Devstral 2
mistral/devstral-2512От Mistral · семейство: devstral · выпуск 2025-12-09 · дата знаний: 2025-12
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Возможности
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding53
- Tool calling40/40
- Structured output0/20
- Reasoning0/10
- Context window (100K → 1M)8/20
- Provider availability5/10
Agents55
- Tool calling35/35
- Structured output0/25
- Reasoning0/15
- Output token limit15/15
- Provider availability5/10
JSON / structured output45
- Structured output / JSON mode0/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume15/20
Cost efficiency53
- Headline price (log-scaled)53/95
- Has prompt-cache pricing0/5
Long context61
- Context window (100K → 2M)51/90
- Has published price for full window10/10
Production-readiness81
- Number of independent providers25/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers6/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $3.00 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $6.00 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $1.80 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $5.20 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $6.00 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Детализация цен
Рекомендованная цена от mistral · devstral-2512
Самый дешёвый провайдер: cortecs · Unknown вход + Unknown выход
Доступна у 5 провайдеров
| Провайдер | ID модели провайдера | Вход / 1M | Выход / 1M | Контекст | Выпуск |
|---|---|---|---|---|---|
| Mistral mistral | devstral-2512 | $0.400 | $2.00 | 262K | 2025-12-09 |
| OpenRouter openrouter | mistralai/devstral-2512 | $0.150 | $0.600 | 262K | 2025-09-12 |
| Kilo Gateway kilo | mistralai/devstral-2512 | $0.400 | $2.00 | 262K | 2025-09-12 |
| Cortecs cortecs | devstral-2512 | Unknown | Unknown | 262K | 2025-12-09 |
| LLM Gateway llmgateway | devstral-2512 | $0.400 | $2.00 | 262K | 2025-12-09 |
Расхождения данных между провайдерами
- context_window varies: 262000, 262144
- release_date varies (span 88d): 2025-09-12, 2025-12-09
Провайдеры сообщают разные значения для этой модели. Сводка выше использует репрезентативного провайдера; детали — в таблице.
Frequently asked questions
How much does Devstral 2 cost?
Devstral 2 costs $0.400 per 1M input tokens and $2.00 per 1M output tokens, sourced from mistral. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Devstral 2?
Devstral 2 has a context window of 262K tokens, with a max output of 262K tokens per reply. This is the total combined size of prompt + completion.
Does Devstral 2 support tool calling?
Yes. Devstral 2 supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does Devstral 2 support structured output / JSON mode?
Support for structured output / JSON-schema-constrained decoding is not reported for Devstral 2 in our data source. Verify with Mistral's official documentation before relying on it in production.
Can Devstral 2 accept image input?
No. Devstral 2 only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is Devstral 2 open-weight?
Yes. Devstral 2's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to Devstral 2?
If Devstral 2 doesn't fit, consider Mistral Nemo Instruct 2407, Mistral Nemo, Mistral Large 2.1. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More Mistral models
- Mistral Nemo Instruct 2407$0.02 in / $0.04 out
- Mistral Nemo$0.15 in / $0.15 out
- Mistral Large 2.1$2.00 in / $6.00 out
- Mistral Large 3$0.50 in / $1.50 out
- Mistral Small 3.2 24B Instruct (2506)$0.10 in / $0.31 out
Capability lists this model is in
Последнее обновление:
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.