Mixtral 8x22B Instruct

FrontierTools

Mistral · Released April 2024 · Knowledge cutoff January 2024

Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...

It belongs to Mistral's catalog, which spans Medium (capability), Small and Ministral (efficiency) and dedicated code models, all with European data-residency roots.

Facts and pricing

Provider
Mistral
Context window
66K tokens
Input price
22.0 credits / 1M tokens ($2.00 raw)
Output price
66.0 credits / 1M tokens ($6.00 raw)
Vision (image input)
No
Tool calling
Yes
Extended reasoning
No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.

Try Mixtral 8x22B Instruct now

Ask Mixtral 8x22B Instruct anything. Your prompt opens in the Zeplik app with this model selected.

Mixtral 8x22B Instruct

What Mixtral 8x22B Instruct is best for

Example prompts

Prompts that suit a frontier model like Mixtral 8x22B Instruct:

Mistral family

ModelContextInput cr/MOutput cr/MReleased
Mistral Medium 3.5262K16.582.5April 2026
Mistral Small 4262K1.76.6March 2026
Devstral 2 2512262K4.422.0December 2025
Ministral 3 14B 2512262K2.22.2December 2025
Ministral 3 8B 2512262K1.71.7December 2025
Ministral 3 3B 2512131K1.11.1December 2025
Mistral Large 3 2512262K5.516.5December 2025
Voxtral Small 24B 250732K1.13.3October 2025
Mistral Medium 3.1131K4.422.0August 2025
Codestral 2508256K3.39.9August 2025

All 19 Mistral models

Frequently asked questions

What is Mixtral 8x22B Instruct?
Mixtral 8x22B Instruct is an AI model by Mistral. Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...
How much does Mixtral 8x22B Instruct cost on Zeplik?
Input tokens cost 22.0 credits per million and output tokens 66.0 credits per million (1 credit = $0.10; the raw provider rates are $2.00 and $6.00 per million). New accounts start with free credits.
How long can a conversation with Mixtral 8x22B Instruct be?
Mixtral 8x22B Instruct has a 66K-token context window (65,536 tokens), which covers the conversation plus any documents you attach.
Does Mixtral 8x22B Instruct support images and tools?
Mixtral 8x22B Instruct is text-only and supports tool calling.

Related models

Mixtral 8x22B Instruct - Mistral AI Model | Zeplik Chat