Quickstart

Celeris provides celeris-1, a diffusion language model for short, structured responses, through an OpenAI-compatible API. Existing OpenAI clients can connect by using the Celeris base URL and API key.

1. Create an account

Sign up at the Customer Console with Google or an email address and password (email signups get a verification code).

2. Activate your workspace

A workspace must be activated before you can create API keys. Open Billing in the Console and add credit. Workspaces with starter credit are activated automatically.

3. Create an API key

In the Console, open API keys and create a key. The full dg_ key is shown at creation. Store it in a secret manager and keep it out of source control:

export CELERIS_API_KEY="dg_..."

You can reveal, rotate, or revoke the key from the Console. See Authentication.

4. Make your first request

The API base URL includes the model's name (see Models):

https://inference.cloud.celeris.ai/celeris-1/v1

cURL

curl https://inference.cloud.celeris.ai/celeris-1/v1/chat/completions \
  -H "Authorization: Bearer $CELERIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "celeris-1",
    "messages": [
      {"role": "user", "content": "Classify the sentiment of: \"the checkout flow was clear and efficient\". Reply with one word."}
    ],
    "max_tokens": 8,
    "temperature": 0
  }'

Python

# pip install openai
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://inference.cloud.celeris.ai/celeris-1/v1",
    api_key=os.environ["CELERIS_API_KEY"],
)

response = client.chat.completions.create(
    model="celeris-1",
    messages=[
        {
            "role": "user",
            "content": 'Classify the sentiment of: "the checkout flow was clear and efficient". Reply with one word.',
        }
    ],
    max_tokens=8,
    temperature=0,
)
print(response.choices[0].message.content)

TypeScript

// npm install openai
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://inference.cloud.celeris.ai/celeris-1/v1',
  apiKey: process.env.CELERIS_API_KEY,
});

const response = await client.chat.completions.create({
  model: 'celeris-1',
  messages: [
    {
      role: 'user',
      content: 'Classify the sentiment of: "the checkout flow was clear and efficient". Reply with one word.',
    },
  ],
  max_tokens: 8,
  temperature: 0,
});
console.log(response.choices[0].message.content);

:::tip Synced language tabs Selecting a language updates the examples on other pages. :::

5. Read the response

Responses use the standard OpenAI chat-completion shape. The quickstart returns one complete JSON response; OpenAI-compatible token streaming is also supported (Making requests):

{
  "id": "chatcmpl-9f2e41c0",
  "object": "chat.completion",
  "created": 1751673600,
  "model": "celeris-1",
  "choices": [
    {
      "index": 0,
      "message": {"role": "assistant", "content": "Positive"},
      "finish_reason": "stop"
    }
  ],
  "usage": {"prompt_tokens": 27, "completion_tokens": 2, "total_tokens": 29}
}

Every successful response includes a Server-Timing header with server-side latency durations. Error responses may omit usage and Server-Timing; see Errors.

Next steps

• Authentication — key lifecycle, rotation, and handling.
• Models — what celeris-1 is good at, and its limits.
• Prompt engineering — how to prompt a diffusion LLM for reliable structured output.
• Agentic workloads — the request patterns the model is built for: classify, extract, judge, rewrite.
• Rate limits — what's limited and how to back off cleanly.
• Pricing — token rates and how to estimate costs.
• Going to production — the production-readiness checklist.
• Use the Playground in the Console to test prompts without writing client code.