Mistral Medium 3.5
StableMistral AI · Released 2026-05 · mistralai/mistral-medium-3-5
Overview
Efficient model from Mistral AI combining strong European-language coverage, coding ability and low-latency serving. Mistral Medium 3.5 supports up to 262K tokens of context, native vision input, and an extended reasoning mode. Served through the FirmLink unified API with OpenAI-compatible endpoints.
Function CallingJSON ModeStreamingReasoningTextVision
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/mistral-medium-3-5",
"messages": [{"role": "user", "content": "Hello!"}]
}'Related models
Mistral AI
Mistral Small (2603)
Function CallingJSON ModeStreamingVision
262K context
$0.15 / $0.60per 1M tok in / out
View details
Mistral AI
Mistral Large (2512)
Function CallingJSON ModeStreamingVision
262K context
$0.50 / $1.50per 1M tok in / out
View details
Mistral AI
Devstral (2512)
Function CallingJSON ModeStreaming
262K context
$0.40 / $2.00per 1M tok in / out
View details
Mistral AI
Ministral 14B (2512)
Function CallingJSON ModeStreaming
262K context
$0.20 / $0.20per 1M tok in / out
View details
Mistral Medium 3.5 is provided by Mistral AI and served through the FirmLink gateway. Availability and limits follow the provider's terms.