Sonar Pro vs Yi-Large
Perplexity vs 01.AI · Prices checked 12 August 2026
There is a 2.2× price gap here. Yi-Large blends to $3.00 per million tokens; Sonar Pro to $6.60. A single 100K-input, 10K-output job costs $0.330 on Yi-Large against $0.450 on Sonar Pro.
Capability favours Sonar Pro, ahead on 3 of 3 suites they both publish. The widest gap is on MATH, where Sonar Pro leads by 20 points. Sonar Pro reads more in one request: 200,000 tokens of context against 32,000.
Pricing and capacity
| Metric | Sonar Pro | Yi-Large | Difference |
|---|---|---|---|
| Input / 1M tokens | $3.00 | $3.00 | level |
| Output / 1M tokens | $15.00 | $3.00 | 5.0× |
| Blended · 70/30calculated | $6.60 | $3.00 | 2.2× |
| Blended · 50/50calculated | $9.00 | $3.00 | 3.0× |
| Blended · 80/20calculated | $5.40 | $3.00 | 44% |
| Blended · 20/80calculated | $12.60 | $3.00 | 4.2× |
| Job cost · 100K + 10Kcalculated | $0.450 | $0.330 | 27% |
| Job cost · 1M + 100Kcalculated | $4.50 | $3.30 | 27% |
| Context window | 200,000 | 32,000 | 6.3× |
Input and output rates are as published by each provider. Blended and job-cost rows are calculated comparison metrics, not published prices — how they are derived.
Benchmarks
| Benchmark | Sonar Pro | Yi-Large | Leader |
|---|---|---|---|
| MMLU | 86% | 78% | Sonar Pro |
| MATH | 80% | 60% | Sonar Pro |
| HumanEval | 80% | 70% | Sonar Pro |
Only suites both models report are listed, so a missing score is never shown as a loss. Figures are provider-published or from public leaderboards and are not independently re-run.
What each model is for
Sonar Pro
Perplexity · Frontier
Web-grounded Perplexity flagship. Returns answers with citations from a live search index.
- Live web search
- Citations included
- Up-to-date answers
Frequently asked questions
Which is cheaper, Sonar Pro or Yi-Large?
There is a 2.2× price gap here. Yi-Large blends to $3.00 per million tokens; Sonar Pro to $6.60. A single 100K-input, 10K-output job costs $0.330 on Yi-Large against $0.450 on Sonar Pro. Blended cost weights input at 70% and output at 30%; price your own token split for an exact answer, since the cheaper model on a blended basis is not always cheaper for your workload.
Which performs better, Sonar Pro or Yi-Large?
Capability favours Sonar Pro, ahead on 3 of 3 suites they both publish. The widest gap is on MATH, where Sonar Pro leads by 20 points. These are the figures each provider or public leaderboard publishes, not results we re-run, and a benchmark average can hide the specific behaviour your workload depends on.
Which has the larger context window, Sonar Pro or Yi-Large?
Sonar Pro reads more in one request: 200,000 tokens of context against 32,000. The context window caps everything in a single request: prompt, retrieved documents, conversation history and the model’s own output all share it.
Can I compare Sonar Pro and Yi-Large on my own numbers?
Yes. Open both in the side-by-side comparison tool to see every field at once, or use the token calculator to price your actual prompt and monthly request volume against each model. Both are free and need no sign-up.
Price it for your own workload
Related matchups
Terms used on this page
Prices and scores are recomputed on every deploy from the catalogue. Prices checked 12 August 2026.