AI model comparison

Qwen3.8 Max (0902) vs GPT-5.3-Codex

Side by side comparison of Qwen3.8 Max (0902) and GPT-5.3-Codex on pricing, benchmark scores, context window, and more.

Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team.

Input / 1M
$2
Output / 1M
$6
Context
1M

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2.

Input / 1M
$1.75
Output / 1M
$14
Context
400K

Comparing image generators? Compare image models

At a glance

Quick verdict

How the two models stack up on the things people ask about most.

Lower price

qwen logo

Qwen3.8 Max (0902)

1.5x cheaper for a typical chat

Higher intelligence score

qwen logo

Qwen3.8 Max (0902)

33.7 vs 32.5 on Artificial Analysis

Larger context window

qwen logo

Qwen3.8 Max (0902)

1M vs 400K tokens

Newer release

qwen logo

Qwen3.8 Max (0902)

Released September 3, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

qwen logoQwen3.8 Max (0902)33.7
openai logoGPT-5.3-Codex32.5

Coding index

qwen logoQwen3.8 Max (0902)76.2
openai logoGPT-5.3-CodexNot available

Agentic index

qwen logoQwen3.8 Max (0902)56
openai logoGPT-5.3-CodexNot available

Pricing

Qwen3.8 Max (0902) vs GPT-5.3-Codex API pricing

Per-token API rates. Cheaper option highlighted.

Metricqwen logoQwen3.8 Max (0902)openai logoGPT-5.3-Codex
Input tokensPer 1M tokens$2$1.75
Output tokensPer 1M tokens$6$14
Cached input (read)Per 1M tokens$0.25$0.18
Cache writePer 1M tokensNot availableNot available
Web searchPer requestNot available$0.01

What it costs in practice

Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.

Chat message

2K in, 500 out

qwen logoQwen3.8 Max (0902)$7
openai logoGPT-5.3-Codex$10.50

Coding task

30K in, 4K out

qwen logoQwen3.8 Max (0902)$84$31.50 cached
openai logoGPT-5.3-Codex$108.50$61.25 cached

Long document summary

150K in, 2K out

qwen logoQwen3.8 Max (0902)$312$49.50 cached
openai logoGPT-5.3-Codex$290.50$54.25 cached

Specs

Context window and capabilities

How much each model can read, how much it can write, and what it accepts as input.

Metricqwen logoQwen3.8 Max (0902)openai logoGPT-5.3-Codex
Context window1M tokens400K tokens
Max output131K tokens128K tokens
Input typesImage, Text, VideoFile, Image, Text
Output typesTextText
Reasoning effort levelsExtra high, High, Medium, Low, MinimalExtra high, High, Medium, Low, None
Default reasoning effortExtra highMedium
Release dateSeptember 3, 2026February 24, 2026

Features

Supported features

API features available for each model.

Metricqwen logoQwen3.8 Max (0902)openai logoGPT-5.3-Codex
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedSupported
TemperatureSupportedNot supported
Stop sequencesSupportedNot supported
Deterministic seedSupportedSupported
Verbosity controlNot supportedSupported

Our take

Qwen3.8 Max (0902) is 1.5x cheaper for a typical chat. Qwen3.8 Max (0902) scores higher on the Artificial Analysis Intelligence Index (33.7 vs 32.5). Qwen3.8 Max (0902) has the larger context window (1M vs 400K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.

FAQ

Frequently asked questions

Is Qwen3.8 Max (0902) or GPT-5.3-Codex cheaper?

Qwen3.8 Max (0902) is cheaper for a typical chat (2K input tokens and 500 output tokens). Qwen3.8 Max (0902) costs $2 per 1M input tokens and $6 per 1M output tokens, while GPT-5.3-Codex costs $1.75 per 1M input tokens and $14 per 1M output tokens.

Which has a bigger context window, Qwen3.8 Max (0902) or GPT-5.3-Codex?

Qwen3.8 Max (0902) supports up to 1M tokens of context, compared with 400K for GPT-5.3-Codex.

Is Qwen3.8 Max (0902) smarter than GPT-5.3-Codex?

On the Artificial Analysis Intelligence Index, Qwen3.8 Max (0902) scores 33.7 and GPT-5.3-Codex scores 32.5, putting Qwen3.8 Max (0902) ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use Qwen3.8 Max (0902) and GPT-5.3-Codex at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Qwen3.8 Max (0902) and GPT-5.3-Codex answer side by side and keep the better response.

qwen logoopenai logo

Why choose? Ask both.

Send one prompt to Qwen3.8 Max (0902) and GPT-5.3-Codex at the same time. Compare the answers side by side and keep the best one.