Skip to content
AI Models Router

Quickstart

Make your first request in under a minute.

AI Models Router exposes one OpenAI-compatible endpoint for every model in the catalog. If your code already uses an OpenAI SDK, the migration is changing the base URL and the API key.

Base URLhttps://api.aimodelsrouter.ai/v1
AuthAuthorization: Bearer sk-amr-v1-…
EndpointPOST /chat/completions

1. Create an API key

Sign up, add credits on the Credits page, then create a key on the API keys page. The full key is shown once; store it in an environment variable:

Shell
export AMR_API_KEY=sk-amr-v1-...

2. Make a request

Pick a model slug from the model directory (format author/model) and send a chat completion:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aimodelsrouter.ai/v1",
    api_key="sk-amr-v1-...",  # or os.environ["AMR_API_KEY"]
)

completion = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash",
    messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)

3. Read the response

The response follows the OpenAI Chat Completions shape. The id is our generation id (gen-…), model is the slug you asked for, and usage.cost is the exact amount charged in USD.

Response (shape)
{
  "id": "gen-3f1c9b8e0a2d4c55b6e7f8a9b0c1d2e3",
  "object": "chat.completion",
  "created": 1793050000,
  "model": "deepseek/deepseek-v4-flash",
  "choices": [{
    "index": 0,
    "message": { "role": "assistant", "content": "..." },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 120,
    "total_tokens": 134,
    "cost": 0.000045
  }
}
Field values above illustrate the shape only. Your real cost is computed from the model's listed prices and the token counts of your request; see Billing & credits.

Next steps