Claude Fable 5$22.000/MClaude Opus 5$11.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MClaude Fable 5$22.000/MClaude Opus 5$11.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/M

GPT-5 vs GPT-4.1

OpenAI vs OpenAI · Prices checked 12 August 2026

GPT-4.1 is 2 per cent cheaper on blended cost, $3.80 per million tokens against $3.88. A single 100K-input, 10K-output job costs $0.280 on GPT-4.1 against $0.225 on GPT-5.

The ranking flips with your token mix: GPT-5 is cheaper for input-heavy work like RAG, while GPT-4.1 wins on output-heavy work like long-form generation or agent loops. GPT-5 leads on 6 of the 6 benchmarks both models report. The widest gap is on LMArena Elo, where GPT-5 leads by 53 points. GPT-4.1 takes a 1,000,000-token context window against 400,000, giving 2.5× more room for long documents or whole-codebase work. GPT-5 was released 2025; GPT-4.1 Apr 2025.

Pricing and capacity

Published token pricing and context window for GPT-5 and GPT-4.1
MetricGPT-5GPT-4.1Difference
Input / 1M tokens$1.25$2.0038%
Output / 1M tokens$10.00$8.0020%
Blended · 70/30calculated$3.88$3.802%
Blended · 50/50calculated$5.63$5.0011%
Blended · 80/20calculated$3.00$3.206%
Blended · 20/80calculated$8.25$6.8018%
Job cost · 100K + 10Kcalculated$0.225$0.28020%
Job cost · 1M + 100Kcalculated$2.25$2.8020%
Context window400,0001,000,0002.5×

Input and output rates are as published by each provider. Blended and job-cost rows are calculated comparison metrics, not published prices — how they are derived.

Benchmarks

Benchmark scores both GPT-5 and GPT-4.1 report
BenchmarkGPT-5GPT-4.1Leader
MMLU91%89%GPT-5
GPQA Diamond84%71%GPT-5
MATH95%87%GPT-5
HumanEval96%90%GPT-5
SWE-bench Verified75%55%GPT-5
LMArena Elo1399 Elo1346 EloGPT-5

Only suites both models report are listed, so a missing score is never shown as a loss. Figures are provider-published or from public leaderboards and are not independently re-run.

What each model is for

GPT-5

OpenAI · Frontier

OpenAI's 2025 flagship, unified reasoning + multimodal model with a 400K context. Replaces the GPT-4 line as the default ChatGPT and API model.

  • Unified reasoning + chat
  • 400K context
  • Native vision
  • Strong tool use

GPT-4.1

OpenAI · Frontier

Long-context coding-focused GPT-4 successor with a 1M-token window. Aimed at developers who need predictable instruction following over very long inputs.

  • 1M context window
  • Strong coding
  • Better instruction following than GPT-4o
  • Cheap relative to GPT-4

Frequently asked questions

Which is cheaper, GPT-5 or GPT-4.1?

GPT-4.1 is 2 per cent cheaper on blended cost, $3.80 per million tokens against $3.88. A single 100K-input, 10K-output job costs $0.280 on GPT-4.1 against $0.225 on GPT-5. Blended cost weights input at 70% and output at 30%; price your own token split for an exact answer, since the cheaper model on a blended basis is not always cheaper for your workload.

Which performs better, GPT-5 or GPT-4.1?

GPT-5 leads on 6 of the 6 benchmarks both models report. The widest gap is on LMArena Elo, where GPT-5 leads by 53 points. These are the figures each provider or public leaderboard publishes, not results we re-run, and a benchmark average can hide the specific behaviour your workload depends on.

Which has the larger context window, GPT-5 or GPT-4.1?

GPT-4.1 takes a 1,000,000-token context window against 400,000, giving 2.5× more room for long documents or whole-codebase work. The context window caps everything in a single request: prompt, retrieved documents, conversation history and the model’s own output all share it.

Can I compare GPT-5 and GPT-4.1 on my own numbers?

Yes. Open both in the side-by-side comparison tool to see every field at once, or use the token calculator to price your actual prompt and monthly request volume against each model. Both are free and need no sign-up.

Price it for your own workload

Related matchups

Terms used on this page

Prices and scores are recomputed on every deploy from the catalogue. Prices checked 12 August 2026.