Devstralon your own GPUs.

Devstral as your private coding model. Repositories and prompts stay inside your network, and your IDE tools point at an OpenAI-compatible endpoint you control.

Start the $4,900 pilot Compare all models

24B

LLM_Deploy

Card no. LD-101Issued 2026-10-27Mistral AI

Devstral Small 2

Pilot $4,900 fixed

Sizes: 24B dense
Active params: All parameters (dense)
Context: 256K
Licence: Apache 2.0
Fits on: 1× T4 16GB at 4-bit, 1× RTX 5090 32GB at FP8
Endpoint: llm.yourcompany.internal/v1
Egress: 0
Owner: YOU

The 72-hour pilot with Devstral.

$4,900 fixed. One model, 24B parameters: an estimated 28.8 GB at FP8, so it fits on 1× T4 16GB at 4-bit.

Live on your data

72 h$4,900 fixed

Devstral live on your data in 72 hours. The clock starts after access and prerequisites.

Your endpoint

/v1OpenAI-compatible

OpenAI-compatible endpoint. Your applications switch by changing the base URL.

Your hardware

1× T4 16GB at 4-bit, 1× RTX 5090 32GB at FP8

The readout

Evalon your data

Reference evaluation on your data. Readout and production scoping.

We size the hardware and source it at cost, with no markup. Ballpark: one H100 80GB ≈ $25–30k; a 4×H100 node ≈ $180–240k; smaller models run on far less.

Same SDK. Change the base URL.

The model is one parameter. Everything else in your application stays as it is.

client = OpenAI(
    base_url="https://llm.yourcompany.internal/v1",   # inside your network
    api_key="your-key",
)
reply = client.chat.completions.create(
    model="devstral-small-2",
    messages=[{"role": "user", "content": "Summarise this contract."}],
)