OpenAI GPT 6 Luna API: AI مدل‌ها

Access GPT 6 Luna API through Muapi at OpenAI rates: $0.10/M input, $0.01/M cached input, $0.125/M cache writes, $0.50/M output. Async and streaming available.

Interactive model controls

GPT 6 Luna is designed for fast, high-volume text generation and focused reasoning. Official token pricing: $0.10/M input, $0.01/M cached input, $0.125/M cache writes, $0.50/M output.

📝

نمای کلی

مدل‌ها

GPT 6 Luna is an OpenAI model available through Muapi for fast, high-volume text generation and focused reasoning. Submit a prompt with an optional system prompt through the asynchronous API or stream the response token by token. Official standard rates per million tokens are $0.10 input, $0.01 cached input, $0.125 cache writes, and $0.50 output. Prompts above 272,000 input tokens use OpenAI long-context rates.

1GPT 6 Luna works well for fast, high-volume text generation and focused reasoning.

2Build chat interfaces with the streaming endpoint or background jobs with the async endpoint.

💰

قیمت‌گذاری و ارزش

تحلیل هزینه

ارائه‌دهنده	هزینه	یادداشت‌ها
Muapi	$0.10/M input, $0.01/M cached input, $0.125/M cache writes, $0.50/M output	OpenAI official standard rates. Long-context rates above 272,000 input tokens: $0.20/$0.02/$0.25/$0.75 per million input/cached/cache-write/output tokens.

Muapi$0.10/M input, $0.01/M cached input, $0.125/M cache writes, $0.50/M output

OpenAI official standard rates. Long-context rates above 272,000 input tokens: $0.20/$0.02/$0.25/$0.75 per million input/cached/cache-write/output tokens.

** مدل‌ها。

⚙️

مشخصات فنی

طرح پیکربندی

پارامتر	نوع	توضیحات	پیش‌فرض
پرامپت (دستور متنی)	string	تنظیم پارامتر The user message or instruction. جهت هدایت دقیق فرآیند تولید مدل.	`Summarize this article in three bullet points.`
پرامپت سیستمی	string	تنظیم پارامتر Optional system-level instruction to guide model behavior. جهت هدایت دقیق فرآیند تولید مدل.	`You are an expert tutor.`

پرامپت (دستور متنی)string

تنظیم پارامتر The user message or instruction. جهت هدایت دقیق فرآیند تولید مدل.

مقدار پیش‌فرضSummarize this article in three bullet points.

پرامپت سیستمیstring

تنظیم پارامتر Optional system-level instruction to guide model behavior. جهت هدایت دقیق فرآیند تولید مدل.

مقدار پیش‌فرضYou are an expert tutor.

📖

راهنمای پیاده‌سازی

مستندات توسعه‌دهندگان

Standard (Async)

POST /api/v1/gpt-6-luna — returns a request_id; poll /api/v1/predictions/{id}/result.

Streaming (SSE)

POST /api/v1/gpt-6-luna/stream — returns text chunks as Server-Sent Events, ending with data: [DONE].

cURL Example

curl -X POST "https://api.muapi.ai/api/v1/gpt-6-luna" \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Explain how to design a reliable queue-based service.","system_prompt":"You are a concise senior engineer."}'

❓

پرسش‌های متداول

سوالات پرتکرار

What is GPT 6 Luna?

GPT 6 Luna is an OpenAI model available through Muapi for fast, high-volume text generation and focused reasoning.

How do I call the GPT 6 Luna API?

Submit a prompt to `/api/v1/gpt-6-luna` and poll the returned request ID, or use `/api/v1/gpt-6-luna/stream` for SSE.

Can I provide a system prompt?

Yes. Pass an optional `system_prompt` to guide the response.

How is GPT 6 Luna billed?

Official standard rates per million tokens: $0.10 input, $0.01 cached input, $0.125 cache writes, and $0.50 output. For prompts above 272,000 input tokens, long-context rates are $0.20 input, $0.02 cached input, $0.25 cache writes, and $0.75 output.

Does it support streaming?

Yes. Use `/api/v1/gpt-6-luna/stream` for a Server-Sent Events response.