Skip to main content

Model format

Models use the provider/model syntax:

Built-in providers

Auto-inference

If you don’t specify a provider, Polpo infers it from the model name:
is equivalent to:

Custom providers

Point to any OpenAI-compatible endpoint by adding a provider in .polpo/polpo.json:
Then use: "model": "my-provider/model-name"

API modes

Custom model definitions

Define model metadata for accurate context window and cost tracking:

Model Gateways

Polpo can route all model calls through a gateway configured in settings.gateway (see Model Gateway). You can also register gateways as custom providers for model-level routing:

LiteLLM

LiteLLM routes to 100+ providers through a single proxy. The model ID follows LiteLLM’s naming convention.

Vercel AI Gateway

The Vercel AI Gateway provides automatic failover, cost tracking, and caching across providers.

Ollama (local)

vLLM

The model ID is passed as-is to the gateway or server — no need to pre-define every model in the config.