Open vision-language model for efficient local deployment, instruction following, and tool useMinistral 3 14B by mistral is offered by 7 providers on this page. Its official list price is $0.20 per 1M tokens. No paid channel is priced below the official list price. Prices vary about 1.9× across the providers that host it.
Median output speed is 94 tokens per second, with 0.94s to the first token.
The context window is 262,144 tokens at the reference host, but hosts report different limits, from 100,000 to 262,144, so the usable window depends on the provider you pick. It supports tool use and structured output. Accepted input modalities are Text, Image, and PDF. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| MistralOfficial ministral-14b-2512 | First-party | $0.20 | $0.20 | $0.02 | — | 262,144 | 262,144 | |
| DigitalOcean mistral-3-14B | Cloud | $0.20 | $0.20 | $0.04 | — | 262,144 | 128,000 | |
| NanoGPT mistralai/ministral-14b-instruct-2512 | Gateway | $0.20 | $0.20 | $0.02 | — | 262,144 | 32,768 | |
| Amazon Bedrock mistral.ministral-3-14b-instruct | Cloud | $0.20 | $0.20 | — | — | 128,000 ⚠ | 4,096 | |
| LowRouter auto/mistralai/ministral-14b-2512 | Gateway | $0.21 | $0.21 | $0.021 | — | 262,144 | 262,144 | |
| Eden AI infomaniak/mistralai/Ministral-3-14B-Instruct-2512 | Gateway | $0.33 | $0.44 | — | — | 100,000 ⚠ | 100,000 | |
| Infomaniak mistralai/Ministral-3-14B-Instruct-2512 | Cloud | $0.37 | $0.50 | — | — | 100,000 ⚠ | 25,600 | beta |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.