ModelPriceWatch.com
Last scan 2026-08-01 Models tracked 181 Providers 27 Cheapest paid Granite 4.0 Micro $0.017/Mtok in Every price links to its source

GPT-5.3 Codex

by OpenAI

Current coding mid tier

Today's price · per 1M tokens

Input

$1.75

per 1M tokens

Output

$14.00

per 1M tokens

Blended

$7.88

avg of input & output $/1M

Cached input

$0.175

10% of input — prompt caching

Source: official OpenAI pricing · read Jul 3, 2026 MODELPRICEWATCH.COM · 2026-08-01

Overview

GPT-5.3 optimized for agentic coding and software engineering. 400K context.

Capabilities

struck through = not supported
Input 2/5
Text ✓ Image ✓ Audio Video PDF
Output 1/5
Text ✓ Image Audio Video Embedding
Features 5/9
Prompt caching ✓ Reasoning ✓ Coding ✓ Fast inference Long context ✓ Open weights Multimodal ✓ Web search Realtime

Benchmark performance

accuracy % · higher is better
Avg benchmark score71%
Perf per $/Mtok9
SWE-Bench Verified vendor
85%
Terminal-Bench 2.1
77.3%
OSWorld-Verified
64.7%
Independent composite scores
  • AA Intelligence Index: 44.3 (Artificial Analysis composite across reasoning, knowledge and coding evals)
  • LMSYS Chatbot Arena: 1416 ELO (Human preference)
How it stacks up
  • Ranks #29 of 68 benchmarked models by average score
  • Ranks #62 of 133 comparably-measured models by percentile score, across 4 independent measurements
  • Ranks #113 of 133 comparably-tested models by normalized performance per dollar
  • Strongest at Terminal-Bench 2.1 — 77.3%, #12 of 31

50 tokens/sec output 0.003s latency to first token (TTFT)

Source: Vellum LLM Leaderboard · updated Aug 1, 2026 · See full rankings →

Specifications

Provider
OpenAI
Context window
400K tokens
Modality
text, image
Parameters
Proprietary
Open source
No — proprietary
Released
Feb 24, 2026
Status
Current
Last updated
Jul 3, 2026
Tags
codingreasoning

Availability verified: Jul 3, 2026 — listed on OpenAI's own page