Mistral Codestral vs Ministral 14B

Lower and Larger mark one number at a time; they don’t rank the models. How well a model does depends on your task; see Benchmarks for measured results.

DetailMistral Codestralmistral/codestralMinistral 14Bmistral/ministral-14b
Makermistralmistral
KindChatChat
Input per 1M tokens$0.315$0.21 Lower
Cached input per 1M tokens$0.0315$0.021
Cache write per 1M tokensSame as inputSame as input
Output per 1M tokens$0.945$0.21 Lower
Context window128,000 tokens262,144 tokens Larger
Max output4,000 tokens256,000 tokens Larger
CapabilitiesTool useTool use, vision, file input
TakesTextText, image, pdf
ReturnsTextText
Zero data retentionYes, on every providerYes, on every provider
No training on requestsYes, on every providerYes, on every provider
Released2024-05-292025-12-02

Example costs

Example requests, priced at today’s rates with no cached input.

Example requestMistral CodestralMinistral 14B
1,000 tokens in, 200 out$0.000504$0.000252
10,000 tokens in, 1,000 out$0.004095$0.00231
100,000 tokens in, 4,000 out$0.03528$0.02184