Available Models
Martian supports 200+ models across major providers. All models are accessible through both our OpenAI-compatible and Anthropic-compatible endpoints.
Pricing
Prices are shown per 1 million tokens for input and output, plus any per-request charges.
Models with the :cheap
suffix offer intelligent cost optimization while maintaining quality comparable to the base model.
Supported Models
Browse the complete list of 200+ supported models with real-time pricing information:
Prices are fetched directly from the Martian API and updated every 5 minutes. For the most up-to-date information, you can also visit the Martian Dashboard.
Usage Examples
Using a Specific Model
response = client.chat.completions.create(
model="openai/gpt-4.1-nano",
messages=[{"role": "user", "content": "Hello!"}]
)
Using Cost-Optimized Routing
response = client.chat.completions.create(
model="openai/gpt-4.1-nano:cheap",
messages=[{"role": "user", "content": "Hello!"}]
)
The :cheap
suffix automatically routes your request to the most cost-effective model that meets the quality requirements of the base model.
Model Updates
We continuously add new models as they become available. Check this page regularly or subscribe to our Discord for updates on new model additions.