QUICK START

Getting Started

Everything you need to start making API requests in minutes.

Base URL

All API requests should be made to the following base URL:

Example
https://llm.market

Available Endpoints

MethodEndpointDescription
POST/v1/chat/completionsOpenAI-compatible chat
POST/v1/responsesOpenAI Responses request
GET/v1/modelsList active models

Rate Limits

Rate limits are applied per plan tier. Limits are measured in requests per minute (RPM) and requests per day (RPD).

The active model catalog, key limits, subscription quota, and PAYG balance determine whether a request can run.

Quick Examples

cURL

Example
curl https://llm.market/v1/chat/completions \
  -H "Authorization: Bearer sk-YOUR_LLM_MARKET_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MODEL_FROM_V1_MODELS",
    "messages": [{"role": "user", "content": "Say hello!"}],
    "max_tokens": 100
  }'

Python

Example
from openai import OpenAI

client = OpenAI(base_url="https://llm.market/v1", api_key="sk-YOUR_LLM_MARKET_KEY")
response = client.chat.completions.create(
    model="MODEL_FROM_V1_MODELS",
    messages=[{"role": "user", "content": "Say hello!"}],
    max_tokens=100,
)
print(response.choices[0].message.content)

Node.js

Example
import OpenAI from 'openai';

const client = new OpenAI({ baseURL: 'https://llm.market/v1', apiKey: 'sk-YOUR_LLM_MARKET_KEY' });
const response = await client.chat.completions.create({
  model: 'MODEL_FROM_V1_MODELS',
  messages: [{ role: 'user', content: 'Say hello!' }],
  max_tokens: 100,
});

Model Discovery

Use the /v1/models endpoint to retrieve the currently active model IDs.

Example
curl https://llm.market/v1/models \
  -H "Authorization: Bearer sk-YOUR_LLM_MARKET_KEY"
Tip

Use the live catalog rather than hard-coding model availability or pricing.

Stuck on setup, or want a free key?

Ask the community on our Discord.