Nvidia

Mistral: Mixtral 8x7B Instruct

Name: Mistral: Mixtral 8x7B Instruct
Brand: Nvidia

Canonical ID: nvidia/mistralai/mixtral-8x7b-instruct

More Nvidia models More mixtral-8x7b-instruct family models

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Reasoning: No Tool use: Yes Open weights

Overview

text

Provider: Nvidia
Family: mixtral-8x7b-instruct
Release date: 2023-12-10
Last updated: 2026-03-15
Input modalities: text
Output modalities: text

Pricing and Limits

Token pricing

Input: $0/1M
Output: $0/1M
Cached input: N/A

Context and output

Context window: 32,768
Max output tokens: 16,384
Qualified ID: nvidia/mistralai/mixtral-8x7b-instruct

Model Summary

Mistral: Mixtral 8x7B Instruct is a model listing in the Nvidia provider catalog. It is categorized under the mixtral-8x7b-instruct family.

The model supports text modalities across input/output paths. Reported context capacity is 32,768. Pricing is listed at $0/1M input and $0/1M output.

Same Family: mixtral-8x7b-instruct

Comparable models in the same family across providers.

Browse family

Model	Provider	Context	Input	Output	Flags
Mistral: Mixtral 8x7B Instruct openrouter/mistralai/mixtral-8x7b-instruct	OpenRouter	32,768	$0.54/1M	$0.54/1M	Tools
Mixtral 8x7B Instruct v0.1 cortecs/mixtral-8x7B-instruct-v0.1	Cortecs	32,000	$0.488/1M	$0.758/1M	Reasoning
Mixtral-8x7B-Instruct-v0.1 amazon_bedrock/mistral.mixtral-8x7b-instruct-v0:1	Amazon Bedrock	32,000	$0.7/1M	$0.7/1M
Mixtral-8x7B-Instruct-v0.1 ovhcloud/mixtral-8x7b-instruct-v0.1	OVHcloud AI Endpoints	32,768	$0.7/1M	$0.7/1M

Mistral: Mixtral 8x7B Instruct

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From Nvidia

Active Speaker Detection

bevformer

BGE M3

ByteDance-Seed/Seed-OSS-36B-Instruct

Codegemma 1.1 7b

Codegemma 7b

Codellama 70b

Codestral 22b Instruct V0.1

Same Family: mixtral-8x7b-instruct