One-line switch: OpenAI SDK → Modelflare

Create a key, then set base_url. One key for text, image, and video — with group failover and per-request cost tracking.

Three steps

1. Create an API key in the console, in a non-default group that lists the model you want to call.
2. Point your OpenAI client at https://modelflare.dev/v1.
3. Use an exact model ID enabled on your group (the Quickstart uses gpt-5.6-sol).

Environment variable (recommended)

Copyexport MODELFLARE_API_KEY="YOUR_MODELFLARE_API_KEY"
# base_url is always https://modelflare.dev/v1

Python

Copyimport os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["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)

Streaming (Python)

Copystream = client.chat.completions.create(
    model="gpt-5.6-sol",
    messages=[{"role": "user", "content": "Say hi in one line"}],
    stream=True,
)
for chunk in stream:
    delta = chunk.choices[0].delta.content or ""
    print(delta, end="", flush=True)

Node.js / TypeScript

Copyimport OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.MODELFLARE_API_KEY,
  baseURL: "https://modelflare.dev/v1",
});

const r = await client.chat.completions.create({
  model: "gpt-5.6-sol",
  messages: [{ role: "user", content: "Hello from Hugging Face" }],
});
console.log(r.choices[0].message.content);

curl

Copycurl https://modelflare.dev/v1/chat/completions \
  -H "Authorization: Bearer $MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-5.6-sol","messages":[{"role":"user","content":"ping"}]}'

Troubleshooting

• 401: the key is missing, malformed, or revoked.
• 403: the key is valid but the selected model or group is not allowed.
• Model unavailable: switch to an id enabled on that group, or change groups in the console.
• Image / video: same key, native request fields — see api-recipes and Image / Video docs.
• Coding agents: Codex / Claude Code / Gemini CLI → coding-agents Space.