LLM Pricing

← All Models

OpenAI: GPT-5

🇺🇸 OpenAI · GPT-5

Input Price $1.25 per million tokens NT$40.0
Output Price $10.00 per million tokens NT$320
Context Window 400K tokens Output limit: 128K
OpenRouter Route Price Please verify with official pricing pages
Use this model via OpenRouter →

Overview

OpenAI: GPT-5 is a large language model API from OpenAI, part of its GPT-5 model family. Priced at $1.25 per million input tokens and $10.00 per million output tokens, it occupies the mid-range, balancing capability against running cost. Output tokens cost about 8× as much as input, so prompt-heavy workloads run noticeably cheaper than generation-heavy ones. A large 400K-token context window (≈600 pages of text) lets it take in whole books, large codebases, or lengthy transcripts in a single call. Beyond plain text it also accepts Image, File input, so it can be applied to multimodal tasks rather than text alone. On Artificial Analysis's Intelligence Index it scores 36 (B grade), a useful proxy for its general reasoning strength relative to the other models tracked here. All prices on this page reflect OpenRouter's routed rates and are re-synced automatically every day; confirm against the provider's official pricing before committing to production.

Dimension Unit Price (USD) Price (TWD) Effective From
Input per 1M tokens $1.25 NT$40.0
Output per 1M tokens $10.00 NT$320
Cached Input per 1M tokens $0.125 NT$4.0
Web Search per search $0.010 NT$0.32

Provider
OpenAI
Model Family
GPT-5
Version String
openai/gpt-5
Status
Active
Modality
Text, Image, File
Context Window
400,000 tokens
Output Limit
128,000 tokens

Index Metrics

Cross-domain capability indexes evaluated by Artificial Analysis — Artificial Analysis

Intelligence Index 36 B Measured: 2026-07-01

Benchmark Scores

Data source: Artificial Analysis

AA-LCR 75.6% A Measured: 2026-07-01
GPQA Diamond 85.4% S Measured: 2026-07-01
HLE 26.5% A Measured: 2026-07-01
IFBench 73.1% B Measured: 2026-07-01
MMMU Pro 74.2% B Measured: 2026-07-01
Non-Hallucination 17.9% Measured: 2026-07-01
Omniscience Accuracy 40.6% Measured: 2026-07-01
SciCode 42.9% B Measured: 2026-07-01
Tau2 84.8% Measured: 2026-07-01
TerminalBench 32.6% Measured: 2026-07-01

Performance Metrics

Real-world benchmarks, updated every 72 hours by Artificial Analysis — Artificial Analysis

First Token Latency 85.9s Measured: 2026-07-01
Output Speed 90 t/s Measured: 2026-07-01
Response Time 91.5s Measured: 2026-07-01

Use Case Analysis

Model strengths, weaknesses, and ideal use cases based on benchmarks and official documentation

Strength

  • Frontier Reasoning AIME 2025 94.6%, GPQA Diamond 85.7%. Configurable reasoning effort levels. Official
  • Advanced Coding SWE-bench Verified 74.9%, Aider polyglot 88%. Excels at bug fixing and complex codebase understanding. Official
  • Superior Tool Calling Tau2-bench telecom 96.7%. Better at understanding when to call tools and proactively suggesting tool use. Official

Best For

  • Complex Reasoning Tasks Math problem-solving, logic puzzles, multi-step reasoning where accuracy is critical. Official
  • Agentic Coding Workflows Long-running agent loops, complex refactors, and multi-file code generation. Official

Weakness

  • Higher Latency Reasoning models are slower than non-reasoning variants. Not suitable for real-time applications. Official

Not Recommended

  • Real-time Applications Use GPT-5 mini or GPT-5 nano for latency-sensitive workloads. Official

90-Day Price Trend

Input / Output price (USD per 1M tokens)

Past 90 days of records; every price change is shown here

Date Dimension Price (USD) Source
Web Search $0.010 OpenRouter
Cached Input $0.125 OpenRouter
Output $10.00 OpenRouter
Input $1.25 OpenRouter
Web Search $0.010 OpenRouter
Cached Input $0.125 OpenRouter
Output $10.00 OpenRouter
Input $1.25 OpenRouter
Web Search $0.010 OpenRouter
Cached Input $0.125 OpenRouter
Output $10.00 OpenRouter
Input $1.25 OpenRouter
Web Search $0.010 OpenRouter
Cached Input $0.125 OpenRouter
Output $10.00 OpenRouter
Input $1.25 OpenRouter
Web Search $0.010 OpenRouter
Cached Input $0.125 OpenRouter
Output $10.00 OpenRouter
Input $1.25 OpenRouter
Web Search $0.010 OpenRouter
Cached Input $0.125 OpenRouter
Output $10.00 OpenRouter
Input $1.25 OpenRouter
Web Search $0.010 OpenRouter
Cached Input $0.125 OpenRouter
Output $10.00 OpenRouter
Input $1.25 OpenRouter
Web Search $0.010 OpenRouter
Cached Input $0.125 OpenRouter
Output $10.00 OpenRouter
Input $1.25 OpenRouter
Web Search $0.010 OpenRouter
Cached Input $0.125 OpenRouter
Output $10.00 OpenRouter
Input $1.25 OpenRouter
Web Search $0.010 OpenRouter
Cached Input $0.125 OpenRouter
Output $10.00 OpenRouter
Input $1.25 OpenRouter
Web Search $0.010 OpenRouter
Cached Input $0.125 OpenRouter
Output $10.00 OpenRouter
Input $1.25 OpenRouter
Web Search $0.010 OpenRouter
Cached Input $0.125 OpenRouter
Output $10.00 OpenRouter
Input $1.25 OpenRouter
Web Search $0.010 OpenRouter
Cached Input $0.125 OpenRouter

Key Insights

Key data points from this page for quick reference and citation.

  • OpenAI: GPT-5 Input price: $1.25/M tokens
  • OpenAI: GPT-5 Output price: $10/M tokens
  • Context window: 400,000 tokens
  • Provider: OpenAI
  • Model family: GPT-5
  • Modalities: Text, Image, File
  • Data source: OpenRouter, updated daily