Which is cheaper, Hermes 3 70B Instruct or Llama 4 Maverick?

Llama 4 Maverick is the cheaper of the two: one 1,000-word request costs about 338 toman, about 1.6× cheaper than Hermes 3 70B Instruct.

Which one has the larger context window?

Llama 4 Maverick, with 1,048,576 tokens.

Hermes 3 70B Instruct vs Llama 4 Maverick

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. On cost, Llama 4 Maverick comes out about 1.6× cheaper.

Feature	Hermes 3 70B Instruct	Llama 4 Maverick
Provider	Nous Research	Meta
Model id	nousresearch/hermes-3-llama-3.1-70b	meta-llama/llama-4-maverick
Context	131,072 tokens	1,048,576 tokens
Max output	16,384 tokens	115,200 tokens
Input / 1M tokens	203,088 toman	58,025 toman
Output / 1M tokens	203,088 toman	201,927 toman
≈ one 1,000-word request	528 toman	338 toman
Input caching	No	No
Image input	No	Yes
File input	No	No
Tool calling	No	Yes
JSON output	Yes	Yes
Reasoning mode	No	No

Which one for what?

Hermes 3 70B Instruct

Chat, summarising, and everyday text generation

528 toman per 1,000 words · Model page

Llama 4 Maverick

Whole documents or a codebase in a single request
Reading screenshots, invoices, and scanned forms
Agents that call your own APIs and database
High-volume work where cost per call decides

338 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": "nousresearch/hermes-3-llama-3.1-70b",
    "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="nousresearch/hermes-3-llama-3.1-70b",
    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: "nousresearch/hermes-3-llama-3.1-70b",
  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' => 'nousresearch/hermes-3-llama-3.1-70b',
    '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:    "nousresearch/hermes-3-llama-3.1-70b",
		Messages: []openai.ChatCompletionMessageParamUnion{openai.UserMessage("Introduce yourself in one sentence.")},
	})
	if err != nil {
		panic(err)
	}
	fmt.Println(resp.Choices[0].Message.Content)
}

model = "meta-llama/llama-4-maverick"

More comparisons: all pairs · model rankings · full catalogue

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