All models

Devstral (2512)

Stable

Mistral AI · Released 2025-12 · mistralai/devstral-2512

Overview

Efficient model from Mistral AI combining strong European-language coverage, coding ability and low-latency serving. Devstral (2512) supports up to 262K tokens of context. Served through the FirmLink unified API with OpenAI-compatible endpoints.

Function CallingJSON ModeStreamingText

API example

Fully OpenAI-compatible — just change the model field.

curl https://api.firmlinktech.com/v1/chat/completions \
  -H "Authorization: Bearer $FIRMLINK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/devstral-2512",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Pricing

Input$0.40 /1M
Output$2.00 /1M
Context window262K
Max output16K
Devstral (2512) is provided by Mistral AI and served through the FirmLink gateway. Availability and limits follow the provider's terms.