Codestral 25.01 vs GPT-5 mini

Codestral 25.01 is cheaper than GPT-5 mini by about 35% on a blended (75% input / 25% output) basis. Codestral 25.01 charges $0.30 / $0.90 per 1M input/output tokens; GPT-5 mini charges $0.25 / $2.00.

FieldCodestral 25.01GPT-5 mini
Input $/Mtok$0.30$0.25
Output $/Mtok$0.90$2.00
Cache read $/Mtok$0.0300$0.0250
Cache write $/Mtok––
Input $/Mchar0.110.0704
Output $/Mchar0.320.56
Context window262144400000
Tokenizermistralo200k
Confidence?aggregatorapi
Sourcemodelsdevopenrouter

Confidence: official = vendor pricing page · api = OpenRouter per-host · aggregator = community list, may lag · unreviewed = automatic extraction awaiting review. When sources disagree the most authoritative wins. Details: /methodology#confidence

Price history

No price changes recorded yet for either model.

Same workload, monthly cost

Illustrative monthly cost at 10M tokens/month, split per workload preset. Not a substitute for the calculator, which uses your own volume, cache and batch assumptions.

WorkloadCodestral 25.01GPT-5 mini
Coding agent$3.30$3.38
RAG chat$3.90$5.13
Summarisation (batch)$3.60$4.25
Classification$3.12$2.85
Chat assistant$5.40$9.50
Content generation$7.80$16.50

Batch pricing not published for Codestral 25.01; standard rate used for the batch share of a workload.

Batch pricing not published for GPT-5 mini; standard rate used for the batch share of a workload.

Cite this page

Codestral 25.01 vs GPT-5 mini: $0.30/$0.90 vs $0.25/$2.00 per 1M tokens as of 2026-11-19. Token Barometer by Dejan Strbad, https://tokenbarometer.com, data CC BY 4.0. https://tokenbarometer.com/compare/mistral_codestral-2501-vs-openai_gpt-5-mini

Codestral 25.01 page | GPT-5 mini page | Open Codestral 25.01 in calculator | Open GPT-5 mini in calculator