AI model comparison
Ministral 3 14B 2512 vs Ministral 3 8B 2512
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Mistral
Ministral 3 14B 2512
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.
- Input / 1M
- $0.20
- Output / 1M
- $0.20
- Context
- 262K
Mistral
Ministral 3 8B 2512
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
- Input / 1M
- $0.15
- Output / 1M
- $0.15
- Context
- 262K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Ministral 3 8B 2512
1.3x cheaper for a typical chat
Higher intelligence score
Ministral 3 14B 2512
6 vs 5.5 on Artificial Analysis
Larger context window
Tie
262K vs 262K tokens
Newer release
Ministral 3 14B 2512
Released December 2, 2025
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Ministral 3 14B 25126Ministral 3 8B 25125.5Coding index
Ministral 3 14B 251214.4Ministral 3 8B 25129.7Agentic index
Ministral 3 14B 25121.1Ministral 3 8B 25120.6Pricing
Ministral 3 14B 2512 vs Ministral 3 8B 2512 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Ministral 3 14B 2512 | Ministral 3 8B 2512 |
|---|---|---|
| Input tokensPer 1M tokens | $0.20 | $0.15 |
| Output tokensPer 1M tokens | $0.20 | $0.15 |
| Cached input (read)Per 1M tokens | $0.02 | $0.02 |
| Cache writePer 1M tokens | Not available | Not available |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
Ministral 3 14B 2512$0.50Ministral 3 8B 2512$0.37Coding task
30K in, 4K out
Ministral 3 14B 2512$6.80$1.40 cachedMinistral 3 8B 2512$5.10$1.05 cachedLong document summary
150K in, 2K out
Ministral 3 14B 2512$30.40$3.40 cachedMinistral 3 8B 2512$22.80$2.55 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Ministral 3 14B 2512 | Ministral 3 8B 2512 |
|---|---|---|
| Context window | 262K tokens | 262K tokens |
| Max output | 210K tokens | 210K tokens |
| Input types | Image, Text | Image, Text |
| Output types | Text | Text |
| Reasoning effort levels | Not available | Not available |
| Default reasoning effort | Not available | Not available |
| Release date | December 2, 2025 | December 2, 2025 |
Features
Supported features
API features available for each model.
| Metric | Ministral 3 14B 2512 | Ministral 3 8B 2512 |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Not supported | Not supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Not supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
Ministral 3 14B 2512View full model details- Ministral 3 14B 2512 vs Qwen3 30B A3B Instruct 2507
- Ministral 3 14B 2512 vs Nova Micro 1.0
- Ministral 3 14B 2512 vs Mistral Small 3
- Ministral 3 14B 2512 vs Gemma 3 12B
- Ministral 3 14B 2512 vs Nova Lite 1.0
- Ministral 3 14B 2512 vs Saba
- Ministral 3 14B 2512 vs Reka Flash 3
- Ministral 3 14B 2512 vs Phi 4
- Ministral 3 14B 2512 vs Llama 3.2 3B Instruct
- Ministral 3 14B 2512 vs Ministral 3 3B 2512
- Ministral 3 14B 2512 vs Granite 4.0 Micro
- Ministral 3 14B 2512 vs Llama 3.2 1B Instruct
Ministral 3 8B 2512View full model details- Ministral 3 8B 2512 vs Mistral Nemo
- Ministral 3 8B 2512 vs Llama 3.1 8B Instruct
- Ministral 3 8B 2512 vs Nova Micro 1.0
- Ministral 3 8B 2512 vs Mistral Small 3
- Ministral 3 8B 2512 vs Gemma 3 12B
- Ministral 3 8B 2512 vs Ministral 3 3B 2512
- Ministral 3 8B 2512 vs Phi 4
- Ministral 3 8B 2512 vs Reka Flash 3
- Ministral 3 8B 2512 vs Granite 4.0 Micro
- Ministral 3 8B 2512 vs Gemma 3 4B
- Ministral 3 8B 2512 vs Llama 3.2 1B Instruct
Our take
Ministral 3 8B 2512 is 1.3x cheaper for a typical chat. Ministral 3 14B 2512 scores higher on the Artificial Analysis Intelligence Index (6 vs 5.5). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is Ministral 3 14B 2512 or Ministral 3 8B 2512 cheaper?
Ministral 3 8B 2512 is cheaper for a typical chat (2K input tokens and 500 output tokens). Ministral 3 8B 2512 costs $0.15 per 1M input tokens and $0.15 per 1M output tokens, while Ministral 3 14B 2512 costs $0.20 per 1M input tokens and $0.20 per 1M output tokens.
Which has a bigger context window, Ministral 3 14B 2512 or Ministral 3 8B 2512?
Ministral 3 14B 2512 supports up to 262K tokens of context, compared with 262K for Ministral 3 8B 2512.
Is Ministral 3 14B 2512 smarter than Ministral 3 8B 2512?
On the Artificial Analysis Intelligence Index, Ministral 3 14B 2512 scores 6 and Ministral 3 8B 2512 scores 5.5, putting Ministral 3 14B 2512 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Ministral 3 14B 2512 and Ministral 3 8B 2512 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Ministral 3 14B 2512 and Ministral 3 8B 2512 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Ministral 3 14B 2512 and Ministral 3 8B 2512 at the same time. Compare the answers side by side and keep the best one.