Codestral (latest) vs OpenAI: o4 Mini
Codestral (latest) is cheaper than OpenAI: o4 Mini by about 100% on a blended (75% input / 25% output) basis. Codestral (latest) charges $0.000000 / $0.000000 per 1M input/output tokens; OpenAI: o4 Mini charges $1.100000 / $4.400000.
| Field | Codestral (latest) | OpenAI: o4 Mini |
|---|---|---|
| Input $/Mtok | free | $1.100000 |
| Output $/Mtok | free | $4.400000 |
| Cache read $/Mtok | – | $0.275000 |
| Cache write $/Mtok | – | – |
| Input $/Mchar | 0.000000 | 0.309885 |
| Output $/Mchar | 0.000000 | 1.239541 |
| Context window | 256000 | 200000 |
| Tokenizer | mistral | o200k |
| Confidence? | aggregator | api |
| Source | litellm | openrouter |
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
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.
| Workload | Codestral (latest) | OpenAI: o4 Mini |
|---|---|---|
| Coding agent | $0.00 | $12.65 |
| RAG chat | $0.00 | $15.95 |
| Summarisation (batch) | $0.00 | $14.30 |
| Classification | $0.00 | $11.66 |
| Chat assistant | $0.00 | $24.20 |
| Content generation | $0.00 | $37.40 |
Cite this page
Codestral (latest) vs OpenAI: o4 Mini: $0.000000/$0.000000 vs $1.100000/$4.400000 per 1M tokens as of 2026-10-04. Token Barometer by Dejan Strbad, https://tokenbarometer.com, data CC BY 4.0. https://tokenbarometer.com/compare/mistral_codestral-2501-vs-openai_o4-mini
Codestral (latest) page | OpenAI: o4 Mini page | Open in calculator