Ministral 3 3B pricing, context window and limits
Ministral 3 3B costs $0.1 per million input tokens and $0.1 per million output tokens at Mistral AI list price. It accepts up to 131,072 tokens of context and returns up to 262,144 tokens.
- Model id
ministral-3b-2512 - Snapshot
What does Ministral 3 3B cost?
| Input | $0.1 |
|---|---|
| Output | $0.1 |
| Cached input (read) | $0.01 |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can Ministral 3 3B read and write?
| Context window | 131,072 |
|---|---|
| Max output | 262,144 |
What can Ministral 3 3B do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | No |
| Input | text, image |
| Output | text |
What does a request to Ministral 3 3B cost?
| A typical request: 1,000 tokens in, 500 out | $0.00015 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.0011 |
| 1,000 typical requests | $0.15 |
| 1 million tokens in and 1 million out | $0.2 |
Input read from the provider's prompt cache costs $0.01 per million tokens instead of $0.1, 90% less. A request that repeats a 1,000-token prompt from the cache costs under $0.0001 instead of $0.00015.
Among 40 Mistral AI models with a published price, Ministral 3 3B is the 4th cheapest by input price. Its context window is the 23rd largest of 40. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Ministral 3 3B through DVARA?
Configure the mistral provider in the DVARA LLM Gateway and send the model id ministral-3b-2512. DVARA, the AI governance platform, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set is counted as costing nothing. Every cost record says which price it used.
What should I check before relying on this data?
The weekly review marked this entry. A person saw each mark and kept the model listed.
- The listed context window is smaller than the listed output limit.
Which other Mistral AI models are there?
- Ministral 3 14B$0.2 in · $0.2 out · 262K context
- Ministral 3B (latest)$0.04 in · $0.04 out · 131K context
- Ministral 3 8B$0.15 in · $0.15 out · 262K context
- Ministral 8B (latest)$0.1 in · $0.1 out · 262K context
- Magistral Medium (latest)$2 in · $5 out · 262K context
- Leanstral 1.5$0 in · $0 out · 262K context
- Devstral Small 2$0 in · $0 out · 256K context
- Mistral Embed$0.1 in · $0 out · 8K context
- GLM-5.2$1.4 in · $4.4 out · 1.05M context
- Mistral Large 2.1$2 in · $6 out · 131K context
- Devstral Small$0.1 in · $0.3 out · 128K context
- Mistral Large 3$0.5 in · $1.5 out · 262K context
Which models from other providers are similar to Ministral 3 3B?
These are the closest in context window and input price, one per provider.
- Qwen3-VL 30B-A3BAlibaba Qwen · $0.108 in · $0.431 out · 131K context
- Gemma 3 12B ITAmazon Bedrock · $0.09 in · $0.29 out · 131K context
- GPT OSS 20BGroq · $0.075 in · $0.3 out · 131K context
- Command RCohere · $0.15 in · $0.6 out · 128K context
- GPT-4o miniOpenAI · $0.15 in · $0.6 out · 128K context