Every client. Every model.
One key.
One OpenAI-compatible key. Every model, every client, no account.
Or try chat firstcurl https://api.minirouter.sh/v1/chat/completions \ -H "Authorization: Bearer $MINIROUTER_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "particle/particle-1", "messages": [{"role": "user", "content": "ping"}] }'from openai import OpenAI client = OpenAI( base_url="https://api.minirouter.sh/v1", api_key="mr-live-…",) client.chat.completions.create( model="particle/particle-1", messages=[{"role": "user", "content": "ping"}],)import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://api.minirouter.sh/v1", apiKey: process.env.MINIROUTER_API_KEY,}); await client.chat.completions.create({ model: "particle/particle-1", messages: [{ role: "user", content: "ping" }],});HTTP/2 200x-minirouter-model: particle/particle-1x-minirouter-provider: particle { "object": "chat.completion", "model": "particle/particle-1", "choices": [{ "message": { "role": "assistant", "content": "pong" } }]}- Published models
- 312
- Extra credit when you pay with MINI
- +5%
- Minimum deposit
- $0.50
- Account or KYC (ID check)
- None
40 AI labs. One endpoint.
Why MiniRouter
Less setup. More models.
More models. One API.
A route around failures.
Crypto in. Credit ready.
A key is all you need.
Catalog
Newest models. Live today.
Picked from 312 published models.
Clients
Already at home in your tools.
Keep your workflow. Connect a different model.
A familiar setup. More choice.
Get a key, add credit or connect provider keys. Keep your client.
OPENAI_BASE_URL=https://api.minirouter.sh/v1OPENAI_API_KEY=mr-live-…OPENAI_MODEL=meta/llama-3.3-70bBase URLAPI keyModel ID
Agent setuphttps://api.minirouter.sh/v1Your providers. Your keys.
Connect OpenAI, Anthropic or DeepSeek. Same endpoint, your limits.
0% fee with one key per providerTwo or more enabled keys for a provider: 3% of published-rate usage. Your provider bills inference separately. Providers without an enabled key keep using MiniRouter credits.
Make a good setup your default.
Save a model, instructions, tools and routing as a named preset. Each change is saved as a new version.
model: "@preset/product-writer"instructions: savedtools: savedversion: activeGive your app a voice.
Speech, transcription and audio input on the key you already use.
curl --fail-with-body --retry 0 --max-time 120 \ https://api.minirouter.sh/v1/audio/speech \ -H "Authorization: Bearer $MINIROUTER_API_KEY" \ -H 'Content-Type: application/json' \ -D response.headers --output speech.mp3 \ --data '{ "model": "openai/tts-1", "input": "The quick brown fox jumps over the lazy dog.", "voice": "alloy", "response_format": "mp3"}'- TTS-1 · per 1M chars
- $15.75
- Whisper · per minute
- $0.0063
Your team’s AI.
One place to pay.
Shared credit. Individual keys. Spending controls.
Need invoicing or a usage commitment? Let’s talk about how your team buys AI.
Explore teamsGood to know.
Credits buy inference and cannot be withdrawn.
Prompts, responses and tool content are saved in private debug traces for 30 days. There is no opt-out.
Read the docsAI-assisted answers about MiniRouter. Leave out keys and secrets.
Changelog