GLM-5
Summary
GLM-5 is an open-weight language model from Zhipu AI (Z.ai), released on 12 Feb 2026. It accepts text and generates text, with a 205K-token context window and up to 131K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.95 per million input tokens and $2.55 per million output tokens (SiliconFlow), across 7 providers we track.
General GLM flagship for coding, analysis, and tool-heavy engineering workflows
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Zhipu AI (Z.ai) |
|---|---|
| Release date | 12 Feb 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | mit [Hugging Face] |
| Parameters | 754B [Hugging Face] |
| Context window | 205K (204,800 tokens) [models.dev] |
| Max output | 131K tokens [models.dev] |
| Knowledge cutoff | Apr 2025 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Hugging Face | zai-org/GLM-5 [Hugging Face] |
GLM-5 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| SiliconFlow zai-org/GLM-5 | $0.95 | $2.55 | $0.20 | 205K | models.dev, 18 Nov 2026 |
| Z.ai API glm-5 | $1 | $3.20 | $0.20 | 205K | models.dev, 18 Nov 2026 |
| Amazon Bedrock zai.glm-5 | $1 | $3.20 | – | 203K | models.dev, 18 Nov 2026 |
| Hugging Face Inference Providers zai-org/GLM-5 | $1 | $3.20 | $0.20 | 203K | models.dev, 18 Nov 2026 |
| Novita AI zai-org/glm-5 | $1 | $3.20 | $0.20 | 203K | models.dev, 18 Nov 2026 |
| OpenRouter z-ai/glm-5 | $1 | $3.20 | $0.20 | 203K | OpenRouter, 18 Nov 2026 |
| Vercel AI Gateway zai/glm-5 | $1 | $3.20 | – | 203K | models.dev, 18 Nov 2026 |
Running GLM-5 locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 457 GB | 459 GB | 461 GB |
| Q8_0 (8-bit) | 801 GB | 803 GB | 805 GB |
| FP16 / BF16 (16-bit) | 1508 GB | 1509 GB | 1511 GB |
At 4-bit with an 8K conversation, GLM-5 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?
GLM-5 has a context window of 204,800 tokens (205K) and can generate up to 131,072 tokens in a single response, according to models.dev.
How much does the GLM-5 API cost?
Through Z.ai API, GLM-5 costs $1 per million input tokens and $3.20 per million output tokens. The lowest listed price is $0.95 input / $2.55 output through SiliconFlow. Prices last verified 18 Nov 2026.
Is GLM-5 open source?
GLM-5 is an open-weight model: its weights are published on Hugging Face as zai-org/GLM-5 under the mit license. Check the license terms before commercial use.
When was GLM-5 released?
Zhipu AI (Z.ai) released GLM-5 on 12 Feb 2026, according to models.dev.
Which providers offer GLM-5?
We track GLM-5 on 7 providers: SiliconFlow, Z.ai API, Amazon Bedrock, Hugging Face Inference Providers, Novita AI, OpenRouter, Vercel AI Gateway.
How much VRAM does GLM-5 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.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Qwen3.5 397B-A17B | Alibaba (Qwen) | 15 Feb 2026 | 262K | $0.45 | $3 | Open |
| Kimi K2.5 | Moonshot AI | 27 Jan 2026 | 262K | $0.45 | $2.25 | Open |
| Qwen3.6 27B | Alibaba (Qwen) | 22 Apr 2026 | 262K | $0.30 | $3.19 | Open |
| Kimi K2.6 | Moonshot AI | 20 Apr 2026 | 262K | $0.65 | $3.40 | Open |
| Inkling | Thinkingmachines | 15 Jul 2026 | 256K | $1 | $4.05 | Open |
| Mistral Medium 3.5 | Mistral AI | 29 Apr 2026 | 262K | $1.50 | $7.50 | Open |
Change history
- Knowledge cutoff changed from Dec 2025 to Apr 2025
- Knowledge cutoff changed from Apr 2025 to Dec 2025
- Knowledge cutoff changed from Dec 2025 to Apr 2025
- Knowledge cutoff changed from Apr 2025 to Dec 2025
- Knowledge cutoff changed from Dec 2025 to Apr 2025
- Knowledge cutoff changed from Apr 2025 to Dec 2025
- Knowledge cutoff changed from Dec 2025 to Apr 2025
- Knowledge cutoff changed from Apr 2025 to Dec 2025
- Knowledge cutoff changed from Dec 2025 to Apr 2025
- Knowledge cutoff changed from Apr 2025 to Dec 2025
- Knowledge cutoff changed from Dec 2025 to Apr 2025
- Knowledge cutoff changed from Apr 2025 to Dec 2025
- Knowledge cutoff changed from Jan 2026 to Apr 2025
- Knowledge cutoff changed from Dec 2025 to Jan 2026
- OpenRouter price changed: input $0.60 → $1, output $1.92 → $3.20 per 1M tokens
- Knowledge cutoff changed from Jan 2026 to Dec 2025
- No longer listed on baseten
- OpenRouter price changed: input $1 → $0.60, output $3.20 → $1.92 per 1M tokens
- Knowledge cutoff changed from Dec 2025 to Jan 2026
- OpenRouter price changed: input $0.60 → $1, output $1.92 → $3.20 per 1M tokens
Sources
- https://openrouter.ai/z-ai/glm-5
- https://github.com/sst/models.dev/blob/dev/providers/zai/models/glm-5.toml
- https://huggingface.co/zai-org/GLM-5
- https://github.com/sst/models.dev/blob/dev/providers/siliconflow/models/zai-org/GLM-5.toml
- https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/zai.glm-5.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/zai-org/GLM-5.toml
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/zai-org/glm-5.toml
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/zai/glm-5.toml