Which is cheaper, Mixtral 8x22B Instruct or Mistral Large?

Mixtral 8x22B Instruct is the cheaper of the two: one 1,000-word request costs about 3,017 toman.

Which one has the larger context window?

Mistral Large, with 128,000 tokens.

Mixtral 8x22B Instruct vs Mistral Large

Both sit behind the same key and the same code on uttapen — the only thing that changes is the model string, so you can run each of them against your own workload without touching anything else.

Feature	Mixtral 8x22B Instruct	Mistral Large
Provider	Mistral	Mistral
Model id	mistralai/mixtral-8x22b-instruct	mistralai/mistral-large
Context	65,536 tokens	128,000 tokens
Max output	52,428 tokens	102,400 tokens
Input / 1M tokens	580,250 toman	580,250 toman
Output / 1M tokens	1,740,750 toman	1,740,750 toman
≈ one 1,000-word request	3,017 toman	3,017 toman
Input caching	58,025 toman / 1M	58,025 toman / 1M
Image input	No	No
File input	Yes	Yes
Tool calling	Yes	Yes
JSON output	Yes	Yes
Reasoning mode	No	No

Which one for what?

Mixtral 8x22B Instruct

Agents that call your own APIs and database

3,017 toman per 1,000 words · Model page

Mistral Large

Agents that call your own APIs and database

3,017 toman per 1,000 words · Model page

Run both with the same code

Swap the model value between the two ids and send the same request twice; what each answer cost comes back in the X-Uttapen-Cost-Toman header.

curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/mixtral-8x22b-instruct",
    "messages": [{"role": "user", "content": "Introduce yourself in one sentence."}],
    "stream": true
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uttapen.ir/v1",
    api_key="sk-up-…",
)

stream = client.chat.completions.create(
    model="mistralai/mixtral-8x22b-instruct",
    messages=[{"role": "user", "content": "Introduce yourself in one sentence."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.uttapen.ir/v1",
  apiKey: "sk-up-…",
});

const stream = await client.chat.completions.create({
  model: "mistralai/mixtral-8x22b-instruct",
  messages: [{ role: "user", content: "Introduce yourself in one sentence." }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

<?php
// composer require openai-php/client guzzlehttp/guzzle
$client = OpenAI::factory()
    ->withBaseUri('https://api.uttapen.ir/v1')
    ->withApiKey('sk-up-…')
    ->make();

$result = $client->chat()->create([
    'model' => 'mistralai/mixtral-8x22b-instruct',
    'messages' => [['role' => 'user', 'content' => 'Introduce yourself in one sentence.']],
]);
echo $result->choices[0]->message->content;

package main

import (
	"context"
	"fmt"

	"github.com/openai/openai-go"
	"github.com/openai/openai-go/option"
)

func main() {
	client := openai.NewClient(
		option.WithBaseURL("https://api.uttapen.ir/v1"),
		option.WithAPIKey("sk-up-…"),
	)
	resp, err := client.Chat.Completions.New(context.Background(), openai.ChatCompletionNewParams{
		Model:    "mistralai/mixtral-8x22b-instruct",
		Messages: []openai.ChatCompletionMessageParamUnion{openai.UserMessage("Introduce yourself in one sentence.")},
	})
	if err != nil {
		panic(err)
	}
	fmt.Println(resp.Choices[0].Message.Content)
}

model = "mistralai/mistral-large"

More comparisons: all pairs · model rankings · full catalogue

base_url = https://api.uttapen.ir/v1