Mistral AIactiveOpen Source

Pixtral 12B

pixtral-12b

Lightweight 12B multimodal model with native image understanding.

Context Window

131.1K

tokens

Max Output

4.1K

tokens

Input Price

$0.15

per 1M tokens

Output Price

$0.15

per 1M tokens

Details

Familypixtral

Parameters12B

Training Cutoff2024-09-01

ReleasedSeptember 17, 2024

Aliasespixtral-12b-2409

Capabilities

VisionFunctionsStreamingJSON ModeCodeTool UseMultimodal

Documentation

https://api.mistral.ai/v1/chat/completions

Quick Access

curl pikaainews.com/api/models/mistral-pixtral-12b

npx pika-models info mistral-pixtral-12b

Get API Access

Official

AWS Bedrock

Amazon Bedrock. Official partnerships with Anthropic, Meta, Mistral, Cohere.

Mistral La Plateforme

Official Mistral API.

Third-Party Providers & Aggregators

DeepInfra

Lowest per-token rates for open-source models.

Fireworks AI

Fastest inference engine. Multimodal support, HIPAA/SOC2.

Groq

Ultra-fast LPU inference. Best latency for real-time apps.

OpenRouter

500+ models, one API key. Pay-per-token, no minimums.

SiliconFlow

China-optimized inference. Strong Qwen/DeepSeek support.

Together AI

Fast open-source model inference. Sub-100ms latency.

Other pixtral models

Mistral

Pixtral Large

pixtral-large-latest

131.1K ctx$2.00/1M