Devstral Small 2 24B Instruct 2512
evroc/devstral-small-2-24b-instruct-2512От evroc · семейство: devstral · выпуск 2025-12-01
⚠ Это сообществом дообученная / производная модель — не официальный релиз вендора.
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.
Coding41
- Tool calling40/40
- Structured output0/20
- Reasoning0/10
- Context window (100K → 1M)0/20
- Provider availability1/10
Agents51
- Tool calling35/35
- Structured output0/25
- Reasoning0/15
- Output token limit15/15
- Provider availability1/10
JSON / structured output39
- Structured output / JSON mode0/50
- Tool calling20/20
- Temperature control0/10
- Price-friendly for high-volume19/20
Cost efficiency68
- Headline price (log-scaled)68/95
- Has prompt-cache pricing0/5
Long context0
- Context ≥ 100K0/100
Production-readiness50
- Number of independent providers5/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers10/10
- Official model (not derivative)0/15
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 | $0.84 < $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 | $1.67 < $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 | $0.47 < $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 | $1.43 < $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 | $1.72 < $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 evroc · mistralai/devstral-small-2-24b-instruct-2512
Доступна у 1 провайдеров
| Провайдер | ID модели провайдера | Вход / 1M | Выход / 1M | Контекст | Выпуск |
|---|---|---|---|---|---|
| evroc evroc | mistralai/devstral-small-2-24b-instruct-2512 | $0.120 | $0.470 | 33K | 2025-12-01 |
Frequently asked questions
How much does Devstral Small 2 24B Instruct 2512 cost?
Devstral Small 2 24B Instruct 2512 costs $0.120 per 1M input tokens and $0.470 per 1M output tokens, sourced from evroc. 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 Small 2 24B Instruct 2512?
Devstral Small 2 24B Instruct 2512 has a context window of 33K tokens, with a max output of 33K tokens per reply. This is the total combined size of prompt + completion.
Does Devstral Small 2 24B Instruct 2512 support tool calling?
Yes. Devstral Small 2 24B Instruct 2512 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 Small 2 24B Instruct 2512 support structured output / JSON mode?
Support for structured output / JSON-schema-constrained decoding is not reported for Devstral Small 2 24B Instruct 2512 in our data source. Verify with evroc's official documentation before relying on it in production.
Can Devstral Small 2 24B Instruct 2512 accept image input?
No. Devstral Small 2 24B Instruct 2512 only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is Devstral Small 2 24B Instruct 2512 open-weight?
Yes. Devstral Small 2 24B Instruct 2512'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 Small 2 24B Instruct 2512?
If Devstral Small 2 24B Instruct 2512 doesn't fit, consider KB Whisper, E5 Multi-Lingual Large Embeddings 0.6B. 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 evroc models
- KB Whisper$0.00 in / $0.00 out
- E5 Multi-Lingual Large Embeddings 0.6B$0.12 in / $0.12 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.