Mistral › Ministral 3 8B 2512 › Pricing
Ministral 3 8B 2512 pricing
API list price by Mistral · same on lab-mistral, mistralai · checked Oct 23, 2026
$0.15 / $0.15per 1M tokens in / out
$0.015cache read · −90%
$0.011per task?
#236on OpenRouter by tokens · 4.8B / week
Price sheetper 1M tokens
| Input | $0.15 | list |
| Output | $0.15 | |
| Cache read | $0.015 | −90% vs input |
| Context · max output | 262K · 210K | tokens |
Where to buy3 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| lab-mistral | $0.15 | $0.15 | — |
| Mistrallab | $0.15 | $0.15 | 262K |
| mistralai | $0.15 | $0.15 | — |
In Mistral's line-upper 1M in / out
| Mistral 7B Instruct v0.2 | $0.055 / $0.055 | −63% |
| Mistral Small 3 | $0.05 / $0.08 | −62% |
| Ministral 3 3B 2512 | $0.10 / $0.10 | −33% |
| Ministral 3 8B 2512 | $0.15 / $0.15 | this model |
| Mistral Nemo | $0.15 / $0.15 | 0% |
| Mistral Small 3.1 (25.03) | $0.10 / $0.30 | 0% |
| Ministral 3 14B 2512 | $0.20 / $0.20 | +33% |
Cheaper for the same workvs Ministral 3 8B 2512
| Ling 3.0 Flash VL thinkingOpen | -40% | score ×4.5 | $0.06 / $0.18 |
| Ling 3.0 Flash Fin thinkingOpen | -40% | score ×4.1 | $0.06 / $0.18 |
| GPT-6 Luna low | -59% | score ×3.9 | $0.005 |
| GPT-5.6 Luna low | -11% | score ×3.8 | $0.01 |
| Ling 3.0 Flash thinkingOpen | -40% | score ×3.7 | $0.06 / $0.18 |
Pricing questions
How much does Ministral 3 8B 2512 cost?›
$0.15 per 1M input tokens and $0.15 per 1M output tokens on Mistral's API and lab-mistral, mistralai. Cached input is $0.015. One Intelligence Index task costs about $0.011 at the default effort.
Is Ministral 3 8B 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 $0.015 per 1M, 90% below the input price.
What is a cheaper alternative to Ministral 3 8B 2512?›
Ling 3.0 Flash VL at thinking effort costs -40% per task with a score ×4.5 on Humanity's Last Exam.