Quickstart
Send a streamed chat completion with any OpenAI-compatible client.
1. Create an API key
Sign in to the console and create a key. The full key is shown once. Store it in a secret manager or an environment variable.
2. Export the key
export INFERE_API_KEY="ik_live_..."3. Send a request
curl https://api.infere.dev/v1/chat/completions \ -H "Authorization: Bearer $INFERE_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "deepseek-v3", "stream": true, "messages": [{"role": "user", "content": "Explain KV caching in one line."}] }'Python and TypeScript work the same way. Install the official OpenAI SDK and point its base URL at infere.dev.
from openai import OpenAI
client = OpenAI( base_url="https://api.infere.dev/v1", api_key=os.environ["INFERE_API_KEY"],)
stream = client.chat.completions.create( model="deepseek-v3", stream=True, messages=[{"role": "user", "content": "Explain KV caching in one line."}],)for chunk in stream: print(chunk.choices[0].delta.content or "", end="")import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.infere.dev/v1", apiKey: process.env.INFERE_API_KEY,});
const stream = await client.chat.completions.create({ model: "deepseek-v3", stream: true, messages: [{ role: "user", content: "Explain KV caching in one line." }],});
for await (const chunk of stream) { process.stdout.write(chunk.choices[0]?.delta?.content ?? "");}Next steps
Check the model ids, the full request reference, and how errors are returned.
Never call the API from a browser or a mobile app with a secret key embedded. Call it from your server.