Animica — Write Python. Deploy to Animica. Get paid when people use it.

# Animica.dev — free AI, Python cloud and coding agent for developers and AI agents > animica.dev is the developer platform of the Animica proof-of-work L1: a free, keyless, > OpenAI-compatible inference API, a Python function cloud that pays deployers in ANM, > a free GitHub-connected coding agent, and GPU media studios — all served by the > Animica miner network. Current release: Animica 10.1.0 (2026-08-14). No signup and no API key are needed for the free AI API, the media studios or the coding agent. Rate limit on `/v1`: 30 requests/minute per IP (burst 12); over-limit requests get HTTP 429. Capacity is community-GPU-provided. Every entry in `GET /v1/models` carries a boolean `serving` flag — check it before sending work. Requests to a model with `serving: false` may queue for a long time or fail; when a worker is serving, completions typically take 1–3 minutes (use `"stream": true` and a generous client timeout). ## Free AI API (keyless, OpenAI-compatible) - [Base URL https://animica.dev/v1](https://animica.dev/v1/models): drop-in OpenAI-compatible; no Authorization header needed - [GET /v1/models](https://animica.dev/v1/models): live model list with per-model `serving` flag — models: `kimi-k3` (default, flagship coding & chat), `animica-chat`, `animica-chat-small`, `animica-chat-flagship`, `animica-knowledge` (ENA, network-trained) - [POST /v1/chat/completions](https://animica.dev/openapi.json): chat completions, SSE streaming via `"stream": true` - [GET /v1/tiers](https://animica.dev/v1/tiers): model tiers with live `available` flags - Note: `/v1/embeddings` is not currently deployed (returns 404); older docs listed it ## Generative media (dispatched to GPU miners) - [POST /v1/images/generations](https://animica.dev/openapi.json): text-to-image; returns 202 `{status:"queued", job_id, poll_url}` — queued jobs persist until a GPU miner is online; a 503 `no_media_miner` means the dispatcher was unreachable and the submission did NOT enqueue

{ "openapi": "3.1.0", "info": { "title": "Animica Free AI API", "version": "10.1.0", "description": "Free, keyless, OpenAI-compatible inference plus GPU-miner media dispatch on animica.dev. No API key required (any placeholder Authorization header is also accepted). Inference is served by community GPU workers on the Animica network: check the per-model boolean `serving` flag in GET /v1/models before sending work \u2014 requests to a non-serving model may queue for a long time or