Devstral 2 2512
CodingToolsMistral · Released December 2025
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window.
It belongs to Mistral's catalog, which spans Medium and Large (capability), Small and Ministral (efficiency) and dedicated code and audio models, all with European data-residency roots.
Facts and pricing
- Provider
- Mistral
- Context window
- 262K tokens
- Input price
- 4.8 credits / 1M tokens ($0.40 raw)
- Output price
- 24.0 credits / 1M tokens ($2.00 raw)
- Vision (image input)
- No
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.
Try Devstral 2 2512 now
What Devstral 2 2512 is best for
- Writing, reviewing and refactoring code; agentic coding workflows
- Long documents: the 262K-token window holds lengthy reports, contracts or papers whole
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a coding model like Devstral 2 2512:
- Refactor this function to be testable and write the tests
- Explain what this regex does and rewrite it to be readable
- Design a database schema for a multi-tenant invoicing app
- Review this pull request diff for correctness and edge cases
Mistral family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Mistral Large 4 | 1.0M | 8.4 | 25.2 | October 2026 |
| Mistral Medium 3.5 | 262K | 18.0 | 90.0 | April 2026 |
| Mistral Medium 3.5 (batch) | 262K | 9.0 | 45.0 | April 2026 |
| Mistral Small 4 | 262K | 1.8 | 7.2 | March 2026 |
| Devstral 2 2512 | 262K | 4.8 | 24.0 | December 2025 |
| Ministral 3 14B 2512 | 262K | 2.4 | 2.4 | December 2025 |
| Ministral 3 8B 2512 | 262K | 1.8 | 1.8 | December 2025 |
| Ministral 3 3B 2512 | 131K | 1.2 | 1.2 | December 2025 |
| Mistral Large 3 2512 | 262K | 6.0 | 18.0 | December 2025 |
| Voxtral Small 24B 2507 | 33K | 1.2 | 3.6 | October 2025 |
Model comparisons
- Llama 4 Maverick vs Mistral Medium 3.5
- GPT-5.6 Luna vs Mistral Small 4
- Gemini 3.5 Flash vs Mistral Small 4
- Kimi K2.7 Code vs Codestral 2508
Frequently asked questions
- What is Devstral 2 2512?
- Devstral 2 2512 is an AI model by Mistral. Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window.
- How much does Devstral 2 2512 cost on Zeplik?
- Input tokens cost 4.8 credits per million and output tokens 24.0 credits per million (1 credit = $0.10; the raw provider rates are $0.40 and $2.00 per million). New accounts start with free credits.
- How long can a conversation with Devstral 2 2512 be?
- Devstral 2 2512 has a 262K-token context window (262,144 tokens), which covers the conversation plus any documents you attach.
- Does Devstral 2 2512 support images and tools?
- Devstral 2 2512 is text-only and supports tool calling.
Related models
Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system.
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 balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
More you can do with Devstral 2 2512
- 468 AI skillsReady-to-run expert methods for writing, data, code and more, each running on Devstral 2 2512 or any model you pick.
- 997 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.