# Devstral 2

Devstral 2 costs $0.4 per 1M input tokens and $2 per 1M output tokens on LLM API, with a 262K-token context window.

Model ID: `devstral-2512` · Mistral AI · Text generation · Released December 1, 2025
Deprecated.
Updated: 2026-10-13
Canonical: https://llmapi.ai/models/mistralai-devstral-2512/

- Input: $0.4 per 1M tokens
- Output: $2 per 1M tokens
- Context: 262K tokens
- Max output: 4K tokens

## Pricing

Served by Mistral AI, the only provider.

| Price | Amount | Per |
| --- | --- | --- |
| Input | $0.4 | per 1M tokens |
| Output | $2 | per 1M tokens |

**Volume pricing.** At higher monthly volume, Devstral 2 may cost less. Book a call and sales will quote a price for your usage. [Book a call with sales](https://meetings.hubspot.com/julia-andriienko/llmapi) or [Create an account first](https://app.llmapi.ai/signup).

## Features

- Tools: Yes
- Parallel tool calls: No
- Image input: No
- Reasoning: No
- Prompt caching: No
- Structured outputs: Yes
- JSON mode: Yes
- Streaming: Yes
- Web search: No

## Call Devstral 2

### Chat Completions (`POST /v1/chat/completions`)

Set LLMAPI_KEY to your LLM API key.

```python
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

response = client.chat.completions.create(
    model="devstral-2512",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
```

Docs: [Chat Completions docs](https://docs.llmapi.ai/api/v1/chat/completions)

## More from Mistral AI

- [Mistral Large 4](https://llmapi.ai/models/mistral-large-4/): $0.7 / $2.1 per 1M input / output
- [Mistral Large 3](https://llmapi.ai/models/mistralai-mistral-large-2512/): $0.5 / $1.5 per 1M input / output
- [Ministral 8B](https://llmapi.ai/models/mistralai-ministral-8b-2512/): $0.15 / $0.15 per 1M input / output

Prices synced 2026-11-09.

Next step: [Get API key](https://app.llmapi.ai/signup)