# GLM-5

GLM-5 是 Z.ai 的 AI 模型，权重开放，于 2026-02-12 发布。 上下文窗口为202,752 token。 最大输出为131,072 token。 每百万 token 的价格为：输入 $1.00，输出 $3.20。

- 开发商: Z.ai
- Id: zai-org/glm-5
- 据报道: 2026-06-21T18:57:49.000Z
- 已发布: 2026-02-12T00:00:00.000Z
- 发现: 2026-09-17T00:11:02.202Z
  - [参考链接](https://models.dev/#glm-5)
- 状态: 已发布
- 权重版本: 2026-02-11
  - [参考链接](https://huggingface.co/api/models/zai-org/GLM-5/paths-info/c183ef8c61faee82855eca1ed9bb3a9a7ce3b0b2)
- 规范地址: https://alexgetman.com/zh/models/z-ai/glm-5-803/

## 常见问题

### GLM-5 的上下文窗口有多大？

上下文窗口为202,752 token。 最大输出为131,072 token。

### GLM-5 的价格是多少？

每百万 token 的价格为：输入 $1.00，输出 $3.20。 缓存输入价格为每百万 token $0.20。

### GLM-5 的权重是否开放？

是的，Z.ai 已公开权重。

### GLM-5 何时发布？

2026-02-12。

## 时间线

- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @kaiyux](https://github.com/NVIDIA/TensorRT-LLM/pull/21019)
> - `modeling_glm5_next_vision.py`: the GLM-5 input processor takes the prefix tokenization cache (the fourth commit). Before, it tokenized every text prompt in full and ignored `enable_tokenization_cache`.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @moraxu](https://github.com/NVIDIA/TensorRT-LLM/pull/22136)
> class is registered for both `DeepseekV3ForCausalLM` and `DeepseekV32ForCausalLM`; GLM-5 (`GlmMoeDsaForCausalLM`) and Mistral Large 3 subclass it, so exact-class matching excludes them. Kimi K2 declares `DeepseekV3ForCausalLM`
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · ROCm/ATOM · @whx-sjtu](https://github.com/ROCm/ATOM/pull/3318)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · ai-dynamo/dynamo · @indrajit96](https://github.com/ai-dynamo/dynamo/pull/18363)
> for any DSA model (including DeepSeek V3.2 and GLM-5), or matching `flashmla_kv`/`trtllm` kernels on K3.1's sharded DCP path. Kernels SGLang has not resolved at CLI
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · ai-dynamo/frontend-crates · @dundysm](https://github.com/ai-dynamo/frontend-crates/pull/600)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]](https://github.com/anomalyco/models.dev/pull/13561)
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · maximhq/bifrost · @mickgvirtu](https://github.com/maximhq/bifrost/pull/4593)
> is not `schemas.Anthropic`, and the served model -- `glm-5`, `Kimi-K2`, ... -- is neither opus-4.8 nor Fable), so Claude Code's per-turn reminders were hoisted every
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · milabench/milabench · @bouthilx](https://github.com/milabench/milabench/pull/65)
> - GLM-5: layout check before launch, loss from the last stage, checkpoint timing and checksums, crash cleanup; `benchmarks/megatron/dev.yaml`, `scripts/trillium/glm/`.
- 2026-11-13T19:01:50.882Z · [GitHub search · Z.ai · pulls · smg-project/smg · @hello-alexmcc](https://github.com/smg-project/smg/pull/6229)
> Atria-Dawn, `glm`, beside Atria-Dawn-Preview: the template writes the GLM-5 shape (`[gMASK]<sop>`, a reasoning-effort system turn, `<|system|>` / `<|user|>` / `<|assistant|>` / `<|observation|>` turns), the tools

## 参考链接

- [vertex-model-garden](https://console.cloud.google.com/vertex-ai/publishers/zai-org/model-garden/glm-5)
- [review](https://docs.z.ai/api-reference/llm/chat-completion)
- [zai-pricing](https://docs.z.ai/guides/overview/pricing)
- [GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @kaiyux](https://github.com/NVIDIA/TensorRT-LLM/pull/21019)
- [GitHub search · Z.ai · pulls · NVIDIA/TensorRT-LLM · @moraxu](https://github.com/NVIDIA/TensorRT-LLM/pull/22136)
- [GitHub search · Z.ai · pulls · ROCm/ATOM · @whx-sjtu](https://github.com/ROCm/ATOM/pull/3318)
- [GitHub search · Z.ai · pulls · ai-dynamo/dynamo · @indrajit96](https://github.com/ai-dynamo/dynamo/pull/18363)
- [GitHub search · Z.ai · pulls · ai-dynamo/frontend-crates · @dundysm](https://github.com/ai-dynamo/frontend-crates/pull/600)
- [GitHub search · Z.ai · pulls · anomalyco/models.dev · @models-dev-automation[bot]](https://github.com/anomalyco/models.dev/pull/13561)
- [GitHub search · Z.ai · pulls · maximhq/bifrost · @mickgvirtu](https://github.com/maximhq/bifrost/pull/4593)
- [GitHub search · Z.ai · pulls · milabench/milabench · @bouthilx](https://github.com/milabench/milabench/pull/65)
- [GitHub search · Z.ai · pulls · smg-project/smg · @hello-alexmcc](https://github.com/smg-project/smg/pull/6229)
- [hf-author-artifacts:zai-org](https://huggingface.co/api/models/zai-org/GLM-5/paths-info/c183ef8c61faee82855eca1ed9bb3a9a7ce3b0b2)
- [huggingface-router](https://huggingface.co/zai-org/GLM-5)
- [models-dev](https://models.dev/#glm-5)

## 信号