Which is cheaper, o3 (batch) or GPT-3.5 Turbo 16k?

o3 (batch) is the cheaper of the two: one 1,000-word request costs about 1,886 toman, about 1.4× cheaper than GPT-3.5 Turbo 16k.

Which one has the larger context window?

o3 (batch), with 200,000 tokens.

o3 (batch) vs GPT-3.5 Turbo 16k

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, o3 (batch) comes out about 1.4× cheaper.

Feature	o3 (batch)	GPT-3.5 Turbo 16k
Provider	OpenAI	OpenAI
Model id	openai/o3:batch	openai/gpt-3.5-turbo-16k
Context	200,000 tokens	16,385 tokens
Max output	100,000 tokens	4,096 tokens
Input / 1M tokens	290,125 toman	870,375 toman
Output / 1M tokens	1,160,500 toman	1,160,500 toman
≈ one 1,000-word request	1,886 toman	2,640 toman
Input caching	72,531 toman / 1M	No
Image input	Yes	No
File input	Yes	No
Tool calling	Yes	Yes
JSON output	Yes	Yes
Reasoning mode	Yes	No

Which one for what?

o3 (batch)

Multi-step problems, maths, and tracking down a bug
Whole documents or a codebase in a single request
Reading screenshots, invoices, and scanned forms
Agents that call your own APIs and database

1,886 toman per 1,000 words · Model page

GPT-3.5 Turbo 16k

Agents that call your own APIs and database

2,640 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": "openai/o3:batch",
    "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="openai/o3:batch",
    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: "openai/o3:batch",
  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' => 'openai/o3:batch',
    '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:    "openai/o3:batch",
		Messages: []openai.ChatCompletionMessageParamUnion{openai.UserMessage("Introduce yourself in one sentence.")},
	})
	if err != nil {
		panic(err)
	}
	fmt.Println(resp.Choices[0].Message.Content)
}

model = "openai/gpt-3.5-turbo-16k"

More comparisons: all pairs · model rankings · full catalogue

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