One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.20 = $0.20
- Output0.1M x $0.20 = $0.02
$0.22per session
Mistral AI - Open weights
Ministral 3 14B pricing and specs
Ministral 3 14B is an open-weights model from Mistral AI that costs $0.20 per 1M input tokens and $0.20 per 1M output tokens on the first-party API, with a 256K-token context window.
Last verified from docs.mistral.ai. All sources
- Input / 1M
- $0.20
- Output / 1M
- $0.20
- Context
- 256K tokens
- Weights
- Open
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| Input | $0.20 |
| Output | $0.20 |
| Cache read | $0.02 |
| Batch inputBatch requests | $0.10 |
| Batch outputBatch requests | $0.10 |
Note: Batch prices come from the pricing page's Batch mode, which applies a factor of 0.5 to standard prices. Priority Tier adds 75% and regional inference adds 10%. The docs give the context only as '256k', and the Vercel AI Gateway lists 262144. No primary page states a max output. Base and Reasoning weights are also published (Ministral-3-14B-Base-2512, Ministral-3-14B-Reasoning-2512), all Apache 2.0. The model card is dated December 2, 2025; release date uses the changelog date (December 1).
Specs
- Context window
- 256,000 tokens
- Release date
- Provider
- Mistral AI
- API model id
ministral-14b-2512- Vercel AI Gateway id
mistral/ministral-14b- Weights
- Open weights
- License
- Apache 2.0
- Weights download
- huggingface.co
What Ministral 3 14B costs in practice
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
A chat app
10,000 requests a day at 2K input and 500 output tokens each.
- Input20M x $0.20 = $4.00
- Output5M x $0.20 = $1.00
$5.00per day
$150.00 per 30-day month
The same session at a 90% cache hit
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
- Cached input0.9M x $0.02 = $0.018
- Uncached input0.1M x $0.20 = $0.02
- Output0.1M x $0.20 = $0.02
$0.058per session
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Ministral 3 14B (this page) | $0.20 | $0.20 |
| Hy-MT2-LiteTencent | $0.044 | $0.177 |
| Amazon Nova LiteAmazon | $0.06 | $0.24 |
| Command R7BCohere | $0.0375 | $0.15 |
| Ministral 3 8BMistral AI | $0.15 | $0.15 |
| Ministral 3 3BMistral AI | $0.10 | $0.10 |
| Mistral Small 4Mistral AI | $0.15 | $0.60 |
| Codestral 25.08Mistral AI | $0.30 | $0.90 |
| Mistral Large 3Mistral AI | $0.50 | $1.50 |
| Mistral Large 4Mistral AI | $1.36 | $4.18 |
FAQ
How much does Ministral 3 14B cost per million tokens?
Ministral 3 14B costs $0.20 per 1M input tokens and $0.20 per 1M output tokens on Mistral AI's first-party API, per docs.mistral.ai on October 17, 2026. Per 1M tokens, cache reads cost $0.02, and the batch rate is $0.10 input and $0.10 output.
What is Ministral 3 14B's context window?
Ministral 3 14B has a 256,000-token context window.
Are Ministral 3 14B's weights open?
Yes. Ministral 3 14B's weights are published at https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512 under the Apache 2.0.
When was Ministral 3 14B released?
Mistral AI released Ministral 3 14B on December 1, 2025.
Sources
Last verified from docs.mistral.ai.
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.