Martian
Martian provides a model router and gateway that forwards each request to the most suitable LLM based on performance, cost, and reliability. It’s a drop-in, OpenAI-compatible endpoint with controls for max cost and willingness-to-pay, automatic failover across providers, benchmarking reports, and access to a large catalog of supported models. A free developer tier includes 2,500 requests; paid usage is metered, and enterprises can deploy custom routers with SLA and VPC options.
No discussions yet
Be the first to start a discussion about Martian
Developer
Martian is an AI research and tooling company focused on interpretability and model routing for higher performance and lower cost.
Pricing and Plans
(Freemium)
Developer (Free tier)
Free
- 2,500 requests free
- API access, unlimited runs
- Access to full model list
- Performance vs. cost optimization
Developer (usage-based)
$20/month
- $20 per additional 5,000 requests after free tier
Enterprise (Custom Router)
Contact for pricing
- Custom-built router tuned to your data and tasks
- SLA and VPC deployment
- API access, unlimited runs
- Performance vs. cost optimization
- Access to complete model list
System Requirements
Operating System
Any OS with HTTPS support
Memory (RAM)
N/A (cloud service)
Processor
N/A (cloud service)
Disk Space
N/A (cloud service)
AI Capabilities
Cost-aware model selection
Performance-aware model selection
Availability-aware routing and failover
OpenAI-compatible gateway
Route scoping to allowed model sets
Per-request metadata capture
Router benchmarking and reporting