Unified AI Gateway

One API key for all LLMs

Point any AI client, agent, SaaS backend, or workflow at OctaRouter. Use one key across OpenAI-compatible, Anthropic Messages, and Gemini generateContent routes with prepaid metering built in.

Drop-in OpenAI-compatible call
$ curl https://api.octarouter.com/v1/chat/completions \
  -H "Authorization: Bearer sk-or-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o","messages":[...]}'

Same key works for /v1/messages (Claude) and /v1beta/... (Gemini) too.

Why OctaRouter

A lighter way to run model traffic across apps, agents, and backends.

Fewer integrations

One account, one base URL, and one API key instead of signing up, topping up, and wiring each LLM vendor separately.

One balance

Prepaid credits cover every model. No separate invoices or quota spreadsheets.

Clear visibility

Request logs show model, tokens, cost, and status so you can trace failures fast.

Built for

Teams shipping AI features that need reliable routing and predictable spend.

AI-powered apps

Ship chat, summarization, or codegen — point baseUrl at OctaRouter and swap models without new vendor accounts.

Agents & workflows

Run tool-calling agents with model fallbacks. One OctaRouter baseUrl + key in production.

SaaS backends

Meter usage per customer with gateway logs and a shared prepaid pool — configure OctaRouter once in your backend.

Scripts & automation

Call the same baseUrl from curl, CI, or cron — change the model name, not your infrastructure.

How it works

Set up once, then route requests across models with one key.

1

Create account

Sign up, verify your email, and add prepaid credits to your balance.

2

Create an API key

Create a gateway key in the dashboard and store it securely. The full secret is shown only once.

3

Send your first request

Choose a model and protocol from the Models page, then call OctaRouter with the matching base URL and endpoint path.

Three protocols, clear base URLs and paths

Each protocol has its own base URL and endpoint path. OpenAI-compatible works as the default for most models, while native Anthropic and Gemini protocols are recommended for Claude and Gemini to unlock full capabilities. Check each model card on the Models page for exact protocol support.

OpenAI protocol
https://api.octarouter.com/v1/chat/completions
Anthropic protocol
https://api.octarouter.com/v1/messages
Gemini protocol
https://api.octarouter.com/v1beta/models/{model}:generateContent

Ready to route your first request?

Create an account, add credits, and reach any major LLM through one key — OpenAI, Anthropic, or Gemini native protocols.

Start routing requests