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

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

Codestral 2508 vs Mistral Small 4

Short answer

Codestral 2508 ($0.30 in / $0.90 out); Mistral Small 4 ($0.15 in / $0.60 out). Lowest listed input price: Mistral Small 4. Longest listed context: Mistral Small 4 at 262,144 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.
FactCodestral 2508Mistral Small 4
LabMistralMistral
KindChatChat
Listed1 Aug 202516 Mar 2026
Context256,000262,144
Input / million$0.30$0.15
Output / million$0.90$0.60
Batch inputNot listedNot listed
Batch outputNot listedNot listed
Inputsfile, textimage, text
Outputstexttext
ToolsYesYes
Open weightsNo public weights id listedYes
Knowledge cutoff2025-03-31Unknown
Third-party indexUnknown4.3
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.

Codestral 2508

New, not yet reviewed. No guide note yet.

Codestral 2508 is listed at $0.30 input and $0.90 output per million tokens, with a 256,000-token context window.

Mistral Small 4

Mistral Small 4 is the reviewed everyday Mistral model: open weights, image input, a 262,144-token window, and a low rate. The listing presents it as the small model that folds several earlier Mistral lines into one.

Mistral Small 4 is listed at $0.15 input and $0.60 output per million tokens, with a 262,144-token context window.

Choose models

Popular comparisons