Skip to content
OpenKey

Mixtral 8x22B Instruct

Mistral AIReleased Apr 17, 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,...

Try in playground
Context window
66K tokens
Input
text, file
Output
text
Tokenizer
Mistral
Knowledge cutoff
Jan 31, 2024
Released
Apr 17, 2024

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$2.00$0.060$2.06
Output$6.00$0.180$6.18
Cache read$0.200$0.0060$0.206

Supported parameters

  • frequency_penalty
  • max_tokens
  • presence_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model mistralai/mixtral-8x22b-instruct.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/mixtral-8x22b-instruct",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="mistralai/mixtral-8x22b-instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "mistralai/mixtral-8x22b-instruct",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does Mixtral 8x22B Instruct cost via API?
Through OpenKey, Mixtral 8x22B Instruct costs $2.06 per 1M input tokens and $6.18 per 1M output tokens. That is the provider price ($2.00 / $6.00) plus a flat 3% fee — nothing else.
What is Mixtral 8x22B Instruct's context window?
Mixtral 8x22B Instruct accepts up to 66K tokens of context.
Is Mixtral 8x22B Instruct OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "mistralai/mixtral-8x22b-instruct" using any OpenAI SDK — only the base URL and API key change.
What inputs does Mixtral 8x22B Instruct support?
Mixtral 8x22B Instruct accepts text, file input and produces text output. Its knowledge cutoff is Jan 31, 2024.

More from Mistral AI

All Mistral AI models →