AI Inference

Checking…

OpenAI-compatible API with multi-provider routing (Animica workers, Bittensor, and external GPU providers). Point any OpenAI SDK at https://pool.animica.org/v1 and pay with crypto credits.

Get an API key Credits

Models

Model	Description	Backend	$/1K in	$/1K out
Loading models…

Quickstart — cURL

curl https://pool.animica.org/v1/chat/completions \
  -H "Authorization: Bearer anm_live_…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anm-fast-8b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Quickstart — Python

from openai import OpenAI

client = OpenAI(
    base_url="https://pool.animica.org/v1",
    api_key="anm_live_…",
)
resp = client.chat.completions.create(
    model="anm-fast-8b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Playground

Run a real request against the live cluster — no API key needed while you're signed in. Each run is billed to your credit balance at the rates above.