Hunyuan-Turbo Reasoning: pricing, context window and benchmarks
Hunyuan-Turbo Reasoning is a multimodal model from Tencent. It offers a 128,000-token context window, costs $11.89 per million input tokens and $42.01 per million output tokens, and averages 77.5 across the index's benchmark suite.
Pricing
Hunyuan-Turbo Reasoning costs $11.89 per million input tokens and $42.01 per million output tokens. A blended 3:1 input-to-output mix works out to about $19.42 per million tokens. Cached input is listed at $1.63 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $11.89 | per 1M tokens |
| Output | $42.01 | per 1M tokens |
| Cached input | $1.63 | per 1M tokens |
| Blended 3:1 | $19.42 | estimate per 1M tokens |
| 1M in + 1M out | $53.90 | 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 | 77.8 | 249 | 59th | |
| GPQA Diamond | 73.5 | 184 | 69th | |
| SWE-bench Verified | 67.1 | 166 | 72th | |
| HumanEval | 83.3 | 153 | 75th | |
| MATH-500 | 79.5 | 221 | 63th | |
| AIME 2025 | 77.4 | 123 | 80th | |
| LiveCodeBench | 70.5 | 180 | 70th | |
| IFEval | 86.5 | 145 | 76th | |
| TruthfulQA | 77.6 | 265 | 56th | |
| HellaSwag | 85.0 | 244 | 59th | |
| MMMU | 74.7 | 165 | 73th | |
| Arena Elo | 1393.6 | 235 | 61th |
What Hunyuan-Turbo Reasoning is good for
Hunyuan-Turbo Reasoning 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 $11.89 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.
- Accepts more than text, including image input where the provider supports it.
- Reasoning-oriented profile, useful for multi-step problems and structured analysis.
- Coding benchmarks are a relative strength within its tier.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Premium input pricing at $11.89 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Codestral | Mistral AI | 65536 | $4.19 | 77.6 |
| Hunyuan-Turbo Pro | Tencent | 65536 | $12.00 | 77.6 |
| ERNIE 4.0 Pro | Baidu | 200000 | $12.58 | 77.5 |
| Hunyuan-Turbo Reasoning | Tencent | 128000 | $11.89 | 77.5 |
| Qwen3 Base | Alibaba Cloud | 65536 | $4.33 | 77.4 |
| Reka Core | Reka AI | 32768 | $12.17 | 77.4 |
FAQ
How much does Hunyuan-Turbo Reasoning cost?
Hunyuan-Turbo Reasoning is listed at $11.89 per million input tokens and $42.01 per million output tokens. Cached input is $1.63 per million tokens. A blended 3:1 input-to-output mix is about $19.42 per million tokens.
What is the context window of Hunyuan-Turbo Reasoning?
Hunyuan-Turbo Reasoning has a context window of 128,000 tokens and can emit up to 8,192 output tokens per request in this index.
Is Hunyuan-Turbo Reasoning open weights?
No. Hunyuan-Turbo Reasoning is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Hunyuan-Turbo Reasoning score on benchmarks?
Hunyuan-Turbo Reasoning averages 77.5 across the scored benchmarks in this index, ranking #186 of 600 models. Its strongest relative result is Arena Elo at 1393.6.
What is Hunyuan-Turbo Reasoning best for?
Hunyuan-Turbo Reasoning 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 $11.89 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.