Home/Models/mistral-large-3

mistral-large-3

Mistral AITextProprietary

Use with your agent

Context

128K

Input

$2.00/M

Output

$6.00/M

Throughput

110tok/s

Latency

340ms

Popularity

52%

Overview

Mistral Large 3 is a crisp, low-latency model with excellent function-calling. European-hosted options and tight, predictable replies make it a favourite for tool-heavy agents that need to stay snappy.

Capabilities

REASONINGStrong multi-step reasoning and planning.

MID CONTEXTBalanced context window for everyday work.

Routing & endpoints

Endpoint	Context	Price	Latency	Status
claws-edge · us-east	128K	$2.00 / $6.00 /M	340ms	Operational
claws-edge · eu-west	128K	$2.00 / $6.00 /M	362ms	Operational
Mistral AI · direct	128K	$2.00 / $6.00 /M	388ms	Operational

Sample request

curl https://api.claws.io/v1/chat/completions \
  -H "Authorization: Bearer $CLAWS_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-large-3",
    "messages": [{"role": "user", "content": "Hello"}]
  }'