Question 1

What is the cost of Mixtral 8x22B Instruct by Prime Inference?

Accepted Answer

Mixtral 8x22B Instruct by Prime Inference costs $2.20 per 1M input tokens and $6.60 per 1M output tokens.

Question 2

What is the context window of Mixtral 8x22B Instruct by Prime Inference?

Accepted Answer

Mixtral 8x22B Instruct by Prime Inference has a context window of 66K tokens. It supports up to 66K input tokens and can generate up to 52K output tokens.

Question 3

What are the capabilities of Mixtral 8x22B Instruct by Prime Inference?

Accepted Answer

Mixtral 8x22B Instruct by Prime Inference supports tool calling/function calling, structured output, adjustable temperature. It has open weights.

Question 4

What input and output types does Mixtral 8x22B Instruct support?

Accepted Answer

Mixtral 8x22B Instruct by Prime Inference accepts text as input and can generate text as output.

Question 5

Is Mixtral 8x22B Instruct by Prime Inference open source?

Accepted Answer

Yes, Mixtral 8x22B Instruct by Prime Inference has open weights, meaning the model weights are publicly available for download and self-hosting.

Question 6

Does Mixtral 8x22B Instruct support function calling?

Accepted Answer

Yes, Mixtral 8x22B Instruct by Prime Inference supports tool calling (also known as function calling), allowing it to interact with external tools and APIs during conversations.

Question 7

What is the knowledge cutoff date for Mixtral 8x22B Instruct?

Accepted Answer

Mixtral 8x22B Instruct by Prime Inference has a knowledge cutoff date of 2024-01-31. This means the model was trained on data available up until that date.

Mixtral 8x22B Instruct API

Input Modalities

Output Modalities

Standard (per 1M tokens)

Mixtral 8x22B Instruct API

Input Modalities

Output Modalities

Standard (per 1M tokens)