9router-Python – Python SDK for the 9Router AI gateway (35 models)

9Router has released 9router-Python, a Python SDK and CLI for its AI gateway that routes requests to 35 models across providers including Gemini, NVIDIA, OpenRouter, Groq, Ollama, Tavily, and Exa. The SDK supports chat, embeddings, image generation, TTS, STT, web search, and web fetch through a single local endpoint with automatic fallback. It requires Python 3.9+ and is installable via pip.

Python SDK + CLI for the 9Router AI gateway. One tiny library to talk to an OpenAI-compatible gateway that routes to Gemini, NVIDIA, OpenRouter, Groq, Ollama, Tavily and Exa — chat, images, TTS, STT, embeddings and web search/fetch — all through a single local endpoint, with automatic fallback between providers. bash $ pip install 9router-python | Capability | SDK method | CLI command | |---|---|---| | 💬 Chat with streaming | client.chat / chat stream | ninerouter chat | | 🌀 Embeddings | client.embeddings | ninerouter embed | | 🖼️ Image generation | client.image | ninerouter image | | 🔊 Text-to-speech | client.tts | ninerouter tts | | 🎙️ Speech-to-text | client.stt | ninerouter stt | | 🔎 Web search | client.web search | ninerouter web search | | 📄 Fetch URL → markdown | client.web fetch | ninerouter web fetch | | ⚙️ Models & health | client.models , health | ninerouter models , health | Everything runs through one base URL. Configure once, use everywhere. bash $ pip install 9router-python $ ninerouter chat "Hello, world " --stream Hello 👋 How can I help you today? That's it. One gateway, one SDK, every capability. python from ninerouter import NineRouter with NineRouter as client: reply = client.chat "Explain a monad in one sentence" print reply.text Stream tokens as they arrive: for chunk in client.chat stream "Write a haiku about Python" : print chunk.content, end="", flush=True image = client.image "a watercolor of mountains at sunrise" open "out.png", "wb" .write image.content audio = client.tts "Olá, mundo ", voice="pt-BR-FernandaNeural", model="gemini/gemini-3.1-flash-tts-preview" open "speech.wav", "wb" .write audio text = client.stt file= "recording.wav", open "recording.wav", "rb" .read print text.text vector = client.embeddings "The quick brown fox" 0 curl similarity = sum a b for a, b in zip vector, other results = client.web search "9Router open source" for r in results.results: print r.title, "-", r.url page = client.web fetch "https://example.com" print page.content.text ninerouter help ninerouter health gateway status ninerouter models --kind chat list chat models ninerouter chat "Hello" --stream chat with streaming ninerouter embed "text" embedding vector ninerouter image "a red fox" --out fox.png ninerouter tts "Hello" --voice pt-BR-FernandaNeural ninerouter stt recording.wav ninerouter web search "9Router" ninerouter web fetch https://example.com ninerouter config show effective config Resolution order: CLI flags environment variables defaults. | Setting | Env var | Default | |---|---|---| | Base URL | NINEROUTER URL | http://localhost:20128 | | API key | NINEROUTER KEY | optional | export NINEROUTER URL="http://localhost:20128" export NINEROUTER KEY="sk-..." optional if gateway has auth disabled The key is only sent when non-empty, so a gateway running with requireApiKey=false works out of the box. SSE-by-default: the gateway often streams SSE even when stream isn't set — the client parses both JSON and SSE transparently. TTS : some OpenRouter TTS models return 502 upstream errors; prefer a gemini/ TTS model. STT : multipart upload with gemini/ or groq/whisper- models. Web search/fetch use not provider model , e.g. tavily , exa , or the search-combo . Combos owned by: "combo" , like Code auto-fallback across providers — great defaults for chat. pip install -e . dev pytest mocked unit tests pytest -m live live tests needs a running gateway Requires Python 3.9+. 9Router gives you keyless access to dozens of AI providers with automatic fallback, so your app keeps working even if one provider's quota or free tier runs out. This SDK removes the friction: you get a typed, tested Python client and a friendly CLI without caring about which endpoint each provider uses. This SDK is a thin HTTP client — it does not hold AI provider keys, does not upload your prompts anywhere other than the gateway you point it at, and ships no telemetry . No secrets in the client. An optional API key is read from the environment NINEROUTER KEY and sent only to your configured gateway. Nothing leaves your network except to the gateway you configure. The SDK never sends data to the SDK author or any third party. The gateway holds the keys. Provider API keys Gemini, NVIDIA, Tavily, … live in your 9Router gateway on your machine/VM — not in this library. Supply-chain hygiene. Only two runtime dependencies httpx , typer , both widely trusted. CI runs unit tests on every push across Python 3.9/3.11/3.13. No-secrets guardrail. A test in CI scans the repo for committed credentials and fails the build if anything slips in. See SECURITY.md /ChristopherDond/9router-python/blob/main/SECURITY.md for the full policy and how to report a vulnerability privately. MIT © ChristopherDond SDK Python + CLI para o gateway de IA 9Router. Um único pacote para conversar com um gateway compatível com a API da OpenAI que roteia Gemini, NVIDIA, OpenRouter, Groq, Ollama, Tavily e Exa — chat, imagens, TTS, STT, embeddings e busca web, com fallback automático entre provedores. pip install 9router-python ninerouter chat "Olá, mundo " --stream Consulte a seção Features e Quickstart acima — a API e o CLI são idênticos. Para configurar, veja Configuration . python from ninerouter import NineRouter with NineRouter as client: print client.chat "Me conta uma piada" ⬆ back to top 9router-python