GLM-4.5 Instruct: pricing, context window and benchmarks
GLM-4.5 Instruct is a multimodal model from Zhipu AI. It offers a 200,000-token context window, costs $4.70 per million input tokens and $22.79 per million output tokens, and averages 78.8 across the index's benchmark suite.
Pricing
GLM-4.5 Instruct costs $4.70 per million input tokens and $22.79 per million output tokens. A blended 3:1 input-to-output mix works out to about $9.22 per million tokens. Cached input is listed at $0.41 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $4.70 | per 1M tokens |
| Output | $22.79 | per 1M tokens |
| Cached input | $0.41 | per 1M tokens |
| Blended 3:1 | $9.22 | estimate per 1M tokens |
| 1M in + 1M out | $27.49 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 82.1 | 119 | 80th | |
| GPQA Diamond | 75.3 | 139 | 77th | |
| SWE-bench Verified | 67.3 | 161 | 73th | |
| HumanEval | 82.2 | 180 | 70th | |
| MATH-500 | 79.6 | 217 | 64th | |
| AIME 2025 | 74.3 | 168 | 72th | |
| LiveCodeBench | 74.8 | 97 | 84th | |
| IFEval | 84.4 | 202 | 66th | |
| TruthfulQA | 83.4 | 96 | 84th | |
| HellaSwag | 87.8 | 149 | 75th | |
| MMMU | 75.4 | 153 | 75th | |
| Arena Elo | 1410.6 | 183 | 70th |
What GLM-4.5 Instruct is good for
GLM-4.5 Instruct is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $4.70 per million input tokens, it sits in the mid-range of the index, and the 200,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 200,000-token context window for long documents and agent traces.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
- Coding benchmarks are a relative strength within its tier.
Trade-offs
- No standout weakness in the indexed specifications, but real-world behaviour still needs testing.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Claude Opus 4.5 Mini | Anthropic | 65536 | $12.72 | 79.0 |
| QwQ Instruct | Alibaba Cloud | 65536 | $4.62 | 79.0 |
| Sonar Pro Turbo | Perplexity | 128000 | $13.55 | 79.0 |
| ERNIE 4.0 Max | Baidu | 32768 | $12.40 | 78.9 |
| GLM-4.5 Instruct | Zhipu AI | 200000 | $4.70 | 78.8 |
| QwQ | Alibaba Cloud | 128000 | $4.57 | 78.6 |
FAQ
How much does GLM-4.5 Instruct cost?
GLM-4.5 Instruct is listed at $4.70 per million input tokens and $22.79 per million output tokens. Cached input is $0.41 per million tokens. A blended 3:1 input-to-output mix is about $9.22 per million tokens.
What is the context window of GLM-4.5 Instruct?
GLM-4.5 Instruct has a context window of 200,000 tokens and can emit up to 128,000 output tokens per request in this index.
Is GLM-4.5 Instruct open weights?
Yes. GLM-4.5 Instruct is listed as an open-weight model under a open weights licence.
How does GLM-4.5 Instruct score on benchmarks?
GLM-4.5 Instruct averages 78.8 across the scored benchmarks in this index, ranking #153 of 600 models. Its strongest relative result is Arena Elo at 1410.6.
What is GLM-4.5 Instruct best for?
GLM-4.5 Instruct is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $4.70 per million input tokens, it sits in the mid-range of the index, and the 200,000-token context window is enough for large files and multi-file diffs.