mistral-medium-3.1

Availability84.0%
Available

Samples: 16

Latency1.1 s
Input / 1M tokens
$0.2
Output / 1M tokens
$1
Context window
131,072
Route
mistral_officialNeeds Plus
Roleplay

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills.

Each benchmark is scaled from 1 to 10 against the models here that it tested. Every publisher counts the same in the average.

Creative Writing v3
mistral-medium-3.1: 1,475.5
Source: EQ-Bench (Sam Paech)

5.8/10

Routes

Value is the score divided by the price (input and output averaged), ranked from 1 to 10 against every model and route here. Higher is better.

Use this model
mistral-medium-3.1mistral_official$0.2$1$0.025.8/107.8/10Roleplay API plans
mistral-medium-3.1-plus-freeplus_freeFree with Plus · 50 a day5.8/10FreeRoleplay API plans
curl --fail-with-body 'https://api.tokenreply.com/v1/chat/completions' \
  -H "Authorization: Bearer $TOKENREPLY_API_KEY" \
  -H 'Content-Type: application/json' \
  --data '{
  "model": "mistral-medium-3.1",
  "messages": [
    {
      "role": "user",
      "content": "Reply with hello."
    }
  ]
}'

Other model IDs for this model

Other versions in this series

More Mistral models

TokenReply

Reload