openai-oxide

Feature-complete OpenAI client for Rust, Node.js, and Python.

openai-oxide implements the full Responses API, Chat Completions, and 20+ other endpoints with persistent WebSockets, hedged requests, streaming with early-parse, and type-safe Structured Outputs.

Why openai-oxide?

• Streaming — SSE parser with anti-buffering headers, 2.5x faster per-chunk vs official JS SDK
• WebSocket Mode — Persistent wss:// connections, 29-44% faster on multi-turn benchmarks
• Stream FC Early Parse — Execute tools the moment arguments.done arrives
• Structured Outputs — parse::<T>() auto-generates JSON schema from Rust types
• Hedged Requests — Send redundant requests, cancel the slower (technique from Google’s “The Tail at Scale”)
• WASM First-Class — Full streaming in Cloudflare Workers and browsers
• 1100+ Types — Auto-synced from Python SDK via openai-types crate

Packages

OpenAI Compatibility

Parameter names match the official Python SDK exactly. If the OpenAI docs show model="gpt-5.4", use .model("gpt-5.4") in Rust or {model: "gpt-5.4"} in Node.js.

See the OpenAI Docs Mapping for a complete cross-reference.