Docs

• Sign in with Discord. You need to be in our Discord server, with a verified email.
• Give your consent on the Consents page for providers outside the EU. Requests are refused until you do.
• Create a key on the API keys page, and keep it private.
• Top up on the Billing page if you need more credit.
• Pick a model on the Models page and send a request.

https://api.adorouter.com/v1

Send your key in the Authorization header as a Bearer token.

curl https://api.adorouter.com/v1/chat/completions \
  -H "Authorization: Bearer $ADOROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-flash",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://api.adorouter.com/v1",
    api_key=os.environ["ADOROUTER_API_KEY"],
)

reply = client.chat.completions.create(
    model="deepseek-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(reply.choices[0].message.content)

• POST /v1/chat/completions, streaming included
• POST /v1/completions
• POST /v1/responses
• POST /v1/messages (Anthropic format)
• POST /v1/embeddings, if a model supports it
• GET /v1/models

adorouter serves text models only for now. Image, video and audio endpoints return a 404 with the code ENDPOINT_NOT_AVAILABLE.

Your balance goes down by each request's cost, and your usage logs show what each one cost. See Pricing.

Ask on our Discord server, or email [email protected].