Sonar Pro Max: pricing, context window and benchmarks
Sonar Pro Max is a multimodal model from Perplexity. It offers a 128,000-token context window, costs $14.01 per million input tokens and $69.33 per million output tokens, and averages 81.1 across the index's benchmark suite.
Pricing
Sonar Pro Max costs $14.01 per million input tokens and $69.33 per million output tokens. A blended 3:1 input-to-output mix works out to about $27.84 per million tokens. Cached input is listed at $1.81 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $14.01 | per 1M tokens |
| Output | $69.33 | per 1M tokens |
| Cached input | $1.81 | per 1M tokens |
| Blended 3:1 | $27.84 | estimate per 1M tokens |
| 1M in + 1M out | $83.34 | 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 | 83.7 | 90 | 85th | |
| GPQA Diamond | 78.8 | 73 | 88th | |
| SWE-bench Verified | 71.7 | 81 | 87th | |
| HumanEval | 85.1 | 113 | 81th | |
| MATH-500 | 86.2 | 90 | 85th | |
| AIME 2025 | 74.9 | 157 | 74th | |
| LiveCodeBench | 75.7 | 88 | 85th | |
| IFEval | 88.3 | 96 | 84th | |
| TruthfulQA | 82.0 | 130 | 78th | |
| HellaSwag | 88.0 | 143 | 76th | |
| MMMU | 77.2 | 113 | 81th | |
| Arena Elo | 1437.8 | 102 | 83th |
What Sonar Pro Max is good for
Sonar Pro Max 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 $14.01 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.
- 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 $14.01 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Command A Pro | Cohere | 200000 | $14.28 | 81.3 |
| Doubao 1.5 Pro Max | ByteDance | 400000 | $14.93 | 81.2 |
| Nova Pro Max | Amazon | 1000000 | $14.05 | 81.2 |
| Mistral Large 3 Instruct | Mistral AI | 400000 | $5.31 | 81.1 |
| Sonar Pro Max | Perplexity | 128000 | $14.01 | 81.1 |
| Claude 3.7 Sonnet Vision | Anthropic | 400000 | $13.96 | 81.0 |
FAQ
How much does Sonar Pro Max cost?
Sonar Pro Max is listed at $14.01 per million input tokens and $69.33 per million output tokens. Cached input is $1.81 per million tokens. A blended 3:1 input-to-output mix is about $27.84 per million tokens.
What is the context window of Sonar Pro Max?
Sonar Pro Max has a context window of 128,000 tokens and can emit up to 4,096 output tokens per request in this index.
Is Sonar Pro Max open weights?
No. Sonar Pro Max is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Sonar Pro Max score on benchmarks?
Sonar Pro Max averages 81.1 across the scored benchmarks in this index, ranking #100 of 600 models. Its strongest relative result is Arena Elo at 1437.8.
What is Sonar Pro Max best for?
Sonar Pro Max 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 $14.01 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.