Runware offers hosted inference APIs for generative AI, including an OpenAI-compatible chat-completions endpoint.

API

What your agent can do

  • Create a chat completion using the documented OpenAI-compatible format and a Runware AIR model ID.

    Via API.

Tasks depend on the interface and permissions.

Connection methods

Choose a route that fits your agent.

API connection
API path
https://api.runware.ai/v1/chat/completions

Authentication
Authorization: Bearer $RUNWARE_API_KEY
Pricing
Pay as you go
POST https://api.runware.ai/v1/chat/completions

Documentation & experience

  • 1 connection path
View sources and checks
How documentation is checked