Mistral: Ministral 3 3B 2512
mistralai/ministral-3b-2512The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
Modalities
In / out per 1M$0.10 / $0.10
Context128K
ReleasedDec 2, 2025
Providers
3 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.10 | $0.10 | $0.01 | 0.36s | 102 tps | 100% | |
| $0.10 | $0.10 | $0.01 | 0.36s | 91 tps | 100% | |
| $0.11 | $0.11 | $0.01 | 1.13s | 118 tps | 100% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Ministral 3 3B 2512 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Ministral 3 3B 2512 costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.10
per 1M tokens
Output
$0.10
per 1M tokens
Cache read
$0.01
per 1M cached tokens
Included in every pass
Ministral 3 3B 2512 is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s1.0s2.0s3.0s4.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Mistral Mistral Mistral (eu)
0 tok/s200 tok/s400 tok/s600 tok/s800 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Mistral Mistral Mistral (eu)
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.99%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 100%
100% 98% 97% 95%
Oct 13, 2:50 PMNow
Apps
Tools that most often run Ministral 3 3B 2512, by tokens this week.
Activity
16.0B tokens processed market-wide in the last month.
0250.0M500.0M750.0M1.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for Ministral 3 3B 2512?
mistralai/ministral-3b-2512. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Ministral 3 3B 2512 hold?
131,072 tokens per request, of which up to 104,857 can be the response.
What can it accept and return?
Input: text, image. Output: text.
What does Ministral 3 3B 2512 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.10 per 1M input tokens and $0.10 per 1M output tokens.
Who built Ministral 3 3B 2512?
Mistral, in the Ministral family.
Explore
Other models your pass can call.


