FunAI API
One API for chat, image, video, audio and 3D generation across many model makers. The chat and image endpoints are OpenAI-compatible, so the OpenAI SDKs work with a base URL and key change.
- Base URL:
https://api.funai.art - API keys: created on the developer platform
- Billing: API calls are paid from your API balance (USD), which is separate from FunAI Studio plans. Credits convert at 10,000 credits = $1. See Pricing & balance.
Quick start
curl https://api.funai.art/v1/chat/completions \
-H "Authorization: Bearer $FUNAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-4o-mini", "messages": [{"role": "user", "content": "Hello!"}]}'
from openai import OpenAI
client = OpenAI(
base_url="https://api.funai.art/v1",
api_key="YOUR_FUNAI_API_KEY",
)
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
Where next
- Authentication: getting a key and the two accepted headers.
- Models: model IDs and how to find them.
- Platform-native generation: image, video, audio and 3D jobs.
- Webhooks: get told when a job finishes.
- MCP server: use FunAI from Claude, Cursor and other MCP clients.
- Errors and rate limits.
- Changelog and versioning policy.