本文へスキップ

OpenAILLM

GPT-5.6 Luna API

Model IDopenai/gpt-5.6-luna

GPT-5.6 Luna through the Hermes OpenAI-compatible chat endpoint.

  • 1.05M context
  • ツール
  • Vision
  • Reasoning
  • Saver channel

プレイグラウンドで GPT-5.6 Luna を実行

Send a chat request with your account and see the exact token charge. Code needs an API key.

パラメーター

モデル
model
openai/gpt-5.6-luna
messages[].content
messages[0].content
max_tokens
temperature

リクエストのプレビュー

{"model": "openai/gpt-5.6-luna","messages": [],"stream": true,"max_tokens": 1024}

Web Playground はサインイン中のセッションでこのボディを送信します。コードからは同じボディを API キーとともに送信してください。

結果

Send a message to run GPT-5.6 Luna with your account.

Usage and charge appear here after a reply.

GPT-5.6 Luna の料金

USD per 1M tokens. The tier is chosen by the prompt size of each request.

料金を読み込み中…
  1. ReserveWhen a request is accepted, Hermes reserves credits for the estimated prompt plus max_tokens of output (8,192 when you set none). Set max_tokens to keep the reservation small.
  2. SettleWhen the response finishes, the reservation is replaced by the exact charge from the usage the model reports: prompt tokens at the input rate, cached prompt tokens at the cache-read rate, completion tokens at the output rate. The remainder is released immediately.
  3. FailuresIf the model rejects the request nothing is charged. If a stream is interrupted after tokens were generated, the generated text is estimated and charged.

GPT-5.6 Luna のバリアントを比較

The saver channel is the same model on a lower-priority upstream route, with its own model ID and price.

VariantModel IDContext windowできること
Standardopenai/gpt-5.6-luna1,050,000 tokensツール, Vision, Reasoning
Saveropenai/gpt-5.6-luna-saver1,050,000 tokensツール, Vision, Reasoning

GPT-5.6 Luna でできること

OpenAI positions Luna for cost-sensitive, high-volume workloads and compares its role to the earlier nano tier. See the OpenAI model page for its native specifications and model guidance. OpenAI's hosted Responses tools and processing modes are separate from the Hermes chat route.

The Hermes catalog lists openai/gpt-5.6-luna and a saver channel. Both list a 1,050,000-token context, vision, reasoning, tools and streaming; structured outputs are not listed. The saver channel has its own route and price. Check current status and token rates for the exact model ID before a request.

ユースケース

  1. Classify and transform high-volume text

    Compare quality, latency and cost on representative inputs.

  2. Read images alongside text

    Supply supported image input when the task calls for visual analysis.

  3. Use tools in an application

    Handle function calls and validate outputs on the Hermes route.

コードから GPT-5.6 Luna を呼び出す

Any OpenAI SDK works: set the base URL and your Hermes key.

  1. 1

    API キーを作成

    In the dashboard, with the chat:create scope. API キー
  2. 2

    Point your SDK at Hermes

    Base URL https://api.hermes-ai.net/api/v1
  3. 3

    Send a chat completion

    POST /chat/completions with openai/gpt-5.6-luna

コード例

Set HERMES_API_KEY in your environment.

shell
export HERMES_API_KEY=your_api_key
Full chat API reference
curl https://api.hermes-ai.net/api/v1/chat/completions \
  -H "Authorization: Bearer $HERMES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.6-luna",
    "messages": [{"role": "user", "content": "Say hello in one sentence."}],
    "max_tokens": 200
  }'

Request

POST https://api.hermes-ai.net/api/v1/chat/completions API key with the chat:create scope, or your signed-in session.

フィールド型備考
modelstringopenai/gpt-5.6-luna
messagesarrayOpenAI chat messages: system, user, assistant and tool roles; text and image_url parts.
streambooleanServer-sent events with a final usage chunk.
max_tokensintegerOutput cap; also sizes the credit reservation.
tools / tool_choicearray / objectFunction tools only.
response_formatobjectJSON mode and JSON schema where the model supports it.
temperature, top_p, stop, seed, reasoning_effortPassed through unchanged.

レスポンス

フィールド備考
choices[].message / deltaThe OpenAI chat completion shape.
usageprompt_tokens, completion_tokens and prompt_tokens_details.cached_tokens as reported by the model.
hermes.charged_microsExact charge in USD micro-units (JSON responses). Streams expose it on GET /api/v1/chat/requests.
x-hermes-requestRequest id header, also used in the billing ledger.
error.codeDocumented Hermes error code; branch on it, not on the message.

GPT-5.6 Luna API のよくある質問

Answers built from the model's catalog entry and the Hermes AI API contract.

Is the saver channel the same endpoint and price?

It uses a separate Hermes model ID and pricing. Check the displayed availability and rate before choosing a channel.

Are OpenAI's hosted Responses tools included?

Not automatically. Their manufacturer documentation describes OpenAI's Responses API; Hermes exposes its own OpenAI-compatible chat contract.

What is the GPT-5.6 Luna API on Hermes AI?

GPT-5.6 Luna by OpenAI is served through the OpenAI-compatible chat completions endpoint, https://api.hermes-ai.net/api/v1/chat/completions, with the model ID openai/gpt-5.6-luna.

What is the context window of GPT-5.6 Luna?

1,050,000 tokens, shared by the prompt and the output.

Does GPT-5.6 Luna support vision, tools and JSON output?

Supported: ツール, Vision および Reasoning. Not supported: JSON および オーディオ. Streaming works with stream: true.

How is GPT-5.6 Luna billed?

Per token, from prepaid credits. When a request is accepted, credits are reserved for the estimated prompt plus max_tokens of output (8,192 when you set none); when it finishes, the exact charge is taken from the usage the model reports and the rest is released. A rejected request is not charged. Rates are in the pricing table.

Can I use the OpenAI SDK with GPT-5.6 Luna?

Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and use your Hermes API key; send openai/gpt-5.6-luna as the model. Chat completions, streaming, tools and JSON output work unchanged.

What is the GPT-5.6 Luna saver channel?

The same model on a lower-priority upstream route, with its own model ID (openai/gpt-5.6-luna-saver) and its own price. Pick it in the variant switch on this page.

What happens when I hit a rate limit?

Too many requests per minute return 429 RATE_LIMITED and too many in flight return 429 CONCURRENCY_LIMITED. If the model provider rate limits, you get 429 UPSTREAM_RATE_LIMITED and nothing is charged. Retry with backoff.

How do I get an API key for GPT-5.6 Luna?

Create one under API キー in the dashboard with the chat:create scope, then add credits on the Billing page.