One key for LLM, image, and video. OpenAI-compatible chat — point your SDK at https://modelflare.dev/v1, with group failover and per-request cost tracking.
Chat, Responses, Anthropic Messages, Images, and Video on the same auth.
Ordered fallbacks so one unavailable route does not fail the request.
Track tokens, images, and video spend per request — plus Smart keys and cache hit guarantee.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_MODELFLARE_API_KEY",
base_url="https://modelflare.dev/v1",
)
r = client.chat.completions.create(
model="gpt-5.6-sol",
messages=[{"role": "user", "content": "Hello from Hugging Face"}],
)
print(r.choices[0].message.content)Setup guides and engineering notes: one key for text, image, and video; the OpenAI SDK switch; coding agents; streaming, fallback, and async video; Smart API Keys; usage and cost records; Media Skill; Castaly.
Org: huggingface.co/Modelflare · Docs: docs.modelflare.dev