OpenAI GPT 6 Luna API: AI大規模言語モデル

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.

📝

概要

このモデルについて

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.

💰

料金と価値

コスト分析

プロバイダー	費用	備考
Muapi	$0.10/M 入力, $0.01/M cached 入力, $0.125/M cache writes, $0.50/M 出力	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 入力, $0.01/M cached 入力, $0.125/M cache writes, $0.50/M 出力

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.

** 競合サービスの料金は類似のモデル構成および利用ティアに基づいて算出された推定値です。

⚙️

技術詳細

設定スキーマ

パラメータ	型	説明	デフォルト
プロンプト	string	生成プロセスを適切に制御するためのパラメータ設定（The user message or instruction.）。	`Summarize this article in three bullet points.`
System プロンプト	string	生成プロセスを適切に制御するためのパラメータ設定（Optional system-level instruction to guide model b）。	`You are an expert tutor.`

プロンプトstring

生成プロセスを適切に制御するためのパラメータ設定（The user message or instruction.）。

デフォルト値Summarize this article in three bullet points.

System プロンプトstring

生成プロセスを適切に制御するためのパラメータ設定（Optional system-level instruction to guide model b）。

デフォルト値You are an expert tutor.

📖

実装ガイド

開発者ドキュメント

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."}'

❓

よくある質問

FAQ

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.