GLM-4.5 7B: pricing, context window and benchmarks
GLM-4.5 7B is a small open-weight model from Zhipu AI. It offers a 8,192-token context window, costs $1.32 per million input tokens and $5.93 per million output tokens, and averages 60.2 across the index's benchmark suite.
Pricing
GLM-4.5 7B costs $1.32 per million input tokens and $5.93 per million output tokens. A blended 3:1 input-to-output mix works out to about $2.47 per million tokens. Cached input is listed at $0.12 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $1.32 | per 1M tokens |
| Output | $5.93 | per 1M tokens |
| Cached input | $0.12 | per 1M tokens |
| Blended 3:1 | $2.47 | estimate per 1M tokens |
| 1M in + 1M out | $7.25 | 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 | 65.1 | 452 | 25th | |
| GPQA Diamond | 54.5 | 472 | 21th | |
| SWE-bench Verified | 45.4 | 462 | 23th | |
| HumanEval | 65.3 | 438 | 27th | |
| MATH-500 | 63.3 | 433 | 28th | |
| AIME 2025 | 51.2 | 448 | 25th | |
| LiveCodeBench | 49.4 | 454 | 24th | |
| IFEval | 70.5 | 448 | 25th | |
| TruthfulQA | 64.4 | 465 | 23th | |
| HellaSwag | 73.1 | 476 | 21th | |
| MMMU | 59.6 | 432 | 28th | |
| Arena Elo | 1258.6 | 477 | 21th |
What GLM-4.5 7B is good for
GLM-4.5 7B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $1.32 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $1.32 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
Trade-offs
- Context window of 8,192 tokens is small for long-document work.
- Average benchmark score is below the index median; test it on your own task.
- Less reliable on open-ended reasoning and complex multi-step instructions.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| SmolLM3 Base | Hugging Face | 16384 | $1.38 | 60.4 |
| GLM-4.5 7B | Zhipu AI | 8192 | $1.32 | 60.2 |
| GPT-NeoX Chat | EleutherAI | 16384 | $1.49 | 60.1 |
| Llama 3.3 8B | Meta AI | 8192 | $1.26 | 60.1 |
| Llama 4 Scout 7B | Meta AI | 32768 | $1.30 | 60.0 |
| Magistral 8B | Mistral AI | 4096 | $1.33 | 60.0 |
FAQ
How much does GLM-4.5 7B cost?
GLM-4.5 7B is listed at $1.32 per million input tokens and $5.93 per million output tokens. Cached input is $0.12 per million tokens. A blended 3:1 input-to-output mix is about $2.47 per million tokens.
What is the context window of GLM-4.5 7B?
GLM-4.5 7B has a context window of 8,192 tokens and can emit up to 8,192 output tokens per request in this index.
Is GLM-4.5 7B open weights?
Yes. GLM-4.5 7B is listed as an open-weight model under a open weights licence.
How does GLM-4.5 7B score on benchmarks?
GLM-4.5 7B averages 60.2 across the scored benchmarks in this index, ranking #448 of 600 models. Its strongest relative result is Arena Elo at 1258.6.
What is GLM-4.5 7B best for?
GLM-4.5 7B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $1.32 per million input tokens it can handle a large share of production traffic.