Checked against the OpenRouter public models feed. Prices are copied, not estimated.

The Best Model ForWhich AI model to use, from ten labs.

Mistral Medium 3.5 vs Mistral Large 4

Short answer

Mistral Medium 3.5 ($1.50 in / $7.50 out); Mistral Large 4 ($0.70 in / $2.10 out). Lowest listed input price: Mistral Large 4. Longest listed context: Mistral Large 4 at 1,048,576 tokens. A lower price is not a quality ranking.

Side-by-side facts. The third-party index is copied when the feed has one. Unknown means it did not.
FactMistral Medium 3.5Mistral Large 4
LabMistralMistral
KindChatChat
Listed30 Apr 20266 Oct 2026
Context262,1441,048,576
Input / million$1.50$0.70
Output / million$7.50$2.10
Batch input$0.75Not listed
Batch output$3.75Not listed
Inputsfile, image, textimage, text
Outputstexttext
ToolsYesYes
Open weightsYesYes
Knowledge cutoffUnknownUnknown
Third-party index4.626.1
GuideNew, not yet reviewedReviewed

Input and output prices are USD per million tokens, from pricing.prompt and pricing.completion. The index is not our benchmark.

Mistral Medium 3.5

New, not yet reviewed. No guide note yet.

Mistral Medium 3.5 is listed at $1.50 input and $7.50 output per million tokens, with a 262,144-token context window.

Mistral Large 4

Mistral Large 4 is listed with a public weights id, image input, about a million tokens of context, and a blurb aimed at reasoning, coding, and agents. Pick it when open weights are a requirement and you still want a frontier-shaped model.

Mistral Large 4 is listed at $0.70 input and $2.10 output per million tokens, with a 1,048,576-token context window.

Choose models

Popular comparisons