Hunyuan-Turbo: pricing, context window and benchmarks
Hunyuan-Turbo is a multimodal model from Tencent. It offers a 128,000-token context window, costs $10.55 per million input tokens and $41.84 per million output tokens, and averages 75.8 across the index's benchmark suite.
Pricing
Hunyuan-Turbo costs $10.55 per million input tokens and $41.84 per million output tokens. A blended 3:1 input-to-output mix works out to about $18.37 per million tokens. Cached input is listed at $1.41 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $10.55 | per 1M tokens |
| Output | $41.84 | per 1M tokens |
| Cached input | $1.41 | per 1M tokens |
| Blended 3:1 | $18.37 | estimate per 1M tokens |
| 1M in + 1M out | $52.39 | 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 | 165 | 73th | |
| GPQA Diamond | 73.9 | 170 | 72th | |
| SWE-bench Verified | 63.4 | 246 | 59th | |
| HumanEval | 81.5 | 196 | 67th | |
| MATH-500 | 78.0 | 257 | 57th | |
| AIME 2025 | 70.3 | 253 | 58th | |
| LiveCodeBench | 64.8 | 296 | 51th | |
| IFEval | 84.9 | 194 | 68th | |
| TruthfulQA | 79.8 | 188 | 69th | |
| HellaSwag | 83.9 | 286 | 52th | |
| MMMU | 72.7 | 227 | 62th | |
| Arena Elo | 1389.7 | 251 | 58th |
What Hunyuan-Turbo is good for
Hunyuan-Turbo is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $10.55 per million input tokens with a 128,000-token window, check its benchmark profile against the specific task before committing.
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.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Premium input pricing at $10.55 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Codestral Chat | Mistral AI | 32768 | $3.89 | 75.8 |
| Hunyuan-Turbo | Tencent | 128000 | $10.55 | 75.8 |
| Llama 3 Lambda Instruct | Lambda | 32768 | $3.92 | 75.8 |
| Llama 3 Anyscale Instruct | Anyscale | 200000 | $3.91 | 75.7 |
| Llama 3 Replicate | Replicate | 200000 | $3.75 | 75.7 |
| Llama 3.1 Instruct | Meta AI | 200000 | $4.05 | 75.7 |
FAQ
How much does Hunyuan-Turbo cost?
Hunyuan-Turbo is listed at $10.55 per million input tokens and $41.84 per million output tokens. Cached input is $1.41 per million tokens. A blended 3:1 input-to-output mix is about $18.37 per million tokens.
What is the context window of Hunyuan-Turbo?
Hunyuan-Turbo has a context window of 128,000 tokens and can emit up to 16,384 output tokens per request in this index.
Is Hunyuan-Turbo open weights?
No. Hunyuan-Turbo is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Hunyuan-Turbo score on benchmarks?
Hunyuan-Turbo averages 75.8 across the scored benchmarks in this index, ranking #228 of 600 models. Its strongest relative result is Arena Elo at 1389.7.
What is Hunyuan-Turbo best for?
Hunyuan-Turbo is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $10.55 per million input tokens with a 128,000-token window, check its benchmark profile against the specific task before committing.