glm-5.2

Name: zai-org/glm-5.2
Brand: Z.ai
Price: 1.4 USD
Availability: InStock

Z.aiAdded Jul 12, 2026

Model idzai-org/glm-5.2

Z.ai's flagship for long, multi-step agent work. A 1M-token context built to stay reliable through long coding and agent sessions, and Z.ai's best open model on the multi-step benchmarks it reports.

Cost /1M tokens

$1.40input

$0.35cached

$4.40output

Context

1Mtokens

Live speed

149 tok/s · 0.38s to first token

Speed

Throughput users got on glm-5.2 with Keln API in the last 24 hours.

Latency

Time to first token users got on glm-5.2 with Keln API in the last 24 hours.

Capabilities

Input

Text

Tool calling

Yes

JSON output

Yes

Reasoning

Yes

Web search

With opt-in

Data retention

Zero

Use the API

Create an API key, save it to KELN_API_KEY, then call the endpoint below.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.keln.ai/v1/",
    api_key=os.environ.get("KELN_API_KEY"),
)

resp = client.chat.completions.create(
    model="zai-org/glm-5.2",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)