GLM-4.6 Base: pricing, context window and benchmarks
GLM-4.6 Base is a multimodal model from Zhipu AI. It offers a 128,000-token context window, costs $4.53 per million input tokens and $20.43 per million output tokens, and averages 78.5 across the index's benchmark suite.
Pricing
GLM-4.6 Base costs $4.53 per million input tokens and $20.43 per million output tokens. A blended 3:1 input-to-output mix works out to about $8.50 per million tokens. Cached input is listed at $0.39 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $4.53 | per 1M tokens |
| Output | $20.43 | per 1M tokens |
| Cached input | $0.39 | per 1M tokens |
| Blended 3:1 | $8.50 | estimate per 1M tokens |
| 1M in + 1M out | $24.96 | 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 | 79.5 | 194 | 68th | |
| GPQA Diamond | 75.1 | 141 | 77th | |
| SWE-bench Verified | 66.0 | 192 | 68th | |
| HumanEval | 83.8 | 139 | 77th | |
| MATH-500 | 83.8 | 127 | 79th | |
| AIME 2025 | 71.8 | 222 | 63th | |
| LiveCodeBench | 74.5 | 99 | 84th | |
| IFEval | 86.9 | 134 | 78th | |
| TruthfulQA | 81.9 | 131 | 78th | |
| HellaSwag | 86.6 | 190 | 68th | |
| MMMU | 73.2 | 211 | 65th | |
| Arena Elo | 1421.8 | 140 | 77th |
What GLM-4.6 Base is good for
GLM-4.6 Base 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 $4.53 per million input tokens, it sits in the mid-range of the index, and the 128,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 128,000-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 |
|---|---|---|---|---|
| QwQ | Alibaba Cloud | 128000 | $4.57 | 78.6 |
| GLM-4.6 Base | Zhipu AI | 128000 | $4.53 | 78.5 |
| Reka Core Reasoning | Reka AI | 32768 | $13.11 | 78.5 |
| Magistral Instruct | Mistral AI | 65536 | $4.48 | 78.4 |
| Nova Pro Turbo | Amazon | 128000 | $13.18 | 78.4 |
| Qwen3-Coder Chat | Alibaba Cloud | 128000 | $4.59 | 78.4 |
FAQ
How much does GLM-4.6 Base cost?
GLM-4.6 Base is listed at $4.53 per million input tokens and $20.43 per million output tokens. Cached input is $0.39 per million tokens. A blended 3:1 input-to-output mix is about $8.50 per million tokens.
What is the context window of GLM-4.6 Base?
GLM-4.6 Base has a context window of 128,000 tokens and can emit up to 32,768 output tokens per request in this index.
Is GLM-4.6 Base open weights?
Yes. GLM-4.6 Base is listed as an open-weight model under a open weights licence.
How does GLM-4.6 Base score on benchmarks?
GLM-4.6 Base averages 78.5 across the scored benchmarks in this index, ranking #155 of 600 models. Its strongest relative result is Arena Elo at 1421.8.
What is GLM-4.6 Base best for?
GLM-4.6 Base 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 $4.53 per million input tokens, it sits in the mid-range of the index, and the 128,000-token context window is enough for large files and multi-file diffs.