GLM 5

Chat Completions

glm-5

Z.ai|Created Feb 11, 2026|202.8k context

Chat Completions

GLM-5 is the flagship open-source foundation model from Z.ai, specifically designed for advanced systems engineering and handling long-term agent workflows. Tailored for skilled developers, it provides production-level performance on extensive programming tasks, matching up to the top proprietary models. Thanks to its sophisticated agent planning, robust backend reasoning, and iterative self-improvement, GLM-5 goes beyond simple code generation to enable comprehensive system creation and autonomous operation.

Overview Specifications Activity Performance Uptime Examples API Reference

Compare

Pricing-50%

Pay-as-you-go rates for this model. More details can be found here.

Input Tokens (1M)

$0.40

Cached Input Tokens (1M)

$0.08

Output Tokens (1M)

$1.28

Capabilities

Input Modalities

Text

Output Modalities

Text

Supported Parameters

Available parameters for API requests

Frequency PenaltyLogit BiasMax Completion TokensPresence PenaltyResponse FormatReasoning EffortStopTemperatureTop PTool ChoiceToolsLogprobsParallel Tool CallsPrediction

Usage Analytics

Token usage of this model on our platform

Throughput

Time-To-First-Token (TTFT)

Code Example

Example code for using this model through our API with Python (OpenAI SDK) or cURL. Replace placeholders with your API key and model ID.

Basic request example. Ensure API key permissions. For more details, see our documentation.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.naga.ac/v1",
    api_key="YOUR_API_KEY",
)

resp = client.chat.completions.create(
    model="glm-5",
    messages=[
        {"role": "user", "content": "What's 2+2?"}
    ],
    temperature=0.2,
)
print(resp.choices[0].message.content)