Quickstart Guide

Get started with Martian in less than three minutes and with minimal code changes.

Authentication and Setup

Step 1: Obtain Your API Key

Get your API key from the Martian Dashboard.

Step 2: Choose Your API Format

Choose from the following API formats supported by Martian:

• OpenAI Chat Completions API: Compatible with OpenAI SDKs and frameworks
• Anthropic Messages API: Native Anthropic format with advanced features

Choose a Model

Select a model from our 200+ AI model catalog and copy its Model Name. You will populate the model field in the API with that name. For example:

• openai/gpt-4.1-nano: OpenAI's lightweight model
• anthropic/claude-sonnet-4-20250514: Anthropic's lightweight model
• google/gemini-2.5-flash: Google's lightweight model

Invoke API Endpoints

OpenAI Chat Completions API

Endpoint: POST /v1/chat/completions

The Martian API is OpenAI-compatible. This means you can use any OpenAI SDK to make requests via Martian.

cURL Example

# Note: Replace $MARTIAN_API_KEY with your assigned API key
curl https://api.withmartian.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MARTIAN_API_KEY" \
  -d '{
    "model": "openai/gpt-4.1-nano",
    "messages": [
      {
        "role": "user",
        "content": "What is Olympus Mons?"
      }
    ]
  }'

Python Example:

import openai

# Note: Define MARTIAN_API_KEY as your assigned API key
oai_client = openai.OpenAI(
    base_url="https://api.withmartian.com/v1",
    api_key=MARTIAN_API_KEY
)

response = oai_client.chat.completions.create(
    model="openai/gpt-4.1-nano",
    messages=[
        {
            "role": "user",
            "content": "Write a Python function that calculates Mars orbital period."
        }
    ]
)

print(response.choices[0].message.content)

Anthropic Messages API

Endpoint: POST /v1/messages

Martian's /messages endpoint enables you to make Anthropic-compatible requests with native support for advanced features like thinking, tool use, and structured outputs.

Use this endpoint to access multiple LLMs from different providers via Anthropic through a unified interface.

cURL Example:

# Note: Replace $MARTIAN_API_KEY with your assigned API key
curl https://api.withmartian.com/v1/messages \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MARTIAN_API_KEY" \
  -d '{
    "model": "anthropic/claude-sonnet-4-20250514",
    "max_tokens": 1024,
    "messages": [
      {
        "role": "user",
        "content": "What is Olympus Mons?"
      }
    ]
  }'

Python Example:

import anthropic

# Note: Define MARTIAN_API_KEY as your assigned API key
anth_client = anthropic.Anthropic(
    base_url="https://api.withmartian.com/v1",
    api_key=MARTIAN_API_KEY
)

response = anth_client.messages.create(
    model="anthropic/claude-3-haiku-20240307",
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": "Write a haiku about Mars (the planet, not the god)."
        }
    ]
)

print(response.content[0].text)

Now that you've made your first API call, explore these resources:

Monitoring & Analytics

Track your usage and optimize costs through the Martian Dashboard:

• Real-time Usage: Monitor API calls, tokens, and costs
• Model Performance: Compare accuracy and latency across models
• Cost Analysis: Identify savings opportunities with smart routing
• Request History: Debug and analyze API interactions

Getting Help

• Documentation: Comprehensive guides at docs.withmartian.com
• Support: Contact our team through the dashboard
• Community: Join our Discord for discussions and updates

Ready to build something amazing? Explore our Advanced Features or browse the Available Models to find the perfect model for your use case.