Zhipu AI (Z.ai)

GLM-5.1

Generally availableOpen weights200K contextReasoning

Summary

GLM-5.1 is an open-weight language model from Zhipu AI (Z.ai), released on 7 Apr 2026. It accepts text and generates text, with a 200K-token context window and up to 131K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $1 per million input tokens and $3.20 per million output tokens (Hugging Face Inference Providers), across 7 providers we track. It is scheduled for retirement on 20 Nov 2026.

Strong GLM coding model for agentic engineering, terminals, and repository generation

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperZhipu AI (Z.ai)
Release date7 Apr 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licensemit [Hugging Face]
Parameters754B [Hugging Face]
Context window200K (200,000 tokens) [models.dev]
Max output131K tokens [models.dev]
Knowledge cutoffApr 2025 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Retirement date20 Nov 2026 [OpenRouter]
Hugging Facezai-org/GLM-5.1 [Hugging Face]

GLM-5.1 API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Hugging Face Inference Providers
zai-org/GLM-5.1
$1$3.20$0.20203Kmodels.dev, 18 Nov 2026
SiliconFlow
zai-org/GLM-5.1
$1.19$3.74$0.60205Kmodels.dev, 18 Nov 2026
Novita AI
zai-org/glm-5.1
$1.38$4.40$0.26205Kmodels.dev, 18 Nov 2026
Z.ai API
glm-5.1
$1.40$4.40$0.26200Kmodels.dev, 18 Nov 2026
FriendliAI
zai-org/GLM-5.1
$1.40$4.40$0.26203Kmodels.dev, 18 Nov 2026
OpenRouter
z-ai/glm-5.1
$1.40$4.40$0.26203KOpenRouter, 18 Nov 2026
Vercel AI Gateway
zai/glm-5.1
$1.40$4.40$0.26203Kmodels.dev, 18 Nov 2026

Running GLM-5.1 locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)457 GB459 GB461 GB
Q8_0 (8-bit)801 GB803 GB805 GB
FP16 / BF16 (16-bit)1508 GB1509 GB1511 GB

At 4-bit with an 8K conversation, GLM-5.1 needs about 459 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of GLM-5.1?

GLM-5.1 has a context window of 200,000 tokens (200K) and can generate up to 131,072 tokens in a single response, according to models.dev.

How much does the GLM-5.1 API cost?

Through Z.ai API, GLM-5.1 costs $1.40 per million input tokens and $4.40 per million output tokens. The lowest listed price is $1 input / $3.20 output through Hugging Face Inference Providers. Prices last verified 18 Nov 2026.

Is GLM-5.1 open source?

GLM-5.1 is an open-weight model: its weights are published on Hugging Face as zai-org/GLM-5.1 under the mit license. Check the license terms before commercial use.

When was GLM-5.1 released?

Zhipu AI (Z.ai) released GLM-5.1 on 7 Apr 2026, according to models.dev.

Which providers offer GLM-5.1?

We track GLM-5.1 on 7 providers: Hugging Face Inference Providers, SiliconFlow, Novita AI, Z.ai API, FriendliAI, OpenRouter, Vercel AI Gateway.

How much VRAM does GLM-5.1 need?

About 459 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 803 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Kimi K2.6Moonshot AI20 Apr 2026262K$0.65$3.40Open
Qwen3.6 27BAlibaba (Qwen)22 Apr 2026262K$0.30$3.19Open
Kimi K2.7 CodeMoonshot AI12 Jun 2026262K$0.60$3.50Open
Qwen3.5 397B-A17BAlibaba (Qwen)15 Feb 2026262K$0.45$3Open
InklingThinkingmachines15 Jul 2026256K$1$4.05Open
Mistral Medium 3.5Mistral AI29 Apr 2026262K$1.50$7.50Open

Change history

  • Knowledge cutoff changed from Oct 2024 to Apr 2025
  • Knowledge cutoff changed from Apr 2025 to Oct 2024
  • Knowledge cutoff changed from Oct 2024 to Apr 2025
  • Knowledge cutoff changed from Apr 2025 to Oct 2024
  • Retirement date changed from none to 20 Nov 2026
  • OpenRouter price changed: input $1.33 → $1.40, output $4.18 → $4.40 per 1M tokens
  • OpenRouter price changed: input $1.40 → $1.33, output $4.40 → $4.18 per 1M tokens
  • Knowledge cutoff changed from Oct 2024 to Apr 2025
  • Knowledge cutoff changed from Apr 2025 to Oct 2024
  • OpenRouter price changed: input $0.97 → $1.40, output $3.04 → $4.40 per 1M tokens
  • OpenRouter price changed: input $1.40 → $0.97, output $4.40 → $3.04 per 1M tokens
  • Knowledge cutoff changed from Oct 2024 to Apr 2025
  • Knowledge cutoff changed from Apr 2025 to Oct 2024
  • Knowledge cutoff changed from Oct 2024 to Apr 2025
  • Knowledge cutoff changed from Apr 2025 to Oct 2024
  • OpenRouter price changed: input $0.97 → $1.40, output $3.04 → $4.40 per 1M tokens
  • Knowledge cutoff changed from Nov 2025 to Apr 2025
  • No longer listed on baseten
  • Knowledge cutoff changed from Apr 2025 to Nov 2025
  • OpenRouter price changed: input $1.33 → $0.97, output $4.18 → $3.04 per 1M tokens
  • OpenRouter price changed: input $0.97 → $1.33, output $3.04 → $4.18 per 1M tokens
  • OpenRouter price changed: input $1.40 → $0.97, output $4.40 → $3.04 per 1M tokens

Sources