Chat Completions

Chat completions are the core inference primitive of the OpenDunes API. Send a conversation as an ordered array of messages, get a completion back — or stream it token by token.

Endpoint#

POST https://opendunes.com/api/v1/chat/completions

This is the only inference endpoint today. It is compatible with the OpenAI chat completions spec, so any code or library targeting the OpenAI API works without modification — just swap the base URL and key.

Request body#

For the full parameter set, including fields that are not yet available, see Parameters.

Messages & roles#

Each message object has a role and content.

content can be a plain string or an array of content parts. Use the parts format to send images alongside text for vision-capable models:

{
  "role": "user",
  "content": [
    { "type": "text", "text": "What is in this image?" },
    { "type": "image_url", "image_url": { "url": "https://example.com/photo.jpg" } }
  ]
}

Example request#

curl https://opendunes.com/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENDUNES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "messages": [
      { "role": "system", "content": "You are a concise assistant." },
      { "role": "user", "content": "Marhba! Say hello in one line." }
    ],
    "temperature": 0.7
  }'

Example response#

{
  "id": "chatcmpl-01938fae2a7b7000aabbccdd",
  "object": "chat.completion",
  "created": 1750000000,
  "model": "anthropic/claude-sonnet-5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Marhba bik! Hello and welcome — great to meet you."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 13,
    "total_tokens": 37
  }
}

The usage object shows token counts for the request. Your balance is deducted at the model's DA-per-million-token rate; the X-Balance-Available header in the response carries your remaining balance in micro-DA.

Streaming#

Set "stream": true to receive tokens as server-sent events. See Streaming for the full event format and code examples.

Errors#

Errors return a non-2xx status code with a JSON body. See Errors for the full status-code table and the exact response shape.