Zhipu AIText APIOnline

GLM-5.3

Zhipu GLM-5.3 text model, available through an OpenAI-compatible Chat Completions endpoint.

Use in your agent

API access

Endpoint

POST /v1/chat/completions

Base URL

https://api.hiapi.ai

OpenAI Chat Completions compatible. Use one HiAPI key across all available models.

Input price

8,800 Credits

/ 1M tokens

Output price

30,800 Credits

/ 1M tokens

Context

context window

Max output

output tokens

Try GLM-5.3

Ask a question to stream the answer and inspect token usage, latency, and estimated cost.

GLM-5.3 API Quickstart

Call GLM-5.3 with the OpenAI-compatible Chat Completions format. Copy a ready-to-use cURL, Python, or Node.js example below.

Code Example

API Endpoint:/v1/chat/completions

curl -X POST "https://api.hiapi.ai/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "glm-5.3",
  "stream": false,
  "messages": [
    {
      "role": "user",
      "content": "请用三句话解释 HTTP 缓存。"
    }
  ]
}'

Tip: Replace YOUR_API_KEY with your actual API key from the API Keys page.

Compatible with the OpenAI Chat Completions format. Set the base URL, API key, and model name to get started.

GLM-5.3 full API documentation Manage API keysUse the same HiAPI key across all available models.

GLM-5.3 API Pricing

Billing follows the input, output, and cache token categories actually reported in usage. All prices below are shown per 1 million tokens.

Input tokens: 8,800 Credits/ 1M tokens
Output tokens: 30,800 Credits/ 1M tokens

GLM-5.3 Model Specifications

These specifications reflect the current public HiAPI text request contract. Undisclosed capabilities are not inferred by the page.

Streaming: Supported
Tool calling: Supported
Structured JSON: Supported
Reasoning: Not disclosed
Input modalities: text
Output modalities: text
Reasoning efforts: -
Max output: -

About GLM-5.3

Zhipu GLM-5.3 text model, available through an OpenAI-compatible Chat Completions endpoint.

HiAPI exposes this model through /v1/chat/completions. Test prompts and parameters in the Playground, then use the same HiAPI API key in your server application.

Provider: Zhipu AI
Endpoint: /v1/chat/completions
Context window: -
Released: 2026-08-14

How to Use GLM-5.3

The Playground and API share the same model ID, so three steps take a tested prompt into production.

Step 1
Validate online
Test the system prompt, temperature, and output length in the Playground.
Step 2
Manage API keys
View an existing key or create another after signing in; one key works across all available models.
Step 3
Integrate your server
Send requests to /v1/chat/completions and track cost with the usage object.

Need to compare models and billing tiers?View live pricing for all models

Frequently asked questions

What is GLM-5.3?

GLM-5.3 is a Zhipu AI text model. HiAPI exposes it through an OpenAI-compatible Chat Completions endpoint for text input and text output.

Which endpoint and model ID should I use for GLM-5.3?

Send POST requests to /v1/chat/completions and set model to glm-5.3. Image, video, and audio models use the separate asynchronous /v1/tasks protocol.

Does GLM-5.3 support streaming, JSON Mode, and function tools?

Yes. Set stream=true for SSE; use response_format.type=json_object for JSON Mode; and use tools with tool_choice for OpenAI-compatible function calling. After executing a tool, continue with the original assistant.tool_calls and a matching role=tool message.

Does GLM-5.3 support image input or the Responses API?

The current HiAPI public integration exposes text Chat Completions only. Image input and the Responses API are not part of this integration. Responses may include reasoning_content, but no user-selectable reasoning effort parameter is exposed.

How is GLM-5.3 billed?

HiAPI bills actual input and output tokens; cached-read tokens are reported separately in usage when present. Use the API response and HiAPI call logs as the source of truth for final usage and charges.