Sonar vs Mistral Large 3
Side-by-side specs, pricing and capabilities. Both models run on Clade under one subscription, so you can switch between them in the same conversation.
Sonar comes from Perplexity and Mistral Large 3 from Mistral. The practical difference for most people is context, price, and which input types each one accepts.
Mistral Large 3 holds more in a single conversation — 256K tokens against 128K — which matters for long documents and large codebases.
Mistral Large 3 is the cheaper of the two on input tokens at $0.50 / 1M tokens.
| Specification | Sonar | Mistral Large 3 |
|---|---|---|
| Provider | Perplexity | Mistral |
| Model ID | sonar | mistral-large-2512 |
| Context window | 128K | 256K |
| Max output | — | 8K |
| Input price | $1.00 / 1M tokens | $0.50 / 1M tokens |
| Output price | $1.00 / 1M tokens | $1.50 / 1M tokens |
| Knowledge cutoff | — | — |
| Input types | text, image, file | text, image, file, audio |
| Output types | text | text |
| Plan | Free | Free |
Which should you use?
Pick Mistral Large 3 when…
- You need the larger context window — 256K against 128K.
- Cost matters: input runs at $0.50 / 1M tokens versus $1.00 / 1M tokens.
- You want longer single responses — up to 8K output tokens.
- You need audio input, which the other model does not accept.
Related comparisons
Try both on Clade
You do not have to choose. One Clade subscription gives you Sonar, Mistral Large 3, and every other model on the platform.