MODELS / MISTRAL

Mistral Medium 3.1

Mistral Medium 3 delivers frontier performance while being an order of magnitude less expensive. For instance, the model performs at or above 90% of Claude Sonnet 3.7 on benchmarks across the board at a significantly lower cost.

TEXTTOOL-USEVISION
128K
CONTEXT WINDOW
64K
MAX OUTPUT TOKENS
$0.4
INPUT PRICE / 1M TOKENS
$2
OUTPUT PRICE / 1M TOKENS
QUICKSTART

Call it in one request.

OpenAI-compatible: change the base URL, and the setup is complete.

curl https://enterprise.blackbox.ai/v1/chat/completions \
  -H "Authorization: Bearer $BLACKBOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "blackboxai/mistral/mistral-medium",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
SPECIFICATIONS

The full spec sheet.

Context, pricing, modalities, routing, and deployment: everything Mistral Medium 3.1 supports, in one table.

MODEL ID
blackboxai/mistral/mistral-medium
DEVELOPED BY
Mistral
MODEL TYPE
Text
RELEASED
May 7, 2025
CONTEXT WINDOW
128K
MAX OUTPUT TOKENS
64K
INPUT MODALITIES
text, image
OUTPUT MODALITIES
text
INPUT PRICE
$0.4 / 1M tokens
OUTPUT PRICE
$2 / 1M tokens
REASONING
Not supported
DATA RETENTION
Standard retention
DEDICATED DEPLOYMENT
Not available (closed-weight model)
SUPPORTED PARAMETERS
max_tokenstemperaturestoptoolstool_choice