Mistral

Ministral 3 14B

AI model by Mistral. Real-time pricing and benchmark data.

Pricing (per 1M tokens)

Input$0.20
Output$0.20
Blended (3:1)$0.20

Source: Artificial Analysis

Performance

Output Speed85 tok/s
Time to First Token960ms

Median values from Artificial Analysis

Editorial Analysis

Profile. Ministral 3 14B is a budget-tier option from Mistral at $0.20/M output tokens. Despite the low price, it scores competitively on Coding Index (14.4) and Intelligence Index (11.2) — making it a candidate for high-volume production workloads where unit cost dominates.

Latency. On latency, Ministral 3 14B reports 85 tok/s output speed and 960ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.

Cost model. For a workload of 1M input tokens + 100K output tokens, Ministral 3 14B costs $0.22 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.

Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.

Compare with similar models

ModelInputOutputSpeed
Ministral 3 14BCurrent
$0.20$0.2085 tok/s
gpt-oss-20b (low)
$0.07$0.20170 tok/s
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
$0.05$0.20225 tok/s
Qwen3.5 9B (Reasoning)
$0.14$0.2081 tok/s
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
$0.05$0.20168 tok/s
Qwen2.5 Turbo
$0.05$0.20108 tok/s

Example Costs

Single Request
$0.0003
1.0K in / 500 out
1K Requests/day
$0.3000
1.0M in / 500.0K out
10K Requests/day
$3.00
10.0M in / 5.0M out