Pixtral Large 2502 API Pricing
Mistral · context window 128K · prices updated 2026-11-22
Where Pixtral Large 2502 sits on price
At $6.00 per million output tokens, Pixtral Large 2502 is a premium tier model — 2.4× the median output price of $2.50, which puts it cheaper than 34% and pricier than 66% of the models we track. It sits 18th cheapest of the 22 Mistral models we track. Output is only 3.0× the input price, an unusually flat spread: long prompts hurt about as much as long answers, so prompt size is where the savings are.
What real workloads cost on Pixtral Large 2502
These three workloads are the ones teams actually run on a premium-priced model — a $6.00/1M model is not bought for the same job as one ten times the price.
| Workload | Per request | Per month |
|---|---|---|
| Support chatbot — 500 conversations/day (5K in / 1.4K out) Conversation history re-sent each turn — the classic prompt-caching win. | $0.0184 | $276 |
| Coding agent — 300 sessions/day (60K in / 12K out) Multi-step loops re-read the same files; caching matters more than raw price. | $0.192 | $1728 |
| Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. | $0.0019 | $57.00 |
Model your exact traffic in the API cost calculator — it preloads Pixtral Large 2502 with caching and batch options.
Pixtral Large 2502 price history
Pixtral Large 2502's price has not moved since we began tracking it on Nov 20, 2026 — 2 days of stability in a market where 113 of the 400 models we track have repriced over the same period, including 6 of Mistral's own 22 models.
Change-points from our daily price snapshots (tracking since Nov 20, 2026; intraday moves between snapshots are not captured).
Pixtral Large 2502 vs Qwen3.8 Max (0902)
The closest-priced alternative from another vendor is Qwen3.8 Max (0902) (Alibaba (Qwen)) — priced within a rounding error on output, with identical input pricing. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.
See Qwen3.8 Max (0902) pricing →Cheaper alternatives
More Mistral models
Frequently asked questions
› How much does the Pixtral Large 2502 API cost?
Pixtral Large 2502 costs $2.00 per million input tokens and $6.00 per million output tokens and no discounted cached-input tier. That works out to roughly 166,667 output tokens per dollar.
› What does the support chatbot workload cost on Pixtral Large 2502?
Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0184 per request and $276 per month on Pixtral Large 2502. Conversation history re-sent each turn — the classic prompt-caching win.
› What does it cost to fill Pixtral Large 2502's 128K context window?
Sending 128K of input in a single request costs $0.256 at $2.00 per million tokens — before any output. There is no cached-input tier on this model, so every repeat of that context is billed at full price. This is why large context windows are cheap to advertise and expensive to actually use.
› Is Pixtral Large 2502 worth the price?
Pixtral Large 2502 sits in the middle of the market (18 of 22 by price within Mistral). The honest test is a routing experiment: send the same 200 real requests to this model and to a tier below, and compare failure rate against the price gap — most teams find a majority of traffic never needed the pricier model.