Sonar Pro Turbo: pricing, context window and benchmarks
Sonar Pro Turbo is a multimodal model from Perplexity. It offers a 128,000-token context window, costs $13.55 per million input tokens and $57.97 per million output tokens, and averages 79.0 across the index's benchmark suite.
Pricing
Sonar Pro Turbo costs $13.55 per million input tokens and $57.97 per million output tokens. A blended 3:1 input-to-output mix works out to about $24.66 per million tokens. Cached input is listed at $1.96 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $13.55 | per 1M tokens |
| Output | $57.97 | per 1M tokens |
| Cached input | $1.96 | per 1M tokens |
| Blended 3:1 | $24.66 | estimate per 1M tokens |
| 1M in + 1M out | $71.52 | 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 | 81.6 | 132 | 78th | |
| GPQA Diamond | 74.2 | 163 | 73th | |
| SWE-bench Verified | 66.3 | 187 | 69th | |
| HumanEval | 84.7 | 123 | 80th | |
| MATH-500 | 84.1 | 125 | 79th | |
| AIME 2025 | 73.9 | 188 | 69th | |
| LiveCodeBench | 73.7 | 116 | 81th | |
| IFEval | 84.9 | 196 | 67th | |
| TruthfulQA | 81.2 | 151 | 75th | |
| HellaSwag | 89.3 | 106 | 82th | |
| MMMU | 75.2 | 160 | 73th | |
| Arena Elo | 1434.8 | 107 | 82th |
What Sonar Pro Turbo is good for
Sonar Pro Turbo 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 $13.55 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 $13.55 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Llama 4 Scout Instruct | Meta AI | 32768 | $4.59 | 79.1 |
| Mistral Large 3 Chat | Mistral AI | 1000000 | $4.90 | 79.1 |
| Sonar Pro | Perplexity | 128000 | $13.01 | 79.1 |
| Claude Opus 4.5 Mini | Anthropic | 65536 | $12.72 | 79.0 |
| QwQ Instruct | Alibaba Cloud | 65536 | $4.62 | 79.0 |
| Sonar Pro Turbo | Perplexity | 128000 | $13.55 | 79.0 |
FAQ
How much does Sonar Pro Turbo cost?
Sonar Pro Turbo is listed at $13.55 per million input tokens and $57.97 per million output tokens. Cached input is $1.96 per million tokens. A blended 3:1 input-to-output mix is about $24.66 per million tokens.
What is the context window of Sonar Pro Turbo?
Sonar Pro Turbo 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 Turbo open weights?
No. Sonar Pro Turbo is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Sonar Pro Turbo score on benchmarks?
Sonar Pro Turbo averages 79.0 across the scored benchmarks in this index, ranking #151 of 600 models. Its strongest relative result is Arena Elo at 1434.8.
What is Sonar Pro Turbo best for?
Sonar Pro Turbo 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 $13.55 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.