OpenAI-compatible API
An OpenAI-compatible API accepts the same request and response format as OpenAI's Chat Completions endpoint, so existing SDKs and tools work with it by changing only the base URL and key.
The de facto standard covers messages with roles, streaming over server-sent events, tool calls and response formats. Inference servers and many providers expose it so clients can switch models without code changes.
Kojen deploys trained agents behind OpenAI-compatible endpoints at /api/v1/endpoints/{deployment}/chat/completions, with real SSE streaming and tool calls forwarded.
Learn more on Kojen
Related terms
- MCPThe Model Context Protocol (MCP) is an open protocol for connecting AI applications to external tools, data and prompts through a standard client–server interface, built on JSON-RPC..
- KV cacheThe KV cache stores the attention keys and values of tokens a Transformer has already processed, so generating each new token doesn't recompute them.
Sources
Put the definitions to work.
Kojen evaluates, tunes and red-teams your agents with these methods built in: Wilson intervals, pass^k, LLM judges with visible components. Free to start.
Start training free