# GLM-4.5

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly enhanced capabilities in reasoning, code generation, and agent alignment. It supports a hybrid inference mode with two options, a "thinking mode" designed for complex reasoning and tool use, and a "non-thinking mode" optimized for instant responses. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)

## Model Information

- **Organization**: [Z.ai](/llm.txt)
- **Slug**: glm-4-5
- **Available at Providers**: 38
- **Release Date**: July 28, 2025

### Benchmark Scores
- HLE: 0.144
- GPQA: 0.791
- SWE Bench: 0.642
- Terminal: 0.375
- Browsecomp: 0.264

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [AIHubMix](/llm/aihubmix.txt) | glm-4.5 | 0.40 | 1.60 |  | [View](https://aihubmix.com/model/glm-4.5) |
| [AIMLAPI](/llm/aimlapi.txt) | GLM 4.5 |  |  |  |  |
| [FastRouter](/llm/fastrouter.txt) | Z.AI: GLM 4.5 | 0.60 | 2.20 |  | [View](https://fastrouter.ai/models/z-ai/glm-4.5) |
| [Abacus](/llm/abacus.txt) | GLM-4.5 | 0.60 | 2.20 |  |  |
| [Novita AI](/llm/novita.txt) | glm-4.5 | 0.60 | 2.20 |  |  |
| [SiliconFlow](/llm/siliconflow.txt) | zai-org/GLM-4.5 | 0.40 | 2.00 |  |  |
| [Zhipu AI](/llm/zhipuai.txt) | GLM-4.5 | 0.60 | 2.20 |  |  |
| [ModelScope](/llm/modelscope.txt) | GLM-4.5 | 0.00 | 0.00 | Yes |  |
| [Nano-GPT](/llm/nanogpt.txt) | GLM 4.5 (Thinking) |  |  |  |  |
| [Nano-GPT](/llm/nanogpt.txt) | GLM 4.5 |  |  |  |  |
| [OpenRouter](/llm/openrouter.txt) | GLM 4.5 | 0.55 | 2.00 |  | [View](https://openrouter.ai/z-ai/glm-4.5) |
| [Poe](/llm/poe.txt) | GLM-4.5 | 5700.00 |  |  | [View](https://poe.com/glm-4.5/api) |
| [Requesty](/llm/requesty.txt) |  | 0.60 | 2.20 |  |  |
| [Requesty](/llm/requesty.txt) |  | 0.60 | 2.20 |  |  |
| [Requesty](/llm/requesty.txt) |  | 0.60 | 2.20 |  |  |
| [Requesty](/llm/requesty.txt) |  | 0.60 | 2.20 |  |  |
| [ValorGPT](/llm/valorgpt.txt) | GLM 4.5 |  |  |  | [View](https://www.valorgpt.com/models/z-ai-glm-4.5) |
| [Vercel AI Gateway](/llm/vercel.txt) | GLM 4.5 | 0.60 | 2.20 |  |  |
| [Yupp](/llm/yupp.txt) | GLM 4.5 (Novita) |  |  |  |  |
| [Yupp](/llm/yupp.txt) | GLM 4.5 (Z.ai) |  |  |  |  |
| [Yupp](/llm/yupp.txt) | GLM 4.5 (OpenRouter) |  |  |  |  |
| [Z.AI](/llm/zai.txt) | GLM-4.5 | 0.60 | 0.11 |  |  |
| [ZenMUX](/llm/zenmux.txt) | Z.AI: GLM 4.5 | 0.35 | 1.54 |  |  |
| [Nebius Token Factory](/llm/nebius.txt) | GLM-4.5 | 0.60 | 2.20 |  | [View](https://huggingface.co/zai-org/GLM-4.5) |
| [Glama](/llm/glama.txt) | glm-4.5 | 0.60 | 2.20 |  | [View](https://glama.ai/gateway/models/glm-4.5) |
| [LangDB](/llm/langdb.txt) | glm-4.5 |  |  |  | [View](https://langdb.ai/app/models) |
| [302.AI](/llm/302ai.txt) | glm-4.5 | 0.29 | 1.14 |  | [View](https://302ai-en.apifox.cn/207705116e0) |
| [SiliconFlow](/llm/siliconflow.txt) | GLM-4.5 |  |  |  |  |
| [Kilo Code](/llm/kilocode.txt) | Z.ai: GLM 4.5 | 0.35 | 1.55 |  |  |
| [302.AI](/llm/302ai.txt) | zai-org/glm-4.5 | 0.57 | 2.29 |  | [View](https://302ai-en.apifox.cn/api-308032503) |
| [Jiekou.AI](/llm/jiekou.txt) | GLM-4.5 | 0.60 | 2.20 |  |  |
| [Blackbox AI](/llm/blackboxai.txt) | blackboxai/z-ai/glm-4.5 |  |  |  |  |
| [CometAPI](/llm/cometapi.txt) | glm-4.5 | 0.96 | 3.84 |  |  |
| [Qiniu](/llm/qiniuai.txt) | GLM 4.5 |  |  |  |  |
| [ApiYI](/llm/apiyi.txt) | glm-4.5 |  |  |  |  |
| [WaveSpeed AI](/llm/wavespeed.txt) | glm-4.5 | 0.39 | 1.71 |  |  |
| [Airforce API](/llm/airforce.txt) | glm-4.5 |  |  |  |  |
| [LLM Stats](/llm/llmstats.txt) | GLM-4.5 |  |  |  |  |

---

[← Back to all providers](/llm.txt)