OpenAILLM
GPT-5.4 Pro API
openai/gpt-5.4-proGPT-5.4 Pro through the Hermes chat model catalog.
- 1.05M context
- Outils
- JSON
Lancez GPT-5.4 Pro dans le playground
Send a chat request with your account and see the exact token charge. Code needs an API key.
Paramètres
Aperçu de la requête
{"model": "openai/gpt-5.4-pro","messages": [],"stream": true,"max_tokens": 1024}Le playground web envoie ce corps avec votre session connectée. Depuis votre code, envoyez le même corps avec une clé d’API.
Résultat
Send a message to run GPT-5.4 Pro with your account.
Usage and charge appear here after a reply.
Tarifs de GPT-5.4 Pro
USD per 1M tokens. The tier is chosen by the prompt size of each request.
- 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.
- 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.
- 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.
Ce que GPT-5.4 Pro sait faire
OpenAI describes Pro as using more compute for difficult tasks and states its native offering is Responses API only. The Hermes route is separate and its compatibility should be tested. See the OpenAI model page for the native model's specifications and lifecycle. OpenAI product capabilities, hosted tools and endpoint support do not automatically establish behavior on the Hermes route.
The Hermes catalog lists openai/gpt-5.4-pro with a 1,050,000-token context. Vision is not listed in the current catalog; check the exact selected channel's tools, reasoning and structured-output flags because these may differ by route. Availability and pricing are shown separately.
Cas d’usage
Evaluate difficult reasoning tasks
Evaluate accuracy and latency with representative tasks.
Integrate with an application
Use the request fields and tool controls documented for the Hermes route.
Work with long inputs
Allow space for the response and other request tokens within the listed context.
Appelez GPT-5.4 Pro depuis votre code
Any OpenAI SDK works: set the base URL and your Hermes key.
- 1
Créez une clé d’API
In the dashboard, with the chat:create scope. Clés d’API - 2
Point your SDK at Hermes
Base URLhttps://api.hermes-ai.net/api/v1 - 3
Send a chat completion
POST /chat/completionswithopenai/gpt-5.4-pro
Exemples de code
Set HERMES_API_KEY in your environment.
export HERMES_API_KEY=your_api_keycurl https://api.hermes-ai.net/api/v1/chat/completions \
-H "Authorization: Bearer $HERMES_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5.4-pro",
"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.
| Champ | Type | Remarques |
|---|---|---|
| model | string | openai/gpt-5.4-pro |
| messages | array | OpenAI chat messages: system, user, assistant and tool roles; text and image_url parts. |
| stream | boolean | Server-sent events with a final usage chunk. |
| max_tokens | integer | Output cap; also sizes the credit reservation. |
| tools / tool_choice | array / object | Function tools only. |
| response_format | object | JSON mode and JSON schema where the model supports it. |
| temperature, top_p, stop, seed, reasoning_effort | Passed through unchanged. |
Réponse
| Champ | Remarques |
|---|---|
| choices[].message / delta | The OpenAI chat completion shape. |
| usage | prompt_tokens, completion_tokens and prompt_tokens_details.cached_tokens as reported by the model. |
| hermes.charged_micros | Exact charge in USD micro-units (JSON responses). Streams expose it on GET /api/v1/chat/requests. |
| x-hermes-request | Request id header, also used in the billing ledger. |
| error.code | Documented Hermes error code; branch on it, not on the message. |
FAQ de l’API GPT-5.4 Pro
Answers built from the model's catalog entry and the Hermes AI API contract.
Can I assume the native OpenAI API behaves identically here?
No. OpenAI's model documentation describes its own endpoints; consult the Hermes route and verify the selected variant before using a particular feature.
What is the GPT-5.4 Pro API on Hermes AI?
GPT-5.4 Pro 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-5.4-pro.
What is the context window of GPT-5.4 Pro?
1,050,000 tokens, shared by the prompt and the output.
Does GPT-5.4 Pro support vision, tools and JSON output?
Supported: Outils et la JSON. Not supported: Vision, Reasoning et la Audio. Streaming works with stream: true.
How is GPT-5.4 Pro 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-5.4 Pro?
Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and use your Hermes API key; send openai/gpt-5.4-pro as the model. Chat completions, streaming, tools and JSON output work unchanged.
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-5.4 Pro?
Create one under Clés d’API in the dashboard with the chat:create scope, then add credits on the Billing page.