GPT-6 Luna API

POST Base URL: https://api.hiapi.ai /v1/responses

The OpenAI-compatible Responses endpoint is recommended for this model, while /v1/chat/completions remains available for compatibility. The same HiAPI API key works across enabled models; media models use /v1/tasks and a different request shape.

Model overview

Model ID	gpt-6-luna
Provider	OpenAI
Type	Text generation · Responses (default) and Chat Completions
Input / output	Text and images → text
Context window	1,050,000 tokens (up to 922,000 input per request)
Max output	128,000 tokens
Knowledge cutoff	2026-05-18
Reasoning efforts	none / low / medium / high / xhigh / max
Examples / Playground effort	medium
Pricing	Live HiAPI token rates

Integrate OpenAI GPT-6 Luna through HiAPI Responses, with Chat Completions also available, for summaries, information extraction, quick Q&A, and other high-volume tasks.

Production guidance

Request contract

Responses: use POST /v1/responses with an input array, stream=true, and store=false. A string input returns HTTP 400. Omit temperature, top_p, and max_output_tokens.
Chat Completions: POST /v1/chat/completions also works, streaming or non-streaming, with reasoning_effort. Omit temperature, top_p, max_tokens, and max_completion_tokens.
Use none, low, medium, high, xhigh, or max for reasoning.effort (Responses) or reasoning_effort (Chat). The default is medium.
To hit the prompt cache, send the same stable value in the prompt_cache_key body field and the session_id request header, and keep the prompt prefix identical. Cached tokens usually appear from the 2nd to 4th request; without both, no cache hit occurs.
The same HiAPI API key works across enabled models. Media models use /v1/tasks with a different request body.
Responses streaming: handle response.completed, response.incomplete, and response.failed separately.

Best suited for

Summaries and information extraction

Condense long documents and pull structured fields out of text or images at low cost.

inputtext

High-volume quick Q&A

Run focused, repetitive requests in volume, and pick a reasoning effort per task.

reasoning.effortinput

Request parameters

model string required

Use this exact public model ID.

example gpt-6-luna enum: gpt-6-luna

input array required

Message items. A plain string is rejected with HTTP 400. Text and input_image parts are supported. Replay the context needed for each turn.

stream boolean optional

Must be true on Responses. Process the response as SSE.

default true

store boolean optional

Must be false. Keep conversation state in your client.

default false

instructions string optional

Optional instructions for the response.

reasoning object optional

Reasoning configuration.

effort enum optional

Use none, low, medium (default), high, xhigh, or max.

example medium enum: nonelowmediumhighxhighmax

prompt_cache_key string optional

Stable session identifier for prompt cache hits. Send the same value in the session_id request header, and keep the prompt prefix identical.

tools array optional

Function tool definitions. Execute functions in your application and return their results.

tool_choice string | object optional

Select automatic or a specific function call.

text object optional

Output format settings.

API examples

POST https://api.hiapi.ai/v1/responses

# Read the streaming response as SSE events
# Replace YOUR_API_KEY with your account API key
curl -N -X POST "https://api.hiapi.ai/v1/responses" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-6-luna",
  "input": [
    {
      "type": "message",
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Summarize the three highest risks in this project plan."
        }
      ]
    }
  ],
  "stream": true,
  "store": false,
  "reasoning": {
    "effort": "medium"
  }
}'

import requests, json

payload = json.loads(r'''{
  "model": "gpt-6-luna",
  "input": [
    {
      "type": "message",
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Summarize the three highest risks in this project plan."
        }
      ]
    }
  ],
  "stream": true,
  "store": false,
  "reasoning": {
    "effort": "medium"
  }
}''')

with requests.post(
    "https://api.hiapi.ai/v1/responses",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
    stream=True,
) as response:
    response.raise_for_status()
    for line in response.iter_lines():
        if line:
            print(line.decode("utf-8"))

const payload = {
  "model": "gpt-6-luna",
  "input": [
    {
      "type": "message",
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Summarize the three highest risks in this project plan."
        }
      ]
    }
  ],
  "stream": true,
  "store": false,
  "reasoning": {
    "effort": "medium"
  }
};

const response = await fetch("https://api.hiapi.ai/v1/responses", {
  method: "POST",
  headers: { "Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json" },
  body: JSON.stringify(payload),
});
if (!response.ok) throw new Error(await response.text());
const decoder = new TextDecoder();
for await (const chunk of response.body) {
  process.stdout.write(decoder.decode(chunk, { stream: true }));
}
process.stdout.write(decoder.decode());