rocketkind
AI

DeepInfra

DeepInfra runs open-weight models — Llama, Mistral, Qwen and the rest — behind an OpenAI-compatible API, plus dedicated deployments you provision for yourself.

Authentication

  • API key

Actions

Generic API request. Call any DeepInfra API endpoint on this connection, for the case where no shipped action covers it yet. The connection supplies the base URL, the authentication and the egress route, so only the path, query and body are yours to fill.

  • Chat CompletionsDeepInfra chat completions (OpenAI-compatible) via connection context and HTTP POST /chat/completions.
  • Chat Completions (Streaming)DeepInfra streaming chat completions (OpenAI-compatible) via connection context.
  • List deploymentsList the model deployments on the DeepInfra account — the custom or dedicated endpoints you have provisioned — to check what is running and its status.
  • List modelsList the inference models DeepInfra makes available, to resolve the modelname that its inference endpoints take, and to see each model's type.

Triggers

  • New deploymentStarts when a new model deployment is created in the DeepInfra account, so a workflow can react to newly provisioned endpoints.

Product names, logos and brands are the property of their respective owners and are used here for identification only. Their use does not imply endorsement by, or affiliation with, those owners.