GLM 5.3

glm-5.3

Use the GLM 5.3 API for chat completions. Send conversation messages and add tools on routes that support tool calling. Build an assistant that can answer questions and coordinate application actions. Compare the available provider routes, request examples, and usage prices on OpenAny.

Published price: From $0.985 / 1M tokens
Billing unit: / 1M tokens
Context / Max output: — / 4.1K
Listed routes: 2

messagesThe conversation messages

Other parameters (19)

do_sampleWhether to enable sampling. When true, the model uses sampling-based generation.frequency_penaltyPenalty for repeated tokensmax_completion_tokensMaximum visible completion tokensmax_tokensMaximum completion tokensnNumber of choices to generatepresence_penaltyPenalty for previously used tokensreasoning_effortControls the reasoning effort level used by the model.request_idClient-provided request identifier for tracing and idempotency.response_formatFormat constraint for the responseseedSeed for deterministic samplingstopSequences that stop generationstreamWhether to stream the responsetemperatureSampling temperaturethinkingThinking configuration object for GLM reasoning behavior. eg: {"type": "disabled" }tool_choiceTool selection policy: string modes none, auto, or required, or an object selecting a specific tooltool_streamWhether to enable streaming output for tool calls.toolsTools available to the modeltop_pNucleus sampling probabilityuser_idEnd-user identifier associated with the request.

Result preview

Tencent · 3422ms

Response example. Run to see the actual response.

{
  "id": "ec57729c-75ab-4d58-bb16-24305e482df7",
  "model": "glm-5.3",
  "usage": {
    "total_tokens": 263,
    "prompt_tokens": 13,
    "completion_tokens": 250,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 213
    }
  },
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm your GLM model trained by Z.ai. How can I help you today? Feel free to ask any questions or share topics you'd like to discuss.",
        "reasoning_content": "Let me consider how to respond to this greeting effectively.\n\nThe user has initiated contact with a simple \"hello,\" which suggests they may be testing the waters or just starting the conversation. This calls for a warm and inviting response that encourages further interaction.\n\nI should acknowledge their greeting in a friendly way and make them feel welcome to share more about what they need help with. It would be good to keep the tone approachable and professional, while also being open to various types of questions they might have.\n\nSince they haven't specified any particular topic or question, I should keep my response flexible and inviting. Perhaps I could offer some guidance on what I can assist with, while leaving the door open for them to direct the conversation.\n\nThe response should be concise yet welcoming, making it easy for them to continue the dialogue if they wish. I want to strike a balance between being helpful and not overwhelming them with too much information.\n\nLet me craft a response that is warm, professional, and open-ended - something that makes them feel comfortable sharing more about what they're looking for."
      },
      "finish_reason": "stop"
    }
  ],
  "created": 1787113497,
  "openmodels_cost": 9944
}

Request example

POST /v1/chat/completions

curl 'https://api.openany.si/v1/chat/completions' \
  -H "Authorization: Bearer $OPENANY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "messages": [
    {
      "content": "hello",
      "role": "user"
    }
  ],
  "model": "glm-5.3",
  "route_mode": "balanced",
  "do_sample": true,
  "frequency_penalty": 0,
  "n": 1,
  "presence_penalty": 0,
  "stream": false,
  "temperature": 1,
  "tool_stream": false,
  "top_p": 1
}'

Model API questions

How do I call GLM 5.3 through OpenAny?

Use model ID glm-5.3 with an OpenAny key and the operation published in this model's API tab. The model API base is https://api.openany.si/v1. Confirm the protocol and request schema; model availability does not imply every OpenAI API operation is supported.

How is GLM 5.3 billed?

Compare the published rate and billing unit of the selected provider route. Input, output and cache token rates may differ. Image, audio and video models can use other units. Recorded usage determines the charge under that route's billing contract.

Are Community and Verified routes the same as an official publisher API?

No. Inspect the provider name and supply classification for the specific route. A marketplace listing or a supply label is not a claim of publisher endorsement, identical service or measured uptime. Different route prices may reflect different supply and conditions.

Where do these prices come from, and when were they updated?

Rates come from the provider routes in OpenAny's public model catalog, not an independent quote from the model publisher. The catalog does not supply a price update timestamp. A page or catalog snapshot date is not a price revision date. Compare supply, billing units, tiers and conditions; a lower listed rate alone does not establish equivalent service or explain the price difference.

Use GLM 5.3 with your agent

Inspect endpoint contracts and confirm availability and pricing before a paid call.