GLM-4.6 Instruct: pricing, context window and benchmarks
GLM-4.6 Instruct is a multimodal model from Zhipu AI. It offers a 1,000,000-token context window, costs $5.15 per million input tokens and $24.32 per million output tokens, and averages 80.4 across the index's benchmark suite.
Pricing
GLM-4.6 Instruct costs $5.15 per million input tokens and $24.32 per million output tokens. A blended 3:1 input-to-output mix works out to about $9.94 per million tokens. Cached input is listed at $0.46 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $5.15 | per 1M tokens |
| Output | $24.32 | per 1M tokens |
| Cached input | $0.46 | per 1M tokens |
| Blended 3:1 | $9.94 | estimate per 1M tokens |
| 1M in + 1M out | $29.47 | 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 | 80.6 | 163 | 73th | |
| GPQA Diamond | 75.8 | 124 | 79th | |
| SWE-bench Verified | 70.5 | 100 | 83th | |
| HumanEval | 85.3 | 108 | 82th | |
| MATH-500 | 84.9 | 110 | 82th | |
| AIME 2025 | 74.5 | 164 | 73th | |
| LiveCodeBench | 72.6 | 134 | 78th | |
| IFEval | 87.4 | 121 | 80th | |
| TruthfulQA | 83.8 | 85 | 86th | |
| HellaSwag | 90.6 | 72 | 88th | |
| MMMU | 78.9 | 74 | 88th | |
| Arena Elo | 1426.6 | 126 | 79th |
What GLM-4.6 Instruct is good for
GLM-4.6 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 $5.15 per million input tokens, it sits in the mid-range of the index, and the 1,000,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 1,000,000-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 |
|---|---|---|---|---|
| ERNIE 4.5 Pro | Baidu | 1000000 | $13.89 | 80.5 |
| Kimi K1.5 Instruct | Moonshot AI | 200000 | $5.15 | 80.5 |
| Sonar Pro Reasoning | Perplexity | 128000 | $13.94 | 80.5 |
| GLM-4.6 Instruct | Zhipu AI | 1000000 | $5.15 | 80.4 |
| GPT-5.2 Mini | OpenAI | 200000 | $13.34 | 80.4 |
| Qwen3 | Alibaba Cloud | 128000 | $5.04 | 80.3 |
FAQ
How much does GLM-4.6 Instruct cost?
GLM-4.6 Instruct is listed at $5.15 per million input tokens and $24.32 per million output tokens. Cached input is $0.46 per million tokens. A blended 3:1 input-to-output mix is about $9.94 per million tokens.
What is the context window of GLM-4.6 Instruct?
GLM-4.6 Instruct has a context window of 1,000,000 tokens and can emit up to 128,000 output tokens per request in this index.
Is GLM-4.6 Instruct open weights?
Yes. GLM-4.6 Instruct is listed as an open-weight model under a open weights licence.
How does GLM-4.6 Instruct score on benchmarks?
GLM-4.6 Instruct averages 80.4 across the scored benchmarks in this index, ranking #109 of 600 models. Its strongest relative result is Arena Elo at 1426.6.
What is GLM-4.6 Instruct best for?
GLM-4.6 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 $5.15 per million input tokens, it sits in the mid-range of the index, and the 1,000,000-token context window is enough for large files and multi-file diffs.