GLM-5.2
Summary
GLM-5.2 is an open-weight language model from Zhipu AI (Z.ai), released on 13 Jun 2026. It accepts text and generates text, with a 1M-token context window and up to 131K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.75 per million input tokens and $2.40 per million output tokens (DeepInfra), across 14 providers we track.
Open flagship GLM for long-horizon coding agents and million-token context work
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Zhipu AI (Z.ai) |
|---|---|
| Release date | 13 Jun 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | mit [Hugging Face] |
| Parameters | 753B [Hugging Face] |
| Context window | 1M (1,000,000 tokens) [models.dev] |
| Max output | 131K tokens [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | zai-org/GLM-5.2 [Hugging Face] |
GLM-5.2 API pricing by provider
USD per million tokens. Sorted by input price.
Running GLM-5.2 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 | 458 GB | 460 GB |
| Q8_0 (8-bit) | 800 GB | 802 GB | 804 GB |
| FP16 / BF16 (16-bit) | 1507 GB | 1508 GB | 1510 GB |
At 4-bit with an 8K conversation, GLM-5.2 needs about 458 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-5.2?
GLM-5.2 has a context window of 1,000,000 tokens (1M) and can generate up to 131,072 tokens in a single response, according to models.dev.
How much does the GLM-5.2 API cost?
Through Alibaba Cloud Model Studio, GLM-5.2 costs $1.40 per million input tokens and $4.40 per million output tokens. The lowest listed price is $0.75 input / $2.40 output through DeepInfra. Prices last verified 18 Nov 2026.
Is GLM-5.2 open source?
GLM-5.2 is an open-weight model: its weights are published on Hugging Face as zai-org/GLM-5.2 under the mit license. Check the license terms before commercial use.
When was GLM-5.2 released?
Zhipu AI (Z.ai) released GLM-5.2 on 13 Jun 2026, according to models.dev.
Which providers offer GLM-5.2?
We track GLM-5.2 on 14 providers: OpenRouter, DeepInfra, SiliconFlow, Alibaba Cloud Model Studio, Z.ai API, Databricks, Google Vertex AI, Nebius AI Studio, Novita AI, FriendliAI, Together AI, Baseten, Hugging Face Inference Providers, Vercel AI Gateway.
How much VRAM does GLM-5.2 need?
About 458 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 802 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 |
|---|---|---|---|---|---|---|
| Nemotron 3 Ultra | NVIDIA | 4 Jun 2026 | 1M | $0.50 | $2.20 | Open |
| Macaron V1 Venti | Mindlab | 21 Jul 2026 | 1M | $0.82 | $2.48 | Open |
| MiniMax-M3 | MiniMax | 1 Jun 2026 | 1M | $0.28 | $1.10 | Open |
| LongCat-2.0 | Meituan | 30 Jun 2026 | 1M | $0.30 | $1.20 | Open |
| Inkling Small | Thinkingmachines | 30 Jul 2026 | 1M | $0.45 | $1.20 | Open |
| Tencent Hy4 Preview | Tencent (Hunyuan) | 28 Aug 2026 | 1M | $0.83 | $2.50 | Open |
Change history
- OpenRouter price changed: input $0.0075 → $0.007, output $6.80 → $6.80 per 1M tokens
- OpenRouter price changed: input $0.006 → $0.0075, output $6.80 → $6.80 per 1M tokens
- No longer listed on cloudflare-workers-ai
- Vercel AI Gateway price changed: input $0.80 → $1.40, output $2.55 → $4.40 per 1M tokens
- OpenRouter price changed: input $0.006 → $0.006, output $7 → $6.80 per 1M tokens
- OpenRouter price changed: input $0.01 → $0.006, output $7 → $7 per 1M tokens
- OpenRouter price changed: input $0.03 → $0.01, output $7 → $7 per 1M tokens
- Nebius AI Studio price changed: input $1.40 → $1.40, output $4.40 → $4.40 per 1M tokens
- OpenRouter price changed: input $0.62 → $0.03, output $2.42 → $7 per 1M tokens
- Baseten price changed: input $1.40 → $1.40, output $4.40 → $4.40 per 1M tokens
- Nebius AI Studio price changed: input $1.40 → $1.40, output $4.40 → $4.40 per 1M tokens
- OpenRouter price changed: input $0.04 → $0.62, output $9 → $2.42 per 1M tokens
- OpenRouter price changed: input $0.02 → $0.04, output $7 → $9 per 1M tokens
- OpenRouter price changed: input $0.05 → $0.02, output $7 → $7 per 1M tokens
- OpenRouter price changed: input $0.06 → $0.05, output $7 → $7 per 1M tokens
- OpenRouter price changed: input $0.06 → $0.06, output $4.20 → $7 per 1M tokens
- OpenRouter price changed: input $0.03 → $0.06, output $10 → $4.20 per 1M tokens
- OpenRouter price changed: input $0.17 → $0.03, output $7.20 → $10 per 1M tokens
- No longer listed on mistral
- OpenRouter price changed: input $0.11 → $0.17, output $12 → $7.20 per 1M tokens
- OpenRouter price changed: input $0.02 → $0.11, output $16 → $12 per 1M tokens
- OpenRouter price changed: input $0.08 → $0.02, output $8 → $16 per 1M tokens
- OpenRouter price changed: input $0.05 → $0.08, output $8 → $8 per 1M tokens
- OpenRouter price changed: input $0.06 → $0.05, output $8 → $8 per 1M tokens
Sources
- https://openrouter.ai/z-ai/glm-5.2
- https://github.com/sst/models.dev/blob/dev/providers/zai/models/glm-5.2.toml
- https://huggingface.co/zai-org/GLM-5.2
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/zai-org/GLM-5.2.toml
- https://github.com/sst/models.dev/blob/dev/providers/siliconflow/models/zai-org/GLM-5.2.toml
- https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/glm-5.2.toml
- https://github.com/sst/models.dev/blob/dev/providers/databricks/models/databricks-glm-5-2.toml
- https://github.com/sst/models.dev/blob/dev/providers/google-vertex/models/zai-org/glm-5.2-maas.toml
- https://github.com/sst/models.dev/blob/dev/providers/nebius/models/zai-org/GLM-5.2.toml
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/zai-org/glm-5.2.toml
- https://github.com/sst/models.dev/blob/dev/providers/friendli/models/zai-org/GLM-5.2.toml
- https://github.com/sst/models.dev/blob/dev/providers/togetherai/models/zai-org/GLM-5.2.toml
- https://github.com/sst/models.dev/blob/dev/providers/baseten/models/zai-org/GLM-5.2.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/zai-org/GLM-5.2.toml
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/zai/glm-5.2.toml
- https://github.com/sst/models.dev/blob/dev/providers/baseten/models/zai-org/GLM-5.2-Fast.toml
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/zai/glm-5.2-fast.toml