AI API guides
Integrating and operating an OpenAI-compatible inference API: authentication, streaming, tool calling, routing, embeddings and migration.
2 published guides · Written by FastInfra · Figures update from the live catalog · RSS feed
Streaming chat completions: handling server-sent events that survive production
Streaming chat completions over server-sent events: how delta chunks arrive, how to parse them, and the timeout, retry and cancellation rules that hold up.
How to move an OpenAI SDK app to an OpenAI-compatible API in one change
Switch an existing OpenAI SDK app to FastInfra's OpenAI-compatible API by changing base_url and the key. Covers model ids, streaming and what differs.