Integrations

Point the official openai Python package at Inference APIs with base_url. Chat, streaming, tool calling, speech and transcription all work unchanged.

Set baseURL on the official openai npm package. Works in Node, Bun, Deno and edge runtimes.

Use the openai/ prefix with api_base to route any LiteLLM call — SDK or proxy — to Inference APIs, including as a fallback provider.

ChatOpenAI accepts base_url, so chains, agents and LangGraph graphs run on Inference APIs models without any provider-specific package.

Use the OpenAILike LLM class, which exists for exactly this case: an OpenAI-compatible endpoint serving non-OpenAI model ids.

Use @ai-sdk/openai-compatible to create a provider for Inference APIs; then streamText, generateText and tool calling work as with any provider.

Add Inference APIs models to Continue with provider: openai and an apiBase. Works for chat, edit and autocomplete roles.

Choose the "OpenAI Compatible" provider in Cline settings and paste the base URL, key and a model id.

One connection gives Open WebUI chat models, speech-to-text and text-to-speech from Inference APIs — useful when the local Whisper or TTS engine is too slow on a CPU host.

Create an OpenAI credential in n8n with a custom Base URL; the OpenAI Chat Model, Transcribe and Text-to-Speech nodes then run on Inference APIs.

Point aider at Inference APIs with two flags or two environment variables.