GPT-5 — OpenAI | Modeldex

GPT-5

Active77.9Strong

OpenAI's frontier flagship model with long context and advanced reasoning.

Updated 4 days agoStructured data from Modeldex catalog

VisionMathAgenticLong contextReasoningCode

Knowledge cutoff

Sep 30, 2024(1.6 years ago)

API release

Aug 7, 2025(8 months ago)

Intelligence Index

77.9/ 100

Strongweighted across 9 benchmarks

General knowledge: 82.0
Math: 81.1
Coding: 76.7
Reasoning: 72.0

Computed as the mean of per-category averages across MMLU, GPQA, SWE-bench, HumanEval, MATH, GSM8K, AIME, Aider Polyglot and more. See each benchmark for methodology.

Overview

GPT-5 is OpenAI's top-tier general-purpose model with strong reasoning, coding, and multimodal capabilities. It supports tool calling, structured outputs, and long context.

History

GPT-5 became available via the OpenAI API on 2025-08-07.

Training & availability

Training data has a knowledge cutoff of 2024-09-30 — information about events after that date is unlikely to appear in the model's responses. OpenAI has not released the underlying model weights — access is via their hosted API only.

Capabilities

Context window: 272K tokens.
Max output: 128K tokens.
Input modalities: text, image.
Intelligence Index: 77.9/100.

Strongest categories: General knowledge (82), Math (81), Coding (77).

Recommended for: vision, math, agentic, long-context, reasoning, code.

Limitations

The knowledge cutoff is 18 months old — this model will not know about recent events, releases, or API changes.

Pricing

Input: $1.2500 per 1M tokens
Output: $10.0000 per 1M tokens

Use the cost calculator above to estimate monthly spend for your workload.

Example interactions

Curated prompts showing the model's response style — not cherry-picked to impress, picked to show what typical output looks like.

Prompt

Explain how a transformer attention layer works, for a programmer who understands matrices but hasn't touched ML before.

Response

Attention is a weighted lookup. Given a token, the layer computes how much attention to pay to every other token in the sequence, then produces a weighted sum of their values. Three projections per token: - **Query (Q):** what this token is looking for - **Key (K):** what this token offers others - **Value (V):** the information it contributes if attended to For each position, compute scores = Q · Kᵀ (dot product against every other token's key). Softmax normalizes these into weights. Output = weights · V. Multi-head attention runs this in parallel with different Q/K/V projections, so different "heads" learn to track different relationships — syntax, coreference, topic, etc. Concat and project back. The matrix view: if you have n tokens and d_model dims, Q/K/V are (n × d_k) each. Attention output is (n × d_k). With h heads, final output concatenates to (n × d_model).

Quick start

Minimal example using the openai API. Copy, paste, replace the key.

from openai import OpenAI

client = OpenAI(api_key="sk-...")
resp = client.chat.completions.create(
    model="gpt-5",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)

Cost calculator

Estimate your monthly bill. Presets are typical workload sizes.

Input tokens / month5.0M

@ $1.25/1M

Output tokens / month2.0M

@ $10/1M

Input cost

$6.25

5.0M × $1.25/1M

Output cost

$20

2.0M × $10/1M

Total / month

$26.25

$315 / year

Benchmarks

Benchmark	Score	Source
AIME 2024Math	60% accuracy	Self-reported OpenAI system card
Aider PolyglotCoding	88% pass@2	Third-party Papers With Code
GPQA DiamondReasoning	72% accuracy	Third-party Artificial Analysis

Integrations & tooling support

Tool calling: Supported
Structured outputs: Supported

Price vs quality

Fair value

Mid-tier performance and pricing — standard choice.

Quality percentile: 57.7%
Effective price: $7.81/1M
Pricing breakdown: $1.25/1M in
$10/1M out

Community ratings

No ratings yet. Be the first to rate GPT-5.