Hunyuan-Large Instruct: pricing, context window and benchmarks
Hunyuan-Large Instruct is a multimodal model from Tencent. It offers a 65,536-token context window, costs $4.39 per million input tokens and $19.44 per million output tokens, and averages 78.2 across the index's benchmark suite.
Pricing
Hunyuan-Large Instruct costs $4.39 per million input tokens and $19.44 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 $0.60 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $4.39 | per 1M tokens |
| Output | $19.44 | per 1M tokens |
| Cached input | $0.60 | per 1M tokens |
| Blended 3:1 | $8.15 | estimate per 1M tokens |
| 1M in + 1M out | $23.83 | 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 | 79.0 | 209 | 65th | |
| GPQA Diamond | 75.4 | 136 | 77th | |
| SWE-bench Verified | 66.1 | 191 | 68th | |
| HumanEval | 84.0 | 132 | 78th | |
| MATH-500 | 82.9 | 148 | 75th | |
| AIME 2025 | 76.9 | 130 | 78th | |
| LiveCodeBench | 68.3 | 219 | 64th | |
| IFEval | 86.1 | 151 | 75th | |
| TruthfulQA | 79.8 | 187 | 69th | |
| HellaSwag | 87.7 | 153 | 75th | |
| MMMU | 74.3 | 176 | 71th | |
| Arena Elo | 1422.1 | 138 | 77th |
What Hunyuan-Large Instruct is good for
Hunyuan-Large 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 $4.39 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 Instruct cost?
Hunyuan-Large Instruct is listed at $4.39 per million input tokens and $19.44 per million output tokens. Cached input is $0.60 per million tokens. A blended 3:1 input-to-output mix is about $8.15 per million tokens.
What is the context window of Hunyuan-Large Instruct?
Hunyuan-Large Instruct has a context window of 65,536 tokens and can emit up to 4,096 output tokens per request in this index.
Is Hunyuan-Large Instruct open weights?
Yes. Hunyuan-Large Instruct is listed as an open-weight model under a open weights licence.
How does Hunyuan-Large Instruct score on benchmarks?
Hunyuan-Large Instruct averages 78.2 across the scored benchmarks in this index, ranking #165 of 600 models. Its strongest relative result is Arena Elo at 1422.1.
What is Hunyuan-Large Instruct best for?
Hunyuan-Large 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 $4.39 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.