Mistral: Devstral 2 2512✓ Catalog verified
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. Devstral 2 supports exploring codebases and orchestrating changes across multiple files while maintaining architecture-level context. It tracks framework dependencies, detects failures, and retries with corrections—solving challenges like bug fixing and modernizing legacy systems. The model can be fine-tuned to prioritize specific languages or optimize for large enterprise codebases. It is available under a modified MIT license.
Overview
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. Devstral 2 supports exploring codebases and orchestrating changes across multiple files while maintaining architecture-level context. It tracks framework dependencies, detects failures, and retries with corrections—solving challenges like bug fixing and modernizing legacy systems. The model can be fine-tuned to prioritize specific languages or optimize for large enterprise codebases. It is available under a modified MIT license.
Access: available through the official Mistral AI API. Context window: 262K.
Specifications
| API identifier | mistralai/devstral-2512 |
| Provider | Mistral AI |
| Model type | Text LLM |
| Context window | 262K catalog |
| Input modalities | text |
| Output modalities | text |
| Released | Dec 9, 2025 |
| Tokenizer | Mistral |
| Moderated | No |
| Architecture modality | text->text |
API defaults
{
"top_p": null,
"temperature": 0.3,
"frequency_penalty": null
}Pricing
Live pricing components for mistralai/devstral-2512 as published in the catalog.
| Pricing component | Raw unit price | Normalized | Unit |
|---|---|---|---|
| Prompt tokens | $4e-7 | $0.40 / 1M | Per input token |
| Completion tokens | $0.000002 | $2.00 / 1M | Per output token |
| Request fee | N/A | N/A | Per request |
| Image fee | N/A | N/A | Per image unit |
| Web search fee | N/A | N/A | Per search request |
Cost calculator
Estimate monthly spend from your own token volumes.
Estimated Total Cost
$0.6Calculated from current list pricing in the ModelsAtlas catalog.Capabilities
| Capability | Status | What it means |
|---|---|---|
| Visual Understanding | Not advertised | Image and document analysis support |
| Audio Processing | Not advertised | Speech and voice aligned flows |
| Tool Calling | ✓ Supported | Supports tools / function calling |
| Self-Hosting | ✓ Supported | Deploy outside managed APIs |
Capability signals
Directional signals derived from model metadata and capability tags — not official benchmark submissions.
Quick start
Call Mistral: Devstral 2 2512 through an OpenAI-compatible client.
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="YOUR_API_KEY"
)
response = client.chat.completions.create(
model="mistralai/devstral-2512",
messages=[{"role": "user", "content": "Explain quantum physics."}]
)
print(response.choices[0].message.content)Alternatives
Closest models by context window from a different provider.
| Model | Provider | Context | Input /1M | Actions |
|---|---|---|---|---|
| ByteDance Seed: Seed 1.6 | Bytedance Seed | 262K | $0.25 | View → |
| ByteDance Seed: Seed 1.6 Flash | Bytedance Seed | 262K | $0.07 | View → |
Sources & attribution
Pricing and metadata are maintained in the ModelsAtlas catalog.
Frequently asked questions
How much does Mistral: Devstral 2 2512 cost?
$0.40 per 1M input tokens and $2.00 per 1M output tokens on the official Mistral AI API.
What is the context window of Mistral: Devstral 2 2512?
Mistral: Devstral 2 2512 supports up to 262K tokens of context.
Does Mistral: Devstral 2 2512 support tool / function calling?
Yes, Mistral: Devstral 2 2512 supports tool / function calling — you can register tools and the model will emit structured tool calls.
How do I access Mistral: Devstral 2 2512?
Use the official Mistral AI API with the model id `mistralai/devstral-2512`. See the Quick start section above for code examples.