GLM 5.1

Refined post-training for coding and agentic engineering workflows.

zai-org/GLM-5.1-FP8

Copied

About

GLM-5.1 is Z.ai's next-generation flagship model built for agentic engineering, with stronger coding capabilities and sustained performance over long-horizon tasks with hundreds of iteration rounds. It's a 754B-parameter MoE model

API Usage
from openai import OpenAI

client = OpenAI(
    api_key="<YOUR_ZYPHRA_API_KEY>",
    base_url="https://api.zyphracloud.com/api/v1",
)

response = client.chat.completions.create(
    model="zai-org/GLM-5.1-FP8",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

Provider

Provider

Provider

Release Date

Release Date

Release Date

Model License

Model License

Model License

Model Architecture

Model Architecture

Model Architecture

Mixture-of-experts

Mixture-of-experts

Mixture-of-experts

Total parameters

Total parameters

Total parameters

Activated parameters

Activated parameters

Activated parameters

Context length

Context length

Context length

Input modality

Input modality

Input modality

Output modality

Output modality

Output modality

Input price

Input price

Input price

Cached input price

Cached input price

Cached input price

Output price

Output price

Output price

ZAI

ZAI

ZAI

MIT

MIT

MIT

Transformer

Transformer

Transformer

Yes

Yes

Yes

754B

754B

754B

40B

40B

40B

200k

200k

200k

Text

Text

Text

Text

Text

Text

$1.20

$1.20

$1.20

$0.20

$0.20

$0.20

$4.00

$4.00

$4.00

© 2026 Zyphra Technologies Inc. All rights reserved.

© 2026 Zyphra Technologies Inc. All rights reserved.