Get Pass

Mistral: Ministral 3 14B 2512

mistralai/ministral-14b-2512
CompareAPITry this model

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart.

Modalities
In / out per 1M$0.20 / $0.20
Context256K
ReleasedDec 2, 2025

Providers

3 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Mistraleu$0.22$0.22$0.020.31s72 tps100%
Mistral$0.20$0.20$0.020.37s76 tps99.79%
Mistral$0.20$0.20$0.020.35s68 tps99.71%

Market-wide measurements, refreshed every 15 minutes. They describe who serves Ministral 3 14B 2512 in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Ministral 3 14B 2512 costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.20
per 1M tokens
Output
$0.20
per 1M tokens
Cache read
$0.02
per 1M cached tokens
Included in every pass
Ministral 3 14B 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 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AMOct 14, 4 PMOct 15, 12 AMOct 15, 8 AM
Mistral Mistral Mistral (eu)
0 tok/s100 tok/s200 tok/s300 tok/s400 tok/s
Oct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AMOct 14, 4 PMOct 15, 12 AMOct 15, 8 AM
Mistral Mistral Mistral (eu)

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.91%
Oct 12, 4:00 PMNow
Availability over the last 24 hoursAvailability 99.96%
100% 98% 97% 95%
Oct 14, 4:10 PMNow

Apps

Tools that most often run Ministral 3 14B 2512, by tokens this week.

PR generation30.9% of tokens284.8MTesis_Data exploratory screening26.7% of tokens245.8MOpenClawPersonal Agent · 18.3% of tokens168.7MClaude CodeCli Agent · 15.3% of tokens140.9MAutoNord8.8% of tokens81.1M

Activity

13.6B tokens processed market-wide in the last month.

0500.0M1.0B1.5B2.0B
Sep 15Sep 20Sep 25Sep 30Oct 5Oct 10Oct 15
Tokens

FAQ

Which model id do I use for Ministral 3 14B 2512?
mistralai/ministral-14b-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 14B 2512 hold?
262,144 tokens per request, of which up to 209,715 can be the response.
What can it accept and return?
Input: text, image. Output: text.
What does Ministral 3 14B 2512 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.20 per 1M input tokens and $0.20 per 1M output tokens.
Who built Ministral 3 14B 2512?
Mistral, in the Ministral family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion