Hugging Face clients

pip install "huggingface_hub>=1.0"
export RUNINFRA_GATEWAY_KEY="rp_your_key_here"

import os
from huggingface_hub import InferenceClient

client = InferenceClient(
    base_url="https://api.runinfra.ai/v1",
    api_key=os.environ["RUNINFRA_GATEWAY_KEY"],
)

completion = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Write a TypeScript retry helper."}],
    max_tokens=16384,
)

print(completion.choices[0].message.content)

npm install @huggingface/inference
export RUNINFRA_GATEWAY_KEY="rp_your_key_here"

import { InferenceClient } from "@huggingface/inference";

const client = new InferenceClient(process.env.RUNINFRA_GATEWAY_KEY, {
  endpointUrl: "https://api.runinfra.ai",
});

const completion = await client.chatCompletion({
  model: "deepseek-v4-flash",
  messages: [{ role: "user", content: "Write a TypeScript retry helper." }],
  max_tokens: 16384,
});

console.log(completion.choices[0].message.content);