GPT-5.6 Luna is designed for cost-sensitive, high-volume workloads. It roughly corresponds to the nano model tier used in earlier GPT-5 families. Reasoning.effort supports: none, low, medium (default), high, xhigh, and max.
One POST request. Get the result back directly — as an image, video, or JSON depending on the tool.
curl -X POST https://apiai.me/api/workflow/gpt-5-6-luna \
-H "X-API-Key: YOUR_API_KEY" \
-F "image=@input.jpg" \
-F "frequency_penalty=VALUE" \
-F "max_tokens=VALUE" \
-F "presence_penalty=VALUE" \
-F "PROMPT=VALUE" \
-F "temperature=VALUE" \
-F "top_p=VALUE"
--output result.json
Test this tool visually before writing any code. Upload an image, set parameters, and see the result live. When it looks right, copy the auto-generated curl command and paste it into your app.
Process hundreds of images at once without writing a loop. Upload a CSV with one row per item, set your parameters, and download the results as a ZIP when they're done.
| Name | Required | Description | Default / Options |
|---|---|---|---|
frequency_penalty |
optional | Reduce repetition of token sequences (-2 to 2) | — |
max_tokens |
optional | Maximum number of tokens to generate | — |
presence_penalty |
optional | Encourage discussion of new topics (-2 to 2) | — |
PROMPT |
required | Text prompt for the OpenAI model | — |
temperature |
optional | Sampling temperature (0-2). Higher = more creative, lower = more deterministic | — |
top_p |
optional | Nucleus sampling: cumulative probability cutoff (0-1) | — |
Get an API key, test GPT-5.6 Luna in the dashboard, and copy the curl command.