ZhipuLLM
GLM 5.3 API
glm/glm-5.3GLM-5.3 for chat and tool-using workflows.
- 1.05M context
- Outils
- Reasoning
Lancez GLM 5.3 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": "glm/glm-5.3","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 GLM 5.3 with your account.
Usage and charge appear here after a reply.
Tarifs de GLM 5.3
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 GLM 5.3 sait faire
Z.ai describes GLM-5.3 as a post-trained update focused on complex coding and long-horizon tasks. See the manufacturer's description for native product details. Its hosted tools and native API controls are separate from the Hermes route.
Hermes lists glm/glm-5.3 with a 1,048,576-token context, tools and streaming, and does not list vision input. Check the selected channel's reasoning and structured-output flags, current status and token rates before use.
Cas d’usage
Work with code or documents
Evaluate results on representative tasks and allow context space for the response.
Build an agent workflow
Handle tool calls in your own application and validate outcomes.
Compare latency and quality
Test model choices on your actual prompts and output requirements.
Appelez GLM 5.3 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/completionswithglm/glm-5.3
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": "glm/glm-5.3",
"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 | glm/glm-5.3 |
| 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 GLM 5.3
Answers built from the model's catalog entry and the Hermes AI API contract.
Does the manufacturer's hosted agent come with the Hermes model?
No. Manufacturer product features are separate from this chat route. Consult the Hermes documentation for available request fields and tool behavior.
What is the GLM 5.3 API on Hermes AI?
GLM 5.3 by Zhipu is served through the OpenAI-compatible chat completions endpoint, https://api.hermes-ai.net/api/v1/chat/completions, with the model ID glm/glm-5.3.
What is the context window of GLM 5.3?
1,048,576 tokens, shared by the prompt and the output.
Does GLM 5.3 support vision, tools and JSON output?
Supported: Outils et la Reasoning. Not supported: Vision, JSON et la Audio. Streaming works with stream: true.
How is GLM 5.3 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 GLM 5.3?
Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and use your Hermes API key; send glm/glm-5.3 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 GLM 5.3?
Create one under Clés d’API in the dashboard with the chat:create scope, then add credits on the Billing page.