Fusion: pricing, context window and benchmarks
Fusion is a mid-range model from OpenRouter. It offers a 16,384-token context window, costs $8.41 per million input tokens and $30.46 per million output tokens, and averages 71.1 across the index's benchmark suite.
Pricing
Fusion costs $8.41 per million input tokens and $30.46 per million output tokens. A blended 3:1 input-to-output mix works out to about $13.92 per million tokens. Cached input is listed at $0.98 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $8.41 | per 1M tokens |
| Output | $30.46 | per 1M tokens |
| Cached input | $0.98 | per 1M tokens |
| Blended 3:1 | $13.92 | estimate per 1M tokens |
| 1M in + 1M out | $38.87 | 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 | 74.9 | 336 | 44th | |
| GPQA Diamond | 64.4 | 373 | 38th | |
| SWE-bench Verified | 59.0 | 341 | 43th | |
| HumanEval | 74.4 | 352 | 41th | |
| MATH-500 | 74.0 | 346 | 42th | |
| AIME 2025 | 65.9 | 332 | 45th | |
| LiveCodeBench | 64.3 | 309 | 49th | |
| IFEval | 81.1 | 307 | 49th | |
| TruthfulQA | 75.0 | 331 | 45th | |
| HellaSwag | 81.1 | 367 | 39th | |
| MMMU | 68.5 | 334 | 44th | |
| Arena Elo | 1349.4 | 365 | 39th |
What Fusion is good for
Fusion 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 $8.41 per million input tokens with a 16,384-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 $8.41 per million tokens.
- Context window of 16,384 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 |
|---|---|---|---|---|
| Fusion | OpenRouter | 16384 | $8.41 | 71.1 |
| Gemma 3 Base | Google DeepMind | 65536 | $3.09 | 71.1 |
| Llama 3 Hyperbolic Base | Hyperbolic | 32768 | $3.02 | 71.1 |
| Mixtral Base | Mistral AI | 65536 | $2.95 | 71.1 |
| Command A Mini | Cohere | 8192 | $8.12 | 71.0 |
| OLMo 2 | Allen Institute for AI | 65536 | $2.99 | 71.0 |
FAQ
How much does Fusion cost?
Fusion is listed at $8.41 per million input tokens and $30.46 per million output tokens. Cached input is $0.98 per million tokens. A blended 3:1 input-to-output mix is about $13.92 per million tokens.
What is the context window of Fusion?
Fusion has a context window of 16,384 tokens and can emit up to 16,384 output tokens per request in this index.
Is Fusion open weights?
No. Fusion is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Fusion score on benchmarks?
Fusion averages 71.1 across the scored benchmarks in this index, ranking #343 of 600 models. Its strongest relative result is Arena Elo at 1349.4.
What is Fusion best for?
Fusion 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 $8.41 per million input tokens with a 16,384-token window, check its benchmark profile against the specific task before committing.