gpt-5.3-codex

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. It achieves state-of-the-art results...

LLM & Generative AI 1 model 1 listings snapshot Oct 14, 2026, 12:43 AM

Platforms

click a card to open the detail table

Cheapest OpenRouter no official benchmark Input$1.75 Output$14.00 per 1M tokens Fastest OpenRouter lowest p50 latency on this board 128.1 ms p50 Most free quota — largest published free allowance — free tier

Model variants

W3r9 dedup — same model + identical tags merge; prices are listed per billing form

Model	Provider	Tags	Input /1M	Output /1M
openai/gpt-5.3-codex	OpenRouter	391k contextmultimodalreasoning	$1.75	$14.00

Capabilities

official design_arena & architecture metadata

Design Arena Elo official design_arena benchmark (OpenRouter)

gamedev 1166 · 51.3% wr
dataviz 1165 · 50.6% wr
website 1165 · 48.6% wr
asciiart 1154 · 51.2% wr
codecategories 1147 · 47.2% wr
uicomponent 1139 · 47.3% wr
svg 1128 · 54.0% wr
godotgamedev 1124 · 45.1% wr
androidnative 1084 · 35.2% wr
mobileapps 1051 · 41.4% wr
webapps 1026 · 36.9% wr
3d 1009 · 35.3% wr

Input / Output modalities modality: text+image+file->text

text in+out
image input only

Platform details

per provider

provider	model	Input /1M	Output /1M	Latency ?	Official $/1M	Availability	Data time
OpenRouter	openai/gpt-5.3-codex	$1.75	$14.00	128.1 ms	—	100% available	2026-10-14 00:43:21

1 rows · snapshot 2026-10-14 00:43:21 · from data/public/prices.json + measurements.json