What is the context window of Mistral Embed by Mistral?

Mistral Embed by Mistral has a context window of 8K tokens. It supports up to 8K input tokens and can generate up to 3K output tokens.

What input and output types does Mistral Embed support?

Mistral Embed by Mistral accepts text as input and can generate text as output.

Is Mistral Embed by Mistral open source?

No, Mistral Embed by Mistral has closed weights. The model is only available through the Mistral API.

Back to Models

Mistral Embed API

Mistral

About

Mistral Embed is a high-performance LLM available via the Mistral API, ideal for scalable text generation and natural language processing. This model delivers cost-effective pricing at $0.10/1M input and Free/1M output tokens. Access Mistral Embed via the Mistral API with up to 3K output tokens.

Capabilities

Input Modalities

text

Output Modalities

text

Reasoning

Structured Output

Tool Use

WeightsClosed

Temperature

Fixed

Attachment

Not Supported

Limits

Context Window

Tokens

Input Limit

Tokens

Max Output

Tokens

Pricing

Standard (per 1M tokens)

Input

$0.10

Output

Free

Frequently Asked Questions

Mistral Embed by Mistral costs $0.10 per 1M input tokens and Free per 1M output tokens.

Model Details

mistral-embed

Provider

Mistral

Family

mistral-embed

Release Date

Dec 11, 2023

Knowledge Cutoff

N/A

API Integration

NPM Package

@ai-sdk/mistral

Environment Variables

MISTRAL_API_KEY

Documentation