The Orchestrator › Models › Mistral AI
Mistral AI: 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. A powerful and efficient language...
Specifications
| Provider | Mistral AI |
| Model ID | mistralai/ministral-14b-2512 |
| Context window | 262K tokens (262,144) |
| Modalities | text + image → text |
| Tokenizer | Mistral |
| Router sources | OpenRouter, TrustedRouter |
| Released | 2025-12-02 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | mistralai/ministral-14b-2512 | $0.2 | $0.2 | 262K |
| standard | TrustedRouter | mistralai/ministral-14b-2512 | $0.211 | $0.211 | 262K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.211 | $0.211 | 262K |
| 2026-11-14 | $0.2 | $0.2 | 262K |
Capabilities
Vision (image input)Agentic tool useStructured outputs256K+ context windowNo content storage (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, max_tokens, presence_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p