Model by Zhipu AI (Z.ai)

GLM 5.1

GLM 5.1 is Zhipu's open-weight coding model, tuned for long-running agent tasks, for people who want MIT-licensed weights or a cheap hosted API.

Checked 2026-11-05

GLM 5.1 is Zhipu's open-weight coding model, tuned for long-running agent tasks, for people who want MIT-licensed weights or a cheap hosted API. The Hugging Face card gives 754 billion parameters, an MIT licence, and serving support in recent SGLang, vLLM, xLLM, Transformers and KTransformers. It states no context length, and gives no active-parameter count or hardware needs. OpenRouter lists it from 7 April 2026 with a context of 204,800 tokens and text only. Z.ai's pricing page matches OpenRouter at $1.40 per million input tokens and $4.40 per million output tokens, with cached input at $0.26, as listed on 5 November 2026. The catch is that it is no longer the newest: Z.ai's page also lists GLM-5.2 and GLM-5.3 at the same price, plus cheaper Flash and FlashX versions. The card's benchmark table is partly self-reported, and shows 5.1 behind some rivals on HLE and GPQA-Diamond. Figures come from the Hugging Face card, Z.ai's pricing page and the OpenRouter model list. We have not run it ourselves. We would try GLM 5.3 first and keep 5.1 as a fallback.

Mentioned here

  • GLM 5.2

    GLM 5.2 is Z.ai's large reasoning model for long agent runs and project-level coding, and it suits teams that want open weights with a very long context.

    • Open weights

    Zhipu AI (Z.ai), 1M context, $0.01 in / 1M

  • GLM 5.3

    GLM 5.3 is an open-weights model from Z.ai, released 2026-08-18, with a 1,048,576-token context and text-only input.

    • Open weights

    Zhipu AI (Z.ai), 1M context, $0.07 in / 1M

  • GLM 5.3 Flash

    GLM 5.3 Flash is a very low-cost open model from Z.ai, released 2026-08-26 under the MIT licence, with a 1,048,576-token context and text, image and video input.

    • Open weights

    Zhipu AI (Z.ai), 1M context, $0.15 in / 1M

  • Z.AI

    Z.ai sells the GLM model family through its open platform API, and it suits developers who want GLM 5.3 straight from the maker, with free small models for testing.

    • Model / inference API
    • OpenAI compatible

  • OpenRouter

    OpenRouter routes more than 600 models through one API key.

    • Model gateway (router)
    • OpenAI compatible

Questions

What is the context window of GLM 5.1?

204,800 tokens, with up to 131,072 tokens of output.

How much does GLM 5.1 cost?

$1.4 per million input tokens and $4.4 per million output tokens, checked 31 October 2026.

Can I run GLM 5.1 on my own hardware?

Yes, the weights are published under the MIT licence. They are on huggingface.co.

Who makes GLM 5.1?

Zhipu AI (Z.ai) makes it, and released it on 7 April 2026.

Reviews

Loading reviews…

Write a review

Your rating

Up to 1000 characters. Stars alone are enough.

Similar

  • GLM 5.3 FlashX

    GLM 5.3 FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash.

    • Closed

    Zhipu AI (Z.ai), 1M context, $0.37 in / 1M

  • GLM 5.3 Prime

    GLM 5.3 Prime is the high-speed variant of Z.ai's GLM-5.3.

    • Closed

    Zhipu AI (Z.ai), 1M context, $2.80 in / 1M