Today's price · per 1M tokens
Input
$5.00
per 1M tokens
Output
$30.00
per 1M tokens
Blended
$17.50
avg of input & output $/1M
Cached input
$0.500
10% of input — prompt caching
Source: official OpenAI pricing · read Jul 3, 2026
MODELPRICEWATCH.COM · 2026-08-01
Overview
Frontier model for coding and professional work. 1.05M context window with multimodal input.
Capabilities
struck through = not supportedInput 3/5
Text ✓
Image ✓
Audio ✓
Video
PDF
Output 1/5
Text ✓
Image
Audio
Video
Embedding
Features 4/9
Prompt caching ✓
Reasoning ✓
Coding
Fast inference
Long context ✓
Open weights
Multimodal ✓
Web search
Realtime
Benchmark performance
accuracy % · higher is betterAvg benchmark score75%
Perf per $/Mtok4.3
GPQA Diamond
93.6%
Terminal-Bench 2.1
82.7%
MCP Atlas
75.3%
BrowseComp
84.4%
OSWorld-Verified
78.7%
Humanity's Last Exam
41.4%
ARC-AGI 2
85%
HumanEval
58.6%
AutoBench *
12.9%
Independent composite scores
- AA Intelligence Index: 54.8 (Artificial Analysis composite across reasoning, knowledge and coding evals)
- AA Agentic Index: 44.9 (Tool use, planning, autonomy)
- AA-Omniscience Index: 20.1 (−100–100)
- GDPval-AA v2: 1491.1 ELO (Real-world work tasks, human baseline = 1000)
- LMSYS Chatbot Arena: 1476.3 ELO (Human preference)
How it stacks up
- Ranks #25 of 68 benchmarked models by average score
- Ranks #25 of 133 comparably-measured models by percentile score, across 13 independent measurements
- Ranks #119 of 133 comparably-tested models by normalized performance per dollar
- Strongest at ARC-AGI 2 — 85%, #2 of 33
79 tokens/sec output 76.69s latency to first token (TTFT)
Source: Vellum LLM Leaderboard · updated Aug 1, 2026 · See full rankings →
Specifications
- Provider
- OpenAI
- Context window
- 1M tokens
- Modality
- text, image, audio
- Parameters
- Proprietary
- Open source
- No — proprietary
- Released
- Nov 15, 2025
- Status
- Current
- Last updated
- Jul 3, 2026
- Tags
Availability verified: Jul 3, 2026 — listed on OpenAI's own page