mistral · MultimodalReleased 2026-10-06

mistral-large-4

mistral/mistral-large-4 id

Mistral Large 4 is Mistral AI's open-weight, natively multimodal model, available in public preview with 1.05 trillion total parameters and 49 billion active parameters. It leads aggregated benchmarks among open-weight models from the US and Europe, with strengths in cyber defense, manufacturing, finance, and visual grounding.

ReasoningStructured outputTool useChat

Type

Use mistral-large-4

# Drop-in OpenAI-compatible client
$ import { generateText } from 'ai'
$ 
$ const { text } = await generateText({
$   model: 'mistral/mistral-large-4',
$   baseURL: 'https://synapse.garden/api/v1',
$   apiKey: process.env.MG_KEY,
$   prompt: 'Why is the sky blue?',
$ })

524.3K

CONTEXT WINDOW

262.1K

MAX OUTPUT

$1.50/M

INPUT · PER M

$4.60/M

OUTPUT · PER M

PRICING

List prices, every modality.

Rate	Per million tokens · USD
Input	$1.50/M
Output	$4.60/M
Cache read	$0.154/M

Honest list pricesHow we calculate prices

Other mistral models

See all 14

Model

Input

Output

Context

Type

codestralMistral's cutting-edge language model for coding released end of July 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.TOOLSJSON
Input
$0.330/M
Output
$0.990/M
Context
128K
codestral-embedCode embedding model that can embed code databases and repositories to power coding assistants.
Input
$0.165/M
Output
—
Context
—
ministral-14bMinistral 3 14B is the largest model in the Ministral 3 family, offering state-of-the-art capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. Optimized for local deployment, it delivers high performance across diverse hardware, including local setups.TOOLSJSON
Input
$0.220/M
Output
$0.220/M
Context
262.1K
ministral-3bA compact, efficient model for on-device tasks like smart assistants and local analytics, offering low-latency performance.TOOLS
Input
$0.110/M
Output
$0.110/M
Context
131.1K
ministral-8bA more powerful model with faster, memory-efficient inference, ideal for complex workflows and demanding edge applications.TOOLSJSON
Input
$0.165/M
Output
$0.165/M
Context
262.1K
mistral-embedGeneral-purpose text embedding model for semantic search, similarity, clustering, and RAG workflows.
Input
$0.110/M
Output
—
Context
—
mistral-large-3Mistral Large 3 2512 is Mistral’s most capable model to date. It has a sparse mixture-of-experts architecture with 41B active parameters (675B total).TOOLSJSON
Input
$0.550/M
Output
$1.65/M
Context
262.1K
mistral-medium-3.5Mistral's frontier-class multimodal model optimized for agentic and coding use cases.REASONINGTOOLSJSON
Input
$1.65/M
Output
$8.25/M
Context
262.1K
mistral-nemo12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.TOOLSJSON
Input
$0.032/M
Output
$0.033/M
Context
131.1K
mistral-smallMistral Small currently runs Mistral Small 4, a multimodal model combining instruction following, reasoning, and coding with a 262,144-token context window.TOOLSJSON
Input
$0.165/M
Output
$0.660/M
Context
262.1K
voxtral-mini-transcribe-3Fast, cost-efficient multilingual transcription with speaker diarization and vocabulary biasing, designed for high-volume audio processing.
Input
—
Output
—
Context
—
voxtral-mini-tts-3Generates natural, expressive speech with preset or cloned voices and inline controls for emotion and pace.
Input
$17.60/M
Output
—
Context
—

FAQ · MISTRAL-LARGE-4

Frequently asked

01 / 04

How do I call mistral-large-4 from my code?

Use the OpenAI or Anthropic SDK and point baseURL at https://synapse.garden/api/v1. Set model: ‘mistral/mistral-large-4’ and supply your Synapse Garden API key. No code changes beyond the base URL.

02 / 04

How much does mistral-large-4 cost?

Input: $1.50/M per million tokens. Output: $4.60/M per million tokens. The free tier includes a million tokens every month at no cost.

03 / 04

What's the context window for mistral-large-4?

mistral-large-4 supports a context window of 524.3K tokens, with a maximum output of 262.1K tokens.

04 / 04

Do I need a separate Anthropic or OpenAI account?

No. Synapse Garden is the single API surface — one key gives you OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, xAI, Cohere, and more. Billing, rate limits, and audit logs are unified.

READY

Try mistral-large-4 in three minutes.

Sign up, create a key, drop our base URL into your existing client. The free tier includes a million tokens every month — no credit card.

Start free Quickstart