Model Marketplace

GLM

Copy success!
Try AIAdd to Compare

Overview

GLM-5.3-Prime is the high-speed variant of GLM-5.3, inheriting its full capabilities while achieving 1.5–2× the output TPS through inference acceleration. It delivers state-of-the-art coding and agentic performance among open-source models, supports 1M context and 128K output tokens, and can produce production-grade results end-to-end — along with emergent cybersecurity capabilities such as vulnerability discovery. Designed for latency-sensitive scenarios including real-time conversation, multi-turn agent orchestration, and streaming code generation.

Input

Text

Output

Text

Features

Prefix Completion

Enable Partial Mode when calling the Qwen API to make the model continue strictly from your provided prefix text.View docs

Function Calling

Use function calling to connect large language models with external tools and systems.View docs

Cache

Context Cache stores shared prefixes for long-context requests to reduce repeated computation, improve latency, and lower cost.View docs

Structured Outputs

Structured Outputs help ensure the model returns a JSON string in the expected format.View docs

Batches

Asynchronously process requests in batches to reduce costs.View docs

Web Search

Enable web search so the model can answer with real-time retrieved data.View docs

Fine-tuning

Train models on sample data to better adapt them to specific tasks.View docs

Pricing

  • Input
    $2.8Per 1M tokens
  • Output
    $8.8Per 1M tokens
  • Input(Implicit Cache)
    $0.56Per 1M tokens

Rate Limits & Context

  • Max Input
    1M
  • Max Output
    131K
  • Max Input (Thinking)
    1M
  • Max Output (Thinking)
    131K
  • Context
    1M
  • Max Reasoning
    131K
  • TPMTokens Per Minute
    2M
  • RPMRequests Per Minute
    10K

Built-in Tools

code_interpreterResponses API
web_extractorResponses API

API Reference

Call API
Copy success!
12345678910111213141516171819202122232425262728
from openai import OpenAI
import os

client = OpenAI(
    # If the environment variable is not set, replace it with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://maas.qwencloudapi.com/compatible-mode/v1",
)

messages = [{"role": "user", "content": "Who are you"}]
completion = client.chat.completions.create(
    model="glm-5.3-prime",  # You can replace this with another deep thinking models
    messages=messages,
    extra_body={"enable_thinking": True},
    stream=True
)
is_answering = False  # Indicates whether the response phase has started
print("\n" + "=" * 20 + "Thinking process" + "=" * 20)
for chunk in completion:
    delta = chunk.choices[0].delta
    if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None:
        if not is_answering:
            print(delta.reasoning_content, end="", flush=True)
    if hasattr(delta, "content") and delta.content:
        if not is_answering:
            print("\n" + "=" * 20 + "Full response" + "=" * 20)
            is_answering = True
        print(delta.content, end="", flush=True)