Mistral Medium 3.5 vs Sonar
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.
Mistral Medium 3.5 comes from Mistral and Sonar from Perplexity. The practical difference for most people is context, price, and which input types each one accepts.
Mistral Medium 3.5 holds more in a single conversation — 262K tokens against 128K — which matters for long documents and large codebases.
Sonar is the cheaper of the two on input tokens at $1.00 / 1M tokens.
| Specification | Mistral Medium 3.5 | Sonar |
|---|---|---|
| Provider | Mistral | Perplexity |
| Model ID | mistral-medium-latest | sonar |
| Context window | 262K | 128K |
| Max output | — | — |
| Input price | $1.50 / 1M tokens | $1.00 / 1M tokens |
| Output price | $7.50 / 1M tokens | $1.00 / 1M tokens |
| Knowledge cutoff | — | — |
| Input types | text, image | text, image, file |
| Output types | text | text |
| Plan | All paid plans | All paid plans |
Which should you use?
Pick Mistral Medium 3.5 when…
- You need the larger context window — 262K against 128K.
Pick Sonar when…
- Cost matters: input runs at $1.00 / 1M tokens versus $1.50 / 1M tokens.
- You need file 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 Mistral Medium 3.5, Sonar, and every other model on the platform.
