Mistral AI

European AI lab building efficient open-weight models

MultilingualStructured outputOCREfficiencyOpenAI-compatible
HQ: Paris, FranceFounded: 2023mistral.ai

About Mistral AI

Mistral AI is a Paris-based company that builds high-performance language models with a focus on efficiency and openness. Their models range from the compact Mistral Small to the powerful Mistral Large, with strong multilingual capabilities and structured output support. Mistral also offers a specialized OCR API for document processing.

Key Models

Mistral LargeMistral SmallMistral NemoCodestral

Live Performance Data

Intelligence Score
57.0
Total Requests
13
Success Rate
3077.0%
Avg Latency
2799ms
Models
57
Tokens Processed
1.8K

Mistral AI Models on Antbase

ModelScoreRequestsSuccess RateAvg Latencyp95 LatencyCapabilities
Mistral Vibe Cli Fast60.000.0%400ms1000ms
👁🔧
Mistral Medium Latest60.000.0%400ms1000ms
👁🔧
Mistral Medium60.000.0%400ms1000ms
👁🔧
Mistral Vibe Cli With Tools60.000.0%400ms1000ms
👁🔧
Open Mistral Nemo60.000.0%400ms1000ms
🔧
Open Mistral Nemo 240760.000.0%400ms1000ms
🔧
Mistral Tiny 240760.000.0%400ms1000ms
🔧
Mistral Tiny Latest60.000.0%400ms1000ms
🔧
Codestral 250860.000.0%400ms1000ms
🔧
Codestral Latest60.000.0%400ms1000ms
🔧
Devstral 251260.000.0%400ms1000ms
🔧
Mistral Vibe Cli Latest60.000.0%400ms1000ms
👁🔧
Devstral Medium Latest60.000.0%400ms1000ms
🔧
Pixtral Large 241160.000.0%400ms1000ms
👁🔧
Pixtral Large Latest60.000.0%400ms1000ms
👁🔧
Devstral Small 250760.000.0%400ms1000ms
🔧
Devstral Medium 250760.000.0%400ms1000ms
🔧
Labs Devstral Small 251260.000.0%400ms1000ms
👁🔧
Devstral Small Latest60.000.0%400ms1000ms
👁🔧
Mistral Medium 250560.000.0%400ms1000ms
👁🔧
Voxtral Mini 250760.000.0%400ms1000ms
Magistral Small 250960.000.0%400ms1000ms
👁🔧
Ministral 3b 251260.000.0%400ms1000ms
👁🔧
Magistral Medium 250960.000.0%400ms1000ms
👁🔧
Magistral Medium Latest60.000.0%400ms1000ms
👁🔧
Magistral Small Latest60.000.0%400ms1000ms
👁🔧
Voxtral Small 250760.000.0%400ms1000ms
🔧
Ministral 3b Latest60.000.0%400ms1000ms
👁🔧
Voxtral Small Latest60.000.0%400ms1000ms
🔧
Ministral 8b 251260.000.0%400ms1000ms
👁🔧
Ministral 8b Latest60.000.0%400ms1000ms
👁🔧
Ministral 14b 251260.000.0%400ms1000ms
👁🔧
Ministral 14b Latest60.000.0%400ms1000ms
👁🔧
Voxtral Mini Transcribe 250760.000.0%400ms1000ms
Mistral Ocr 251260.000.0%400ms1000ms
👁🔧
Mistral Ocr Latest60.000.0%400ms1000ms
👁🔧
Mistral Ocr 250360.000.0%400ms1000ms
👁🔧
Mistral Ocr 250560.000.0%400ms1000ms
👁🔧
Voxtral Mini 260260.000.0%400ms1000ms
Voxtral Mini Latest60.000.0%400ms1000ms
Mistral Medium 250860.000.0%400ms1000ms
👁🔧
Voxtral Mini Realtime Latest60.000.0%400ms1000ms
Devstral Latest60.000.0%400ms1000ms
🔧
Labs Leanstral 260360.000.0%400ms1000ms
👁🔧
Voxtral Mini Transcribe Realtime 260260.000.0%400ms1000ms
Voxtral Mini Realtime 260260.000.0%400ms1000ms
Mistral Large 241160.000.0%400ms1000ms
🔧
Mistral Large Pixtral 241160.000.0%400ms1000ms
👁🔧
Mistral Large 251260.000.0%400ms1000ms
👁🔧
Labs Mistral Small Creative60.000.0%400ms1000ms
🔧
Mistral Small 250660.000.0%400ms1000ms
👁🔧
Mistral Small 260360.000.0%400ms1000ms
👁🔧
Mistral Large Latest40.058000.0%28821ms43647ms
👁🔧
mistral/mistral-large33.010.0%1284ms1284ms
Glm 5 233.010.0%1200ms1200ms
🔧
Zai Glm 5 232.050.0%1149ms1632ms
🔧
Mistral: Mistral Small 3.1 24B (free)15.010.0%106306ms106306ms
👁🔧

How to Use Mistral AI on Antbase

All Mistral AI models are available through Antbase's unified OpenAI-compatible API. You can either route directly to a specific Mistral AI model or let ANT's intelligent router automatically select the best model for your task.

python
from openai import OpenAI

client = OpenAI(
    base_url="https://antbase.ai/v1",
    api_key="your-ant-api-key",
)

# Let ANT auto-route (may use Mistral AI if optimal)
response = client.chat.completions.create(
    model="ant:auto",
    messages=[{"role": "user", "content": "Hello!"}],
)

# Or route directly to a Mistral AI model
response = client.chat.completions.create(
    model="mistral/mistral-large",
    messages=[{"role": "user", "content": "Hello!"}],
)

Why Use Mistral AI Through Antbase?

  • •No separate account needed — access Mistral AI models instantly through your Antbase API key.
  • •Intelligent routing — ANT automatically selects the best Mistral AI model for each task, or falls over to another provider if Mistral AI is slow or down.
  • •Same token prices — Antbase charges zero markup on Mistral AI token prices. You pay exactly what Mistral AI charges.
  • •Automatic failover — if Mistral AI has an outage, your requests seamlessly route to an equivalent model on another provider.