Hunyuan-Large: pricing, context window and benchmarks
Hunyuan-Large is a multimodal model from Tencent. It offers a 65,536-token context window, costs $4.33 per million input tokens and $20.11 per million output tokens, and averages 78.2 across the index's benchmark suite.
Pricing
Hunyuan-Large costs $4.33 per million input tokens and $20.11 per million output tokens. A blended 3:1 input-to-output mix works out to about $8.28 per million tokens. Cached input is listed at $0.64 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $4.33 | per 1M tokens |
| Output | $20.11 | per 1M tokens |
| Cached input | $0.64 | per 1M tokens |
| Blended 3:1 | $8.28 | estimate per 1M tokens |
| 1M in + 1M out | $24.44 | 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 | 80.7 | 157 | 74th | |
| GPQA Diamond | 75.0 | 146 | 76th | |
| SWE-bench Verified | 67.8 | 149 | 75th | |
| HumanEval | 82.1 | 184 | 69th | |
| MATH-500 | 83.1 | 145 | 76th | |
| AIME 2025 | 74.3 | 170 | 72th | |
| LiveCodeBench | 71.8 | 151 | 75th | |
| IFEval | 84.4 | 204 | 66th | |
| TruthfulQA | 80.9 | 160 | 73th | |
| HellaSwag | 84.6 | 262 | 56th | |
| MMMU | 75.7 | 143 | 76th | |
| Arena Elo | 1394.8 | 230 | 62th |
What Hunyuan-Large is good for
Hunyuan-Large 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 $4.33 per million input tokens, it sits in the mid-range of the index, and the 65,536-token context window is enough for large files and multi-file diffs.
Strengths
- 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 |
|---|---|---|---|---|
| GLM-4.5 | Zhipu AI | 200000 | $4.55 | 78.2 |
| Hunyuan-Large | Tencent | 65536 | $4.33 | 78.2 |
| Hunyuan-Large Instruct | Tencent | 65536 | $4.39 | 78.2 |
| Llama 3.3 | Meta AI | 128000 | $4.56 | 78.2 |
| Mistral Large 3 Base | Mistral AI | 65536 | $4.47 | 78.2 |
| QwQ Chat | Alibaba Cloud | 65536 | $4.28 | 78.2 |
FAQ
How much does Hunyuan-Large cost?
Hunyuan-Large is listed at $4.33 per million input tokens and $20.11 per million output tokens. Cached input is $0.64 per million tokens. A blended 3:1 input-to-output mix is about $8.28 per million tokens.
What is the context window of Hunyuan-Large?
Hunyuan-Large has a context window of 65,536 tokens and can emit up to 8,192 output tokens per request in this index.
Is Hunyuan-Large open weights?
Yes. Hunyuan-Large is listed as an open-weight model under a open weights licence.
How does Hunyuan-Large score on benchmarks?
Hunyuan-Large averages 78.2 across the scored benchmarks in this index, ranking #164 of 600 models. Its strongest relative result is Arena Elo at 1394.8.
What is Hunyuan-Large best for?
Hunyuan-Large 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 $4.33 per million input tokens, it sits in the mid-range of the index, and the 65,536-token context window is enough for large files and multi-file diffs.