Fusion Max: pricing, context window and benchmarks
Fusion Max is a mid-range model from OpenRouter. It offers a 65,536-token context window, costs $9.14 per million input tokens and $43.52 per million output tokens, and averages 72.5 across the index's benchmark suite.
Pricing
Fusion Max costs $9.14 per million input tokens and $43.52 per million output tokens. A blended 3:1 input-to-output mix works out to about $17.73 per million tokens. Cached input is listed at $1.13 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $9.14 | per 1M tokens |
| Output | $43.52 | per 1M tokens |
| Cached input | $1.13 | per 1M tokens |
| Blended 3:1 | $17.73 | estimate per 1M tokens |
| 1M in + 1M out | $52.66 | 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 | 75.1 | 329 | 45th | |
| GPQA Diamond | 71.5 | 229 | 62th | |
| SWE-bench Verified | 59.1 | 340 | 43th | |
| HumanEval | 79.1 | 262 | 56th | |
| MATH-500 | 74.1 | 344 | 43th | |
| AIME 2025 | 65.1 | 337 | 44th | |
| LiveCodeBench | 63.3 | 334 | 44th | |
| IFEval | 81.4 | 288 | 52th | |
| TruthfulQA | 78.6 | 231 | 62th | |
| HellaSwag | 82.6 | 331 | 45th | |
| MMMU | 67.7 | 348 | 42th | |
| Arena Elo | 1359.7 | 345 | 43th |
What Fusion Max is good for
Fusion Max 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 $9.14 per million input tokens with a 65,536-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 $9.14 per million tokens.
- Average benchmark score is below the index median; test it on your own task.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Mixtral Chat | Mistral AI | 65536 | $3.30 | 72.6 |
| Firefunction Reasoning | Fireworks AI | 8192 | $9.08 | 72.5 |
| Fusion Max | OpenRouter | 65536 | $9.14 | 72.5 |
| Mixtral Groq Instruct | Groq | 16384 | $3.25 | 72.5 |
| DBRX Instruct | Databricks | 8192 | $3.21 | 72.4 |
| Mixtral Turbo | Together AI | 65536 | $3.20 | 72.4 |
FAQ
How much does Fusion Max cost?
Fusion Max is listed at $9.14 per million input tokens and $43.52 per million output tokens. Cached input is $1.13 per million tokens. A blended 3:1 input-to-output mix is about $17.73 per million tokens.
What is the context window of Fusion Max?
Fusion Max has a context window of 65,536 tokens and can emit up to 65,536 output tokens per request in this index.
Is Fusion Max open weights?
No. Fusion Max is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Fusion Max score on benchmarks?
Fusion Max averages 72.5 across the scored benchmarks in this index, ranking #314 of 600 models. Its strongest relative result is Arena Elo at 1359.7.
What is Fusion Max best for?
Fusion Max 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 $9.14 per million input tokens with a 65,536-token window, check its benchmark profile against the specific task before committing.