# 64bit/async-openai

Rust library for OpenAI

Repository: https://github.com/64bit/async-openai
Canonical: https://ross.abutalabs.com/products/async-openai
Homepage: https://docs.rs/async-openai
Language: Rust
License: MIT
License Family: permissive
Topics: openai, rust
Last push: 2026-08-18T18:06:26+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 98, release rhythm 83, longevity 99
- inputs: {"age_days": 1391, "days_push": 15, "days_rel": 33, "gap_med": 3.5, "n_releases_24m": 61}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1998, forks 400 (observed 2026-08-28T04:06:03.641182+00:00)

## What it is
async-openai is a Rust library providing typed, async clients for the OpenAI API, covering chat completions, responses, embeddings, assistants, audio, images, batches, fine-tuning, and more via feature flags. It is built on reqwest and tokio and supports custom configurations, organizations, and streaming.

## Use cases
- call the OpenAI API from Rust
- build a chatbot in Rust with GPT models
- generate embeddings for semantic search in Rust
- stream chat completions with SSE in Rust
- transcribe audio with Whisper from a Rust app
- generate images with DALL-E from Rust
- fine-tune OpenAI models programmatically

## When to choose
- you are writing a Rust application or service that needs OpenAI API access with typed requests and responses
- you want async, streaming support (SSE/WebSocket) for chat completions and realtime APIs
- you need broad OpenAI API coverage (assistants, batches, files, vector stores, moderation) in one crate

## When to avoid
- you need a multi-provider LLM client that abstracts over Anthropic, Gemini, and others
- you are not using Rust or an async runtime like tokio
- you only need simple one-off HTTP calls and prefer a raw HTTP client without typed models

## Facets
- artifact type: library
- maturity: active
- function: http-client, sdk, llm-inference, chatbot, rag, speech-recognition, image-processing, tts
- domain: large-language-models, artificial-intelligence, apis, developer-tools
- platform: rust, cross-platform
- tags: openai-api, async, tokio, api-client, crates-io

## Member repositories
- 64bit/async-openai (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:03.641182+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:02:11.716081+00:00, confidence not recorded.
  - readme: https://github.com/64bit/async-openai (fetched 2026-08-28T04:06:03.641182+00:00, sha bbb8c2275775)
  - homepage: https://docs.rs/async-openai (fetched 2026-08-29T10:42:03.904815+00:00, sha 675c6730002a)
  - site_page: https://docs.rs/ (fetched 2026-08-29T10:42:03.908189+00:00, sha ec250476e6e4)
  - site_page: https://docs.rs/crate/async-openai/latest (fetched 2026-08-29T10:42:03.909838+00:00, sha d30161f2fd89)
  - site_page: https://docs.rs/crate/async-openai/latest/features (fetched 2026-08-29T10:42:03.911561+00:00, sha eb7403922327)
  - site_page: https://docs.rs/about (fetched 2026-08-29T10:42:03.913089+00:00, sha 29ab7986fbf5)
  - site_page: https://docs.rs/about/badges (fetched 2026-08-29T10:42:03.914598+00:00, sha 6588cac258af)
  - site_page: https://docs.rs/about/builds (fetched 2026-08-29T10:42:03.916444+00:00, sha 811231ca4680)
  - site_page: https://docs.rs/about/metadata (fetched 2026-08-29T10:42:03.918420+00:00, sha 0dcdccb2b2b2)
  - site_page: https://docs.rs/about/redirections (fetched 2026-08-29T10:42:03.920020+00:00, sha 1b1efd93105f)
- Data as of 2026-08-30T08:39:29.467469+00:00.