Making requests

Celeris exposes an OpenAI-compatible HTTP API. You can use the official OpenAI SDKs or other clients that support a custom base URL.

Base URL   https://inference.cloud.celeris.ai/celeris-1/v1
Auth       Authorization: Bearer dg_...
Content    application/json

Chat completions

POST /chat/completions is the primary endpoint.

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": "system", "content": "Extract the requested fields. Reply with JSON only."},
      {"role": "user", "content": "Order #4411: 2x flat white, oat milk, pickup 8:15am. Fields: items, milk, pickup_time"}
    ],
    "max_tokens": 64,
    "temperature": 0,
    "seed": 7
  }'

Python

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": "system", "content": "Extract the requested fields. Reply with JSON only."},
        {
            "role": "user",
            "content": "Order #4411: 2x flat white, oat milk, pickup 8:15am. Fields: items, milk, pickup_time",
        },
    ],
    max_tokens=64,
    temperature=0,
    seed=7,
)
print(response.choices[0].message.content)

TypeScript

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: 'system', content: 'Extract the requested fields. Reply with JSON only.'},
    {
      role: 'user',
      content: 'Order #4411: 2x flat white, oat milk, pickup 8:15am. Fields: items, milk, pickup_time',
    },
  ],
  max_tokens: 64,
  temperature: 0,
  seed: 7,
});
console.log(response.choices[0].message.content);

Parameters that matter most here

The API accepts the chat-completion fields listed in the API reference. These parameters have the greatest effect on short, structured workloads:

Parameter	Guidance
max_tokens	Set a limit that fits the expected response. For example, a label may need 4 tokens and a small JSON object may need 64. Lower limits reduce worst-case latency and cost.
temperature	Use 0 for classification and extraction. Increase it only when the task benefits from variation.
seed	Combine with temperature: 0 to reduce sampling variation between requests.
stop	Standard stop sequences are honored.
messages	Keep prompts short and pointed. Prompt plus max_tokens must fit the 4,096-token context window.

The full parameter reference lives in the API reference.

Streaming

Leave stream unset for one complete JSON response, or set stream: true for OpenAI-compatible server-sent events. Streaming responses end with [DONE]. Set stream_options: {"include_usage": true} so the final chunk carries the request's token usage.

For short responses, a single JSON response is usually simpler. Use streaming when an interactive client needs to display partial output. A client disconnect does not guarantee that processing stops; see Pricing.

Calling from the browser

The API supports browser requests. It responds to preflight OPTIONS requests, returns Access-Control-Allow-Origin: *, and exposes the Server-Timing header to browser scripts. A single-page application can call Celeris directly:

const response = await fetch(
  'https://inference.cloud.celeris.ai/celeris-1/v1/chat/completions',
  {
    method: 'POST',
    headers: {
      'Authorization': `Bearer ${key}`,
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      model: 'celeris-1',
      messages: [{role: 'user', content: 'Rewrite as a search query: cheap flights sydney to tokyo june'}],
      max_tokens: 32,
      temperature: 0,
    }),
  },
);
if (!response.ok) throw new Error(`Celeris request failed: ${response.status}`);
const result = await response.json();
console.log(result.choices[0].message.content);

Authentication uses a bearer header rather than a cookie. Do not embed a Celeris key in public client-side code. See Authentication.

Response behavior

• API errors use OpenAI-compatible JSON. SDKs expose them as HTTP errors with the status intact. Handle broad cases by status and use error.code when you need more detail. Some infrastructure-level 5xx responses may not include JSON. See Errors.
• Every successful response includes usage (prompt, completion, and total tokens) — the same numbers the usage dashboard aggregates.
• Every successful response includes Server-Timing with server-side latency durations. Error responses may omit usage and Server-Timing. 429 responses include Retry-After, and responses echo a caller-supplied trace ID.