Mistral › Ministral 3 3B 2512 › Pricing
Ministral 3 3B 2512 pricing
API list price by Mistral · same on lab-mistral, mistralai · checked Oct 23, 2026
$0.10 / $0.10per 1M tokens in / out
$0.01cache read · −90%
$0.008per task?
#233on OpenRouter by tokens · 5.2B / week
Price sheetper 1M tokens
| Input | $0.10 | list |
| Output | $0.10 | |
| Cache read | $0.01 | −90% vs input |
| Context · max output | 131K · 105K | tokens |
Where to buy3 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| lab-mistral | $0.10 | $0.10 | — |
| Mistrallab | $0.10 | $0.10 | 131K |
| mistralai | $0.10 | $0.10 | — |
In Mistral's line-upper 1M in / out
| Mistral 7B Instruct v0.1 | $0.055 / $0.055 | −45% |
| Mistral 7B Instruct v0.2 | $0.055 / $0.055 | −45% |
| Mistral Small 3 | $0.05 / $0.08 | −42% |
| Ministral 3 3B 2512 | $0.10 / $0.10 | this model |
| Ministral 3 8B 2512 | $0.15 / $0.15 | +50% |
| Mistral Nemo | $0.15 / $0.15 | +50% |
| Mistral Small 3.1 (25.03) | $0.10 / $0.30 | +50% |
Cheaper for the same workvs Ministral 3 3B 2512
| Ling 3.0 Flash VL thinkingOpen | -10% | score ×5.1 | $0.06 / $0.18 |
| Ling 3.0 Flash Fin thinkingOpen | -10% | score ×4.7 | $0.06 / $0.18 |
| GPT-6 Luna low | -42% | score ×4.4 | $0.005 |
| Ling 3.0 Flash thinkingOpen | -10% | score ×4.2 | $0.06 / $0.18 |
| Qwen 3.5 9B non-thinkingOpen | -8% | score ×2.7 | $0.08 / $0.13 |
Pricing questions
How much does Ministral 3 3B 2512 cost?›
$0.10 per 1M input tokens and $0.10 per 1M output tokens on Mistral's API and lab-mistral, mistralai. Cached input is $0.01. One Intelligence Index task costs about $0.008 at the default effort.
Is Ministral 3 3B 2512 free to use?›
There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.
How much does prompt caching save?›
Cache reads cost $0.01 per 1M, 90% below the input price.
What is a cheaper alternative to Ministral 3 3B 2512?›
Ling 3.0 Flash VL at thinking effort costs -10% per task with a score ×5.1 on Humanity's Last Exam.