Devstral 2 2512
About this model
Devstral 2 2512 is an AI model from Mistral AI, made available through the API on December 9, 2025. It can read up to 262,144 tokens in one request, roughly 492 pages of text, and write up to 209,715 tokens in a single answer. Besides text, it accepts files such as PDFs as input.
Through the API it costs $0.40 per million input tokens and $2 per million output tokens. Its pricing sits in the middle of the market.
It can call tools and functions, so developers can connect it to search, databases or other software. Its weights are openly published (mistralai/Devstral-2-123B-Instruct-2512), so it can also be downloaded and run on your own hardware.
Quality scores
Rankings →Not rated yet. Independent test results usually appear a few weeks after a model is released.
Where to use it
Companies that serve this model through an API: 1. Prices per million tokens, cheapest first.
Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.
Use it in your code
Call Devstral 2 2512 through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "mistralai/devstral-2512", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'import os
from openai import OpenAI
client = OpenAI(base_url="https://openrouter.ai/api/v1", api_key=os.environ["OPENROUTER_API_KEY"])
reply = client.chat.completions.create(
model="mistralai/devstral-2512",
messages=[{"role": "user", "content": "Hello! What can you do?"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://openrouter.ai/api/v1", apiKey: process.env.OPENROUTER_API_KEY });
const reply = await client.chat.completions.create({
model: "mistralai/devstral-2512",
messages: [{ role: "user", content: "Hello! What can you do?" }],
});
console.log(reply.choices[0].message.content);The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.
What it costs in practice
- 1,000 chat replies$0.80
- Summarise a 100-page document$0.022
- An app with 10,000 requests a day for a month$360
Similar-priced alternatives
| Model | Inputi | Outputi | Contexti | |
|---|---|---|---|---|
Qwen3.8 27BAlibaba Qwen | $0.42 | $3 | 1M | Compare with ⇄ |
GLM 5.3 FlashXZ.ai (Zhipu) | $0.37 | $1.25 | 1M | Compare with ⇄ |
MiMo-V2.6-ProXiaomi | $0.44 | $0.87 | 1.1M | Compare with ⇄ |
Inkling SmallThinking Machines Lab | $0.45 | $1.20 | 512K | Compare with ⇄ |
Kimi K2.5Moonshot AI | $0.45 | $2.25 | 256K | Compare with ⇄ |
Muse Glimmer 30BMeta | $0.35 | $1.50 | 128K | Compare with ⇄ |
News about Mistral AI
See all →Frequently asked questions
- How much does Devstral 2 2512 cost?
- Devstral 2 2512 costs $0.40 per million input tokens and $2 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $0.80.
- What is the context window of Devstral 2 2512?
- Devstral 2 2512 can read up to 262,144 tokens in one request, about 492 pages of text. It can write up to 209,715 tokens in a single answer.
- Is Devstral 2 2512 open source?
- Yes. Its weights are published (mistralai/Devstral-2-123B-Instruct-2512), so you can download it and run it on your own hardware, or use it through one of 1 API providers.
- Who makes Devstral 2 2512?
- Devstral 2 2512 is made by Mistral AI. It became available through the API on December 9, 2025.
- Can Devstral 2 2512 read images?
- Yes. Besides text, it accepts files such as PDFs as input.
- What are the alternatives to Devstral 2 2512?
- Models with a similar price from other companies include Qwen3.8 27B, GLM 5.3 FlashX and MiMo-V2.6-Pro. You can compare them side by side on this page.