Codestral (latest) vs OpenAI: GPT-5 Mini
Codestral (latest) is cheaper than OpenAI: GPT-5 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: GPT-5 Mini charges $0.250000 / $2.000000.
| Field | Codestral (latest) | OpenAI: GPT-5 Mini |
|---|---|---|
| Input $/Mtok | $0.000000 | $0.250000 |
| Output $/Mtok | $0.000000 | $2.000000 |
| Cache read $/Mtok | – | $0.025000 |
| Cache write $/Mtok | – | – |
| Input $/Mchar | 0.000000 | 0.070428 |
| Output $/Mchar | 0.000000 | 0.563428 |
| Context window | 256000 | 400000 |
| Tokenizer | mistral | o200k |
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: GPT-5 Mini |
|---|---|---|
| Coding agent | $0.00 | $3.38 |
| RAG chat | $0.00 | $5.13 |
| Summarisation (batch) | $0.00 | $4.25 |
| Classification | $0.00 | $2.85 |
| Chat assistant | $0.00 | $9.50 |
| Content generation | $0.00 | $16.50 |
Cite this page
Codestral (latest) vs OpenAI: GPT-5 Mini: $0.000000/$0.000000 vs $0.250000/$2.000000 per 1M tokens, as of 2026-10-04 (Token Barometer, https://tokenbarometer.com/compare/mistral_codestral-2501-vs-openai_gpt-5-mini).
Codestral (latest) page | OpenAI: GPT-5 Mini page | Open in calculator