GLM-4.5 Base: pricing, context window and benchmarks
GLM-4.5 Base is a multimodal model from Zhipu AI. It offers a 32,768-token context window, costs $3.99 per million input tokens and $20.65 per million output tokens, and averages 74.9 across the index's benchmark suite.
Pricing
GLM-4.5 Base costs $3.99 per million input tokens and $20.65 per million output tokens. A blended 3:1 input-to-output mix works out to about $8.15 per million tokens. Cached input is listed at $0.44 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.99 | per 1M tokens |
| Output | $20.65 | per 1M tokens |
| Cached input | $0.44 | per 1M tokens |
| Blended 3:1 | $8.15 | estimate per 1M tokens |
| 1M in + 1M out | $24.64 | 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 | 76.1 | 302 | 50th | |
| GPQA Diamond | 70.6 | 244 | 59th | |
| SWE-bench Verified | 61.6 | 289 | 52th | |
| HumanEval | 78.7 | 270 | 55th | |
| MATH-500 | 77.5 | 265 | 56th | |
| AIME 2025 | 68.6 | 286 | 52th | |
| LiveCodeBench | 71.5 | 160 | 73th | |
| IFEval | 83.3 | 236 | 61th | |
| TruthfulQA | 76.5 | 291 | 52th | |
| HellaSwag | 84.6 | 261 | 57th | |
| MMMU | 74.4 | 172 | 71th | |
| Arena Elo | 1403.0 | 202 | 66th |
What GLM-4.5 Base is good for
GLM-4.5 Base is an open-weight model, so it can be self-hosted or run through a third-party inference provider. That matters for data residency, fine-tuning and long-run cost control. At $3.99 per million input tokens (hosted list price) and a 32,768-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Input price of $3.99 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
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 |
|---|---|---|---|---|
| Llama 3 DeepInfra Chat | DeepInfra | 200000 | $3.74 | 75.0 |
| Nemotron 4 Chat | NVIDIA | 65536 | $3.99 | 75.0 |
| GLM-4.5 Base | Zhipu AI | 32768 | $3.99 | 74.9 |
| Llama 3 Baseten | Baseten | 128000 | $3.62 | 74.9 |
| Llama 3 Modal | Modal | 32768 | $3.82 | 74.9 |
| MiniMax-Text Base | MiniMax | 128000 | $3.66 | 74.9 |
FAQ
How much does GLM-4.5 Base cost?
GLM-4.5 Base is listed at $3.99 per million input tokens and $20.65 per million output tokens. Cached input is $0.44 per million tokens. A blended 3:1 input-to-output mix is about $8.15 per million tokens.
What is the context window of GLM-4.5 Base?
GLM-4.5 Base has a context window of 32,768 tokens and can emit up to 32,768 output tokens per request in this index.
Is GLM-4.5 Base open weights?
Yes. GLM-4.5 Base is listed as an open-weight model under a open weights licence.
How does GLM-4.5 Base score on benchmarks?
GLM-4.5 Base averages 74.9 across the scored benchmarks in this index, ranking #255 of 600 models. Its strongest relative result is Arena Elo at 1403.0.
What is GLM-4.5 Base best for?
GLM-4.5 Base is an open-weight model, so it can be self-hosted or run through a third-party inference provider. That matters for data residency, fine-tuning and long-run cost control. At $3.99 per million input tokens (hosted list price) and a 32,768-token context window, it is a practical option for teams that want more control than a closed API allows.