Mistral AI: Pixtral 12B

Name: Pixtral 12B API
Brand: Mistral

stable

Pixtral 12B is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

pixtral-12bpixtralreleased Sep 1, 2024

Provider Quick start

Context

128K

tokens

Max output

128K

tokens

Input

$0.15

per 1M

Output

$0.15

per 1M

Activity

Daily period usage

Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M

Mistral AI

128K$0.15$0.15

Pricing

Item	Price	Unit
Input	$0.15	per 1M tokens
Output	$0.15	per 1M tokens

Performance

Reliability

Compare

Compare usage and performance

Place this model beside up to three other catalog models.

Capabilities

Modalities

Input

Output

Details

Model ID: pixtral-12b
Family: pixtral
Status: stable
Knowledge: Sep 1, 2024
Released: Sep 1, 2024

Gateway Config

API: 2024-01-01
Auth: MISTRAL_API_KEY
Discovery: static
Provider type: static

Quick Start

index.ts

import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@mistral/pixtral-12b",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL

https://api.mistral.ai/v1

Chat completions

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

Model

pixtral-12b

Auth env

MISTRAL_API_KEY

Pixtral 12B FAQ

How much does the Pixtral 12B API cost?

Through Mistral AI, Pixtral 12B costs $0.15 per 1M input tokens and $0.15 per 1M output tokens.

What is the context window of Pixtral 12B?

Pixtral 12B accepts up to 128K tokens of context and returns up to 128K output tokens on Mistral AI.

What can Pixtral 12B do?

Pixtral 12B supports chat, function calling and image input. It accepts text and image input.

How do I call Pixtral 12B through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @mistral/pixtral-12b. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.