o4-mini vs Magistral Medium pricing
Side-by-side LLM API pricing.o4-mini is cheaper on input ($1.10 vs $2.00 /1M), and o4-mini is cheaper on output ($4.40 vs $5.00 /1M). On a blended average, o4-mini is lower — but which wins for you depends on your input/output mix, so check the example workloads below or run the calculator.
| Attribute | o4-mini | Magistral Medium |
|---|---|---|
| Provider | OpenAI | Mistral |
| Tier | Reasoning | Reasoning |
| Status | GA | GA |
| Context window | 200K | — |
| Input /1M | $1.10 | $2.00 |
| Output /1M | $4.40 | $5.00 |
| Cached input /1M | $0.275 | — |
| Batch input /1M | $0.55 | $1.00 |
| Batch output /1M | $2.20 | $2.50 |
| Blended (avg in+out) | $2.75 | $3.50 |
| 1M in + 1M out | $5.50 | $7.00 |
| 1M in (90% cached) + 100K out | $0.7975 | $2.50 |
List prices, USD, directional. Rates are provider list prices per 1M tokens and are meant for comparison, not billing. Batch rates shown as 50% off are derived where a provider offers batch but does not publish a separate figure. Preview, promo, intro, peak/off-peak, long-context, and third-party-host prices are labeled where they apply. Token counts vary by tokenizer, so per-token price is not always a like-for-like cost. Always confirm with the provider before relying on a number. Prices as of 2026-08-03.
Which should you pick?
For a balanced job (1M input + 1M output), o4-mini costs $5.50 versus $7.00. If your prompts are large and reused, prompt caching changes the maths — the cache-heavy row above shows a 90%-cached input scenario. If your work can run asynchronously, both providers' batch rates cut the bill further where offered.
Full price matrices: o4-mini pricing → · Magistral Medium pricing → · Back to the LLM pricing hub →