Codestral (latest) vs GPT-5 Mini
Codestral (latest) is cheaper than GPT-5 Mini by about 56% on a blended (75% input / 25% output) basis. Codestral (latest) charges $0.20 / $0.60 per 1M input/output tokens; GPT-5 Mini charges $0.25 / $2.00.
| Field | Codestral (latest) | GPT-5 Mini |
|---|---|---|
| Input $/Mtok | $0.20 | $0.25 |
| Output $/Mtok | $0.60 | $2.00 |
| Cache read $/Mtok | – | $0.0250 |
| Cache write $/Mtok | – | – |
| Input $/Mchar | 0.0711 | 0.0704 |
| Output $/Mchar | 0.21 | 0.56 |
| Context window | 256000 | 400000 |
| 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) | GPT-5 Mini |
|---|---|---|
| Coding agent | $2.20 | $3.38 |
| RAG chat | $2.60 | $5.13 |
| Summarisation (batch) | $2.40 | $4.25 |
| Classification | $2.08 | $2.85 |
| Chat assistant | $3.60 | $9.50 |
| Content generation | $5.20 | $16.50 |
Cite this page
Codestral (latest) vs GPT-5 Mini: $0.20/$0.60 vs $0.25/$2.00 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_gpt-5-mini
Codestral (latest) page | GPT-5 Mini page | Open in calculator