GPT-5.6 Luna Chat Completion

Call the lightweight GPT-5.6 Luna model for fast, cost-efficient text and streaming workloads through the PixMind API.

GPT-5.6 Luna is the lightweight route for high-volume text workloads. Its pricing separates standard input and output from cache reads and writes, including a long-context tier above 272K input tokens.

GPT-5.6 Luna through PixMind's OpenAI-compatible chat completions endpoint.

Provider

OpenAI

Model ID

gpt-5.6-luna

Endpoint

POST /api-platform/v1/chat/completions

Open model playground Create API key

Model notes

Keep the API key on your server and use streaming when the client needs incremental output.
The pricing tier is selected from the request's input-token count. Above 272K input tokens, the long-context tier applies to the entire request—not only the excess tokens. Cache reads and cache writes are billed independently.

Request parameters

Parameter	Type	Required	Description
`model`	string	Yes	Stable PixMind model ID. Use `gpt-5.6-luna`. Allowed values: `gpt-5.6-luna`
`messages`	array	Yes	OpenAI-compatible chat messages. Gemini user content may be a string or an array of text, image_url, and video_url blocks.
`max_tokens`	integer	No	Maximum number of completion tokens to generate. Default: `4096`
`temperature`	number	No	Sampling temperature for the response. Allowed values: `0`, `0.5`, `1`, `2` Default: `1`
`stream`	boolean	No	Return tokens incrementally when enabled. Allowed values: `true`, `false` Default: `false`

Request example

cURL

curl https://aihub-admin.aimix.pro/api-platform/v1/chat/completions \
  -H "Authorization: Bearer $PIXMIND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-5.6-luna",
  "messages": [
    {
      "role": "user",
      "content": "Draft three launch concepts for this product."
    }
  ],
  "stream": false
}'

JavaScript

const response = await fetch("https://aihub-admin.aimix.pro/api-platform/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${process.env.PIXMIND_API_KEY}`,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
  "model": "gpt-5.6-luna",
  "messages": [
    {
      "role": "user",
      "content": "Draft three launch concepts for this product."
    }
  ],
  "stream": false
})
});

const task = await response.json();

Accepted task response

Generation is asynchronous. Save taskId and poll GET /api-platform/v1/tasks/{taskId} until status is ready or failed.

200 OK

{
  "code": 1000,
  "data": {
    "id": "img_44160",
    "taskId": 44160,
    "type": "image",
    "model": "gpt-5.6-luna",
    "status": "processing"
  }
}

API pricing

Configuration	Price
Input · ≤272K input tokens	147.784 credits (~$0.16) / 1M tokens
Output · ≤272K input tokens	886.704 credits (~$0.94) / 1M tokens
Cache read · ≤272K input tokens	14.742 credits (~$0.02) / 1M tokens
Cache write · ≤272K input tokens	184.73 credits (~$0.20) / 1M tokens
Input · >272K input tokens	295.568 credits (~$0.32) / 1M tokens
Output · >272K input tokens	1330.056 credits (~$1.41) / 1M tokens
Cache read · >272K input tokens	29.484 credits (~$0.04) / 1M tokens
Cache write · >272K input tokens	369.46 credits (~$0.39) / 1M tokens

API pricing uses the apiPlatform role and is separate from PixMind Studio credits. The accepted task response is the final pricing snapshot.