Fusion Turbo: pricing, context window and benchmarks
Fusion Turbo is a mid-range model from OpenRouter. It offers a 8,192-token context window, costs $8.55 per million input tokens and $40.27 per million output tokens, and averages 71.7 across the index's benchmark suite.
Pricing
Fusion Turbo costs $8.55 per million input tokens and $40.27 per million output tokens. A blended 3:1 input-to-output mix works out to about $16.48 per million tokens. Cached input is listed at $0.69 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $8.55 | per 1M tokens |
| Output | $40.27 | per 1M tokens |
| Cached input | $0.69 | per 1M tokens |
| Blended 3:1 | $16.48 | estimate per 1M tokens |
| 1M in + 1M out | $48.82 | 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 | 76.0 | 307 | 49th | |
| GPQA Diamond | 67.3 | 324 | 46th | |
| SWE-bench Verified | 58.3 | 349 | 42th | |
| HumanEval | 76.2 | 324 | 46th | |
| MATH-500 | 77.8 | 261 | 57th | |
| AIME 2025 | 64.0 | 355 | 41th | |
| LiveCodeBench | 60.4 | 362 | 40th | |
| IFEval | 80.5 | 320 | 47th | |
| TruthfulQA | 74.5 | 340 | 43th | |
| HellaSwag | 82.4 | 339 | 44th | |
| MMMU | 71.1 | 270 | 55th | |
| Arena Elo | 1368.7 | 323 | 46th |
What Fusion Turbo is good for
Fusion 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 $8.55 per million input tokens with a 8,192-token window, check its benchmark profile against the specific task before committing.
Strengths
- 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 $8.55 per million tokens.
- Context window of 8,192 tokens is small for long-document work.
- Average benchmark score is below the index median; test it on your own task.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Llama 3 DeepInfra Base | DeepInfra | 16384 | $2.95 | 71.8 |
| DBRX Chat | Databricks | 65536 | $3.07 | 71.7 |
| Fusion Turbo | OpenRouter | 8192 | $8.55 | 71.7 |
| Mixtral Turbo Chat | Together AI | 32768 | $3.02 | 71.7 |
| OLMo 2 Instruct | Allen Institute for AI | 32768 | $3.03 | 71.7 |
| Qwen3-Max Nano | Alibaba Cloud | 65536 | $8.31 | 71.7 |
FAQ
How much does Fusion Turbo cost?
Fusion Turbo is listed at $8.55 per million input tokens and $40.27 per million output tokens. Cached input is $0.69 per million tokens. A blended 3:1 input-to-output mix is about $16.48 per million tokens.
What is the context window of Fusion Turbo?
Fusion Turbo has a context window of 8,192 tokens and can emit up to 8,192 output tokens per request in this index.
Is Fusion Turbo open weights?
No. Fusion Turbo is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Fusion Turbo score on benchmarks?
Fusion Turbo averages 71.7 across the scored benchmarks in this index, ranking #333 of 600 models. Its strongest relative result is Arena Elo at 1368.7.
What is Fusion Turbo best for?
Fusion 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 $8.55 per million input tokens with a 8,192-token window, check its benchmark profile against the specific task before committing.