GPT-4.1 vs GPT-4o
OpenAI vs OpenAI · Prices checked 12 August 2026
GPT-4.1 is 20 per cent cheaper on blended cost, $3.80 per million tokens against $4.75. A single 100K-input, 10K-output job costs $0.280 on GPT-4.1 against $0.350 on GPT-4o.
GPT-4.1 leads on 5 of the 6 benchmarks both models report. The widest gap is on LMArena Elo, where GPT-4.1 leads by 30 points. 1 suite tied. GPT-4.1 takes a 1,000,000-token context window against 128,000, giving 7.8× more room for long documents or whole-codebase work. GPT-4.1 was released Apr 2025; GPT-4o May 2024.
Pricing and capacity
| Metric | GPT-4.1 | GPT-4o | Difference |
|---|---|---|---|
| Input / 1M tokens | $2.00 | $2.50 | 20% |
| Output / 1M tokens | $8.00 | $10.00 | 20% |
| Blended · 70/30calculated | $3.80 | $4.75 | 20% |
| Blended · 50/50calculated | $5.00 | $6.25 | 20% |
| Blended · 80/20calculated | $3.20 | $4.00 | 20% |
| Blended · 20/80calculated | $6.80 | $8.50 | 20% |
| Job cost · 100K + 10Kcalculated | $0.280 | $0.350 | 20% |
| Job cost · 1M + 100Kcalculated | $2.80 | $3.50 | 20% |
| Context window | 1,000,000 | 128,000 | 7.8× |
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 | GPT-4.1 | GPT-4o | Leader |
|---|---|---|---|
| MMLU | 89% | 88% | GPT-4.1 |
| GPQA Diamond | 71% | 53% | GPT-4.1 |
| MATH | 87% | 76% | GPT-4.1 |
| HumanEval | 90% | 90% | Level |
| SWE-bench Verified | 55% | 33% | GPT-4.1 |
| LMArena Elo | 1346 Elo | 1316 Elo | GPT-4.1 |
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
Frequently asked questions
Which is cheaper, GPT-4.1 or GPT-4o?
GPT-4.1 is 20 per cent cheaper on blended cost, $3.80 per million tokens against $4.75. A single 100K-input, 10K-output job costs $0.280 on GPT-4.1 against $0.350 on GPT-4o. 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-4.1 or GPT-4o?
GPT-4.1 leads on 5 of the 6 benchmarks both models report. The widest gap is on LMArena Elo, where GPT-4.1 leads by 30 points. 1 suite tied. 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-4.1 or GPT-4o?
GPT-4.1 takes a 1,000,000-token context window against 128,000, giving 7.8× 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-4.1 and GPT-4o 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.