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