Put your model in front of developers
Model labs, fine-tuners and GPU inference hosts: list your models on Solo Router and reach developers who already have a funded account and one key for everything. We handle sign-up, billing, payments and support. You serve tokens.
Who we work with
Open-weight model labs, teams with fine-tuned or specialised models (coding, vision, regional languages), and inference hosts with spare GPU capacity.
What you get
Paying users from day one, launch promotion on our channels (including "stealth" previews before your public launch), and per-model usage reports.
How you get paid
A per-token price you set, invoiced monthly in USD for the tokens your endpoint served. Or a revenue share. We'll agree on it together.
What we need from you
- A standard
/v1/chat/completionsendpoint (the format most AI tools use) with streaming and token usage in responses - Your price per million input and output tokens, context length and rate limits
- Reliable uptime and a status or contact channel for incidents
- A clear data policy: we only route to providers that don't train on or keep customer prompts
- The model licence, so we know it can be offered commercially
Write to [email protected] with your model name, a test endpoint and your pricing. We reply within two business days.