Devstral 2 2512 API Pricing
Mistral · context window 262K · prices updated 2026-09-15
Where Devstral 2 2512 sits on price
At $2.00 per million output tokens, Devstral 2 2512 is a mid tier model — right at the median output price of $2.08, which puts it cheaper than 53% and pricier than 47% of the models we track. It sits 18th cheapest of the 25 Mistral models we track. Output costs 5.0× input, the usual spread — trim both, starting with the answer length.
Cached input is 90% cheaper. On an input-heavy workload you need roughly a 28% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.
What real workloads cost on Devstral 2 2512
These three workloads are the ones teams actually run on a mid-priced model — a $2.00/1M 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. | $0.0048 | $72.00 |
| Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. | $0.0022 | $660 |
| Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. | $0.0005 | $15.00 |
Model your exact traffic in the API cost calculator — it preloads Devstral 2 2512 with caching and batch options.
Devstral 2 2512 price history
Mistral last cut Devstral 2 2512's output price on Aug 31, 2026 (-9% per output token), from $0.44/$2.20 to $0.4/$2.00 per 1M in/out. That is the only repricing in the 21 days we have tracked it — worth knowing before you hard-code today's rate into a budget.
| Date | Input /1M | Output /1M | Output change |
|---|---|---|---|
| Aug 25, 2026 (tracking began) | $0.44 | $2.20 | — |
| Aug 31, 2026 | $0.4 | $2.00 | -9% |
Change-points from our daily price snapshots (tracking since Aug 25, 2026; intraday moves between snapshots are not captured).
Devstral 2 2512 vs Qwen3.6 27B
The closest-priced alternative from another vendor is Qwen3.6 27B (Alibaba (Qwen)) — priced within a rounding error on output, with $0.1 less per million input tokens. 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 Qwen3.6 27B pricing →Cheaper alternatives
More Mistral models
Frequently asked questions
› How much does the Devstral 2 2512 API cost?
Devstral 2 2512 costs $0.4 per million input tokens and $2.00 per million output tokens, with cached input at $0.04 per million (90% cheaper). That works out to roughly 500,000 output tokens per dollar.
› What does the support chatbot workload cost on Devstral 2 2512?
Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0048 per request and $72.00 per month on Devstral 2 2512. Conversation history re-sent each turn — the classic prompt-caching win.
› What does it cost to fill Devstral 2 2512's 262K context window?
Sending 262K of input in a single request costs $0.1049 at $0.4 per million tokens — before any output. With prompt caching that same fill drops to about $0.0105 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.
› Is Devstral 2 2512 worth the price?
Devstral 2 2512 sits in the middle of the market (18 of 25 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.