAI SDK#

No Gamra-specific client is needed.

import OpenAI from "openai";
 
const client = new OpenAI({
  baseURL: "https://api.gamra.dev/v1",
  apiKey: process.env.GAMRA_API_KEY,
});
 
const completion = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [{ role: "user", content: "Hello!" }],
  stream: false,
});

Next#