HomeAboutModelsPricingSupport

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.

SpecificationMistral Medium 3.5Sonar
ProviderMistralPerplexity
Model IDmistral-medium-latestsonar
Context window262K128K
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 typestext, imagetext, image, file
Output typestexttext
PlanAll paid plansAll paid plans

Which should you use?

Pick Mistral Medium 3.5 when…

  • You need the larger context window — 262K against 128K.
Mistral Medium 3.5 details

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.
Sonar details

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.