Skip to content
Seedance 2.0 Face is here — generate video from real-person reference photos.Try it now →
Back to Models
openaiopenai·Aug 7, 2025

OpenAI: GPT-5

openai/gpt-5
context
400K
Max Output
128K
Input / 1M
$1.25
Output / 1M
$10.00

About

GPT-5 is OpenAI's flagship model, generally available since August 2025, with improvements in reasoning, code quality, and instruction following. It is optimized for complex tasks requiring step-by-step reasoning and accuracy in high-stakes use cases, and supports user-specified intent such as asking the model to think harder. On coding benchmarks it scores 74.9% on SWE-bench Verified and 88% on Aider Polyglot. It accepts text, image, and file inputs and returns text, with a 400K-token context window and up to 128K output tokens. OpenAI reports reductions in hallucination and sycophancy relative to prior models.

Capabilities

Context Length
400K
Max Output
128K
Reasoning
Yes
In
text, image, file
Out
text

Benchmarks

View leaderboard
21.8#77 of 133
Intelligence Index
21.2#84 of 118
Coding Index
48.3#38 of 63
Math Index

Reasoning & Knowledge

MMLU-Pro82.0%
GPQA Diamond68.6%
HLE5.8%

Coding & Agentic

LiveCodeBench54.3%
SciCode37.8%
Terminal-Bench Hard12.9%

Math

AIME 202548.3%

Source: Artificial Analysis

Pricing

Full pricing
TypePrice / 1M tokens
Input$1.25
Output$10.00
Cache Read$0.125
Web Search$0.01 / call

API

API reference

OpenAI-compatible · Model ID openai/gpt-5

curl https://api.elliotgate.com/v1/chat/completions \
  -H "Authorization: Bearer sk-omg-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

OFTEN COMPARED

GPT-5 comparisons

Decide which model wins on the dimensions that matter for your workload — context, benchmarks, pricing, or serving latency.