Quickstart

curl https://api.infero.xyz/v1/chat/completions \
  -H "Authorization: Bearer sk-infero-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.infero.xyz/v1", api_key="sk-infero-...")
r = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(r.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.infero.xyz/v1", apiKey: "sk-infero-..." });
const r = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(r.choices[0].message.content);

import anthropic

client = anthropic.Anthropic(base_url="https://api.infero.xyz", api_key="sk-infero-...")
r = client.messages.create(
    model="kimi-k2.6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
)
print(r.content[0].text)

export ANTHROPIC_BASE_URL=https://api.infero.xyz
export ANTHROPIC_API_KEY=sk-infero-...
export ANTHROPIC_MODEL=qwen3-coder-480b
export ANTHROPIC_SMALL_FAST_MODEL=deepseek-v4-flash
claude

model = "qwen3-coder-480b"
model_provider = "infero"

[model_providers.infero]
name = "infero"
base_url = "https://api.infero.xyz/v1"
env_key = "INFERO_API_KEY"
wire_api = "chat"   # infero serves chat completions, not the Responses API

{
  "provider": {
    "infero": {
      "npm": "@ai-sdk/openai-compatible",
      "options": { "baseURL": "https://api.infero.xyz/v1", "apiKey": "sk-infero-..." },
      "models": { "qwen3-coder-480b": {}, "kimi-k3": {}, "glm-5": {} }
    }
  }
}