Mistral Small 4 vs GPT-5 mini

Mistral Small 4 is cheaper than GPT-5 mini by about 62% on a blended (75% input / 25% output) basis. Mistral Small 4 charges $0.15 / $0.60 per 1M input/output tokens; GPT-5 mini charges $0.25 / $2.00.

FieldMistral Small 4GPT-5 mini
Input $/Mtok$0.15$0.25
Output $/Mtok$0.60$2.00
Cache read $/Mtok$0.0150$0.0250
Cache write $/Mtok––
Input $/Mchar0.05330.0704
Output $/Mchar0.210.56
Context window262144400000
Tokenizermistralo200k
Confidence?apiapi
Sourceopenrouteropenrouter

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.

WorkloadMistral Small 4GPT-5 mini
Coding agent$1.73$3.38
RAG chat$2.17$5.13
Summarisation (batch)$1.95$4.25
Classification$1.59$2.85
Chat assistant$3.30$9.50
Content generation$5.10$16.50

Batch pricing not published for Mistral Small 4; 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

Mistral Small 4 vs GPT-5 mini: $0.15/$0.60 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_mistral-small-2603-vs-openai_gpt-5-mini

Mistral Small 4 page | GPT-5 mini page | Open Mistral Small 4 in calculator | Open GPT-5 mini in calculator