respan-gateway

<div align="center"> <a href="https://www.respan.ai"> <picture> <source media="(prefers-color-scheme: dark)" srcset="docs/assets/wordmark-dark.png"> <img src="docs/assets/wordmark.png" alt="Respan Gateway" width="420"> </picture> </a> <p><b>The universal adapter for AI.</b></p> <div> <a href="#license"><img src="https://img.shields.io/badge/License-MIT%20OR%20Apache--2.0-brightgreen.svg?style=flat" alt="License: MIT OR Apache-2.0"></a> <a href="https://github.com/respanai/respan-gateway/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/respanai/respan-gateway/ci.yml?branch=main&style=flat&label=CI" alt="CI"></a> <a href="https://github.com/respanai/respan-gateway/releases"><img src="https://img.shields.io/github/v/release/respanai/respan-gateway?style=flat&label=Latest%20Release&color=6D28D9" alt="Latest release"></a> <a href="https://crates.io/crates/respan-gateway"><img src="https://img.shields.io/crates/v/respan-gateway?style=flat&logo=rust&label=crates.io&color=6D28D9" alt="crates.io"></a> <a href="https://pypi.org/project/respan-gateway/"><img src="https://img.shields.io/pypi/v/respan-gateway?style=flat&logo=python&logoColor=white&label=PyPI&color=6D28D9" alt="PyPI"></a> <a href="https://discord.com/invite/KEanfAafQQ"><img src="https://img.shields.io/badge/Discord-Join-5865F2?style=flat&logo=discord&logoColor=white" alt="Discord"></a> </div> </div> <br>

Respan Gateway is a single Rust binary that sits between your code and every AI API. Point the SDK you already use at it, and it connects you to everything: chat models, images, video and voice from every major provider; tools for any model, from web search and memory to code sandboxes and any MCP server; and traffic control (format translation, fallback, retries and hedged requests), with a live log of every call. ▶ Watch the demo

<br> <div align="center"> <img alt="Your app plugs into Respan Gateway, which connects it to models, voice, image and video, tools, embeddings and self-hosted models, with fallback, hedging, translation, tool loop, PII redaction and tracing built in" src="docs/assets/gateway-hero.png" width="900"> </div> <br>

Key features

• Any client, any model<br> OpenAI Chat Completions, OpenAI Responses, Anthropic Messages and Gemini API clients can all call any model, with streaming, tools, images and reasoning translated.

• Multimodal<br> Realtime voice across vendors (an OpenAI Realtime client talks to Gemini Live, and back), plus images, speech, transcription, embeddings and video through OpenAI's or Gemini's APIs, to any vendor that has them.

• MCP tools for every model<br> Put MCP servers or built-in tool vendors behind the gateway, from web search to code sandboxes. It runs their tools inside chat requests, so a plain chat call can use them, whatever the client or model.

• Traffic control<br> Named routes, globs and provider/model; fallback, retries, cheapest or fastest; and hedged requests that race a slow call against a second provider.

• Observability<br> A live request log with cost, latency and tokens for every call, and traces in Respan, where span-02 analyzes how your agents behave.

• Best-in-class performance<br> 0.07 ms of added latency, 56,000 requests per second and 31 MB of memory in our benchmarks: about 3× the throughput of the next fastest gateway we tested.

• Write your own plugin in minutes<br> Every feature above is a plugin, built on the same public Rust API you can use: one trait with four hooks. Start from the plugin guide or an example such as guardrails, PII masking or billing.

Quickstart

1. Install

pip install respan-gateway

Or cargo install respan-gateway, or a GitHub release.

2. Run it with your keys

export OPENAI_API_KEY=sk-...
respan-gateway

No config file needed: every vendor whose key is set becomes a provider.

3. Call any model from any SDK

from anthropic import Anthropic

client = Anthropic(base_url="http://localhost:8080", api_key="unused")
reply = client.messages.create(
    model="gpt-6-luna", max_tokens=256,
    messages=[{"role": "user", "content": "Hello from the Anthropic SDK"}])
print(reply.content[0].text)

The web UI is at localhost:8080/ui/. Next: configuration and MCP tools.

Other ways to run it

• Python, in-process — Run the gateway inside your Python app, with no server.
• Embed in Rust — Mount the gateway in your own Rust service.
• Docker — docker run -p 8080:8080 -e OPENAI_API_KEY -e RESPAN_CLIENT_KEYS=<a key of yours> ghcr.io/respanai/respan-gateway on any container host; listening beyond localhost, it needs a client key.

Performance

| | Respan Gateway | Bifrost | Portkey | LiteLLM (1 worker) | |---|---:|---:|---:|---:| | Added latency (p50) | 0.07 ms | 0.16 ms | 0.17 ms | 4.34 ms | | Throughput | 56,734/s | 18,182/s | 4,187/s | 268/s | | Memory | 31 MB | 488 MB | 350 MB | 418 MB | | 1k streams, success | 100% | 92–100% | — | 79% | | 1k streams, memory | 128 MB | 688 MB | — | 493 MB | | p99, 5% slow calls | 105 ms | 2,002 ms | 2,003 ms | 2,024 ms |

Configuration

You don't need a config file to start. When you want more, run respan-gateway init for a commented gateway.toml. One file sets up keys, providers, traffic control, tools and tracing:

client_keys = [{ name = "app", key = "env:APP_KEY" }]   # who may call the gateway

[providers.openai]                      # a built-in vendor: just add a key
vendor = "openai"
key = "env:OPENAI_API_KEY"

[providers.anthropic]
vendor = "anthropic"
key = "env:ANTHROPIC_API_KEY"

[providers.local]                       # any OpenAI-compatible endpoint
formats = ["openai-chat"]
base_url = "http://localhost:8000/v1"

[routes.smart]                          # clients ask for "model": "smart"
to = ["anthropic/claude-haiku-5-5", "openai/gpt-6-luna"]
hedge = "800ms"                         # race the second if the first is slow

[tools.search]                          # web search as MCP tools
vendor = "linkup"
key = "env:LINKUP_API_KEY"

[plugins.tool_loop]                     # every model can use them
servers = ["search"]

[plugins.respan]                        # trace every call in Respan
key = "env:RESPAN_API_KEY"

respan-gateway check validates it, and --watch or SIGHUP reloads it without a restart. Without client keys, the gateway answers only on loopback and refuses to start on a public address.

Reference: configuration · vendors · tool vendors · MCP and tools · gateway.example.toml

Supported API formats

Call the gateway in any format on the left, and it reaches every provider on the right, translating between them.

| | Your code calls | It can reach | |---|---|---| | Chat | OpenAI Chat Completions<br>OpenAI Responses<br>Anthropic Messages<br>Gemini API | <picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/vendors/openai-dark.svg"><img src="docs/assets/vendors/openai.svg" alt="OpenAI" title="OpenAI" width="20" height="20"></picture> <picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/vendors/anthropic-dark.svg"><img src="docs/assets/vendors/anthropic.svg" alt="Anthropic" title="Anthropic" width="20" height="20"></picture> <img src="docs/assets/vendors/gemini.svg" alt="Gemini" title="Gemini" width="20" height="20"> <picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/vendors/xai-dark.svg"><img src="docs/assets/vendors/xai.svg" alt="xAI" title="xAI" width="20" height="20"></picture> <img src="docs/assets/vendors/deepseek.svg" alt="DeepSeek" title="DeepSeek" width="20" height="20"> <img src="docs/assets/vendors/mistral.svg" alt="Mistral" title="Mistral" width="20" height="20"> <picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/vendors/groq-dark.svg"><img src="docs/assets/vendors/groq.svg" alt="Groq" title="Groq" width="20" height="20"></picture> <picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/vendors/openrouter-dark.svg"><img src="docs/assets/vendors/openrouter.svg" alt="OpenRouter" title="OpenRouter" width="20" height="20"></picture> <img src="docs/assets/vendors/together.svg" alt="Together" title="Together" width="20" height="20"> <img src="docs/assets/vendors/deepinfra.svg" alt="DeepInfra" title="DeepInfra" width="20" height="20"> <picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/vendors/ollama-dark.svg"><img src="docs/assets/vendors/ollama.svg" alt="Ollama" title="Ollama" width="20" height="20"></picture> <img src="docs/assets/vendors/empiriolabs.png" alt="EmpirioLabs AI" title="EmpirioLabs AI" width="20" height="20"><br>any chat model, whichever of the four formats it speaks | | Realtime voice | OpenAI Realtime<br>Gemini Live | <picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/vendors/openai-dark.svg"><img src="docs/assets/vendors/openai.svg" alt="OpenAI" title="OpenAI" width="20" height="20"></picture> <img src="docs/assets/vendors/gemini.svg" alt="Gemini" title="Gemini" width="20" height="20"> <img src="docs/assets/vendors/mistral.svg" alt="Mistral" title="Mistral" width="20" height="20"><br>OpenAI ⇄ Gemini voice; Mistral for transcription | | Images | OpenAI Images<br>Gemini Images | <picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/vendors/openai-dark.svg"><img src="docs/assets/vendors/openai.svg" alt="OpenAI" title="OpenAI" width="20" height="20"></picture> <img src="docs/assets/vendors/gemini.svg" alt="Gemini" title="Gemini" width="20" height="20"> <picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/vendors/xai-dark.svg"><img src="docs/assets/vendors/xai.svg" alt="xAI" title="xAI" width="20" height="20"></picture> <img src="docs/assets/vendors/together.svg" alt="Together" title="Together" width="20" height="20"> <img src="docs/assets/vendors/deepinfra.svg" alt="DeepInfra" title="DeepInfra" width="20" height="20"> <picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/vendors/openrouter-dark.svg"><img src="docs/assets/vendors/openrouter.svg" alt="OpenRouter" title="OpenRouter" width="20" height="20"></picture> <img src="docs/assets/vendors/empiriolabs.png" alt="EmpirioLabs AI" title="EmpirioLabs AI" width="20" height="20"> | | Speech, transcription | OpenAI Speech<br>OpenAI Transcriptions | <picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/vendors/openai-dark.svg"><img src="docs/assets/vendors/openai.svg" alt="OpenAI" title="OpenAI" width="20" height="20"></picture> <picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/vendors/groq-dark.svg"><img src="docs/assets/vendors/groq.svg" alt="Groq" title="Groq" width="20" height="20"></picture> <img src="docs/assets/vendors/deepinfra.svg" alt="DeepInfra" title="DeepInfra" width="20" height="20"> <img src="docs/assets/vendors/empiriolabs.png" alt="EmpirioLabs AI" title="EmpirioLabs AI" width="20" height="20"> | | Embeddings | OpenAI Embeddings | <picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/vendors/openai-dark.svg"><img src="docs/assets/vendors/openai.svg" alt="OpenAI" title="OpenAI" width="20" height="20"></picture> <img src="docs/assets/vendors/gemini.svg" alt="Gemini" title="Gemini" width="20" height="20"> <img src="docs/assets/vendors/mistral.svg" alt="Mistral" title="Mistral" width="20" height="20"> <im