API Documentation

Quick Start

Get started in 3 steps: connect a provider key, generate a GMT key, and start making API calls.

1. 1.Sign up at givemesometokens.dev/login and connect your AI provider key under Dashboard → API Keys.
2. 2.Generate a GMT key under Dashboard → Integrations. It starts with gmt_.
3. 3.Make API calls using your GMT key:

curl https://givemesometokens.dev/api/v1/chat/completions \
  -H "Authorization: Bearer gmt_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Or use the OpenAI Python SDK:

from openai import OpenAI

client = OpenAI(
    api_key="gmt_your_key_here",
    base_url="https://givemesometokens.dev/api/v1"
)

response = client.chat.completions.create(
    model="claude-sonnet-4-6",   # or gpt-4o, gemini-2.5-pro, etc.
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Authentication

All API requests require a GMT key passed as a Bearer token in the Authorization header.

Authorization: Bearer gmt_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Chat Completions

Full OpenAI-compatible endpoint. Supports streaming.

Request body

{
  "model": "claude-sonnet-4-6",        // Required: model name
  "messages": [                         // Required: conversation history
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ],
  "stream": false,                      // Optional: enable SSE streaming
  "max_tokens": 1024,                   // Optional
  "temperature": 0.7,                   // Optional (0-2)
  "top_p": 1.0                          // Optional
}

Response

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "created": 1718000000,
  "model": "claude-sonnet-4-6",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help you today?"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 12,
    "total_tokens": 27
  }
}

Streaming example

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Write a poem"}],
    stream=True
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

Models

curl https://givemesometokens.dev/api/v1/models \
  -H "Authorization: Bearer gmt_your_key_here"

Models are routed by prefix:

Providers

14 providers supported. Connect your keys at Dashboard → API Keys.

See all providers for supported models and API details.

Wallet API

curl https://givemesometokens.dev/api/wallet \
  -H "Authorization: Bearer gmt_your_key_here"

{
  "claudeBalance": 50.0,
  "openaiBalance": 100.0,
  "geminiBalance": 25.0,
  "groqBalance": 75.0
  // ... all 14 providers
}

Support API

Send token support to a creator programmatically.

{
  "creatorId": "clxxxxxxxxxxxx",
  "provider": "claude",
  "amount": 10.0,
  "message": "Keep up the great work!",
  "isAnonymous": false,
  "isPublic": true
}

curl https://givemesometokens.dev/api/users/alice

{
  "id": "clxxxxxxxxxxxx",
  "username": "alice",
  "name": "Alice",
  "bio": "AI developer",
  "isCreator": true,
  "creatorTier": "Gold"
}

GMT Connect OAuth

Allow your app to authenticate users via GiveMeSomeTokens and access their token balances. Requires a Pro plan. Register an OAuth app →

OAuth flow

1. 1. Redirect user to the authorization endpoint
2. 2. User approves access on GMT
3. 3. GMT redirects back with ?code=...
4. 4. Exchange code for access token
5. 5. Use token to call GMT APIs on behalf of the user

https://givemesometokens.dev/api/oauth/authorize
  ?client_id=your_client_id
  &redirect_uri=https://yourapp.com/callback
  &response_type=code
  &scope=read_balance use_provider
  &state=random_state_string
  &code_challenge=sha256_of_verifier   // PKCE required
  &code_challenge_method=S256

{
  "grant_type": "authorization_code",
  "code": "auth_code_from_redirect",
  "redirect_uri": "https://yourapp.com/callback",
  "client_id": "your_client_id",
  "client_secret": "your_client_secret",
  "code_verifier": "your_pkce_verifier"
}

Available scopes

Error Codes

All errors return JSON: { "error": "message" }

SDKs & Tools

Since GMT is OpenAI-compatible, any existing OpenAI SDK works out of the box.

from openai import OpenAI
client = OpenAI(
  api_key="gmt_...",
  base_url="https://givemesometokens.dev/api/v1"
)

import OpenAI from "openai";
const client = new OpenAI({
  apiKey: "gmt_...",
  baseURL: "https://givemesometokens.dev/api/v1"
});

# Set in tool settings:
API Base URL: https://givemesometokens.dev/api/v1
API Key: gmt_your_key_here

curl https://givemesometokens.dev/api/v1/chat/completions \
  -H "Authorization: Bearer gmt_..." \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o","messages":[...]}'