Model comparison
GPT-4.1 vs GPT-4.1 Mini
Price history, scores and specs for both models, line by line. Every value shows where it came from and when we last confirmed it.
OpenAI
GPT-4.1
GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning.
OpenAI
GPT-4.1 Mini
GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.
Quick take
Where each one leads
- GPT-4.1 Mini costs less to send text to: $0.400 per million tokens, against $2.00 per million tokens for GPT-4.1.
- GPT-4.1 Mini costs less per word it writes: $1.60 per million tokens, against $8.00 per million tokens for GPT-4.1.
- GPT-4.1 scores higher on the Artificial Analysis Intelligence Index: 12.7 to 10.2.
- More people run GPT-4.1 Mini through OpenRouter than GPT-4.1 right now.
Each line comes from a checked value in the tables below. Pick on your workload: price and usage matter for high volume, context and scores for long documents and agent loops.
Price history
Prices side by side, day by day
- GPT-4.1
- GPT-4.1 Mini
- GPT-4.1
- GPT-4.1 Mini
Prices are the listed OpenRouter base rates in US dollars. A day we could not confirm is left out of the line, never filled in.
Price
What each one costs now
| Measure | GPT-4.1 | GPT-4.1 Mini |
|---|---|---|
| Input price | $2.00 per million tokens | $0.400 per million tokens Leads |
| Output price | $8.00 per million tokens | $1.60 per million tokens Leads |
Scores
Benchmarks, with source and date
| Measure | GPT-4.1 | GPT-4.1 Mini |
|---|---|---|
| Artificial Analysis Intelligence Index | 12.7 Leads | 10.2 |
| Artificial Analysis Coding Index | Not checked yet | 20.2 |
| LMArena text rating (Elo) | 1,383 Leads | 1,341 |
| LMArena vision rating (Elo) | 1,210 Leads | 1,181 |
| Design Arena rating (Elo) | 1,104 Leads | 1,064 |
Specs
Context, modalities and tool use
| Measure | GPT-4.1 | GPT-4.1 Mini |
|---|---|---|
| Context window | 1,047,576 tokens | 1,047,576 tokens |
| Reads | Images, Text, Files | Images, Text, Files |
| Writes | Text | Text |
| Tool calling | Yes | Yes |
| Reasoning mode | No | No |
| Open weights | No | No |
| Listed since | 14 Apr 2025 | 14 Apr 2025 |
Usage
How much each one is used
| Measure | GPT-4.1 | GPT-4.1 Mini |
|---|---|---|
| Tokens served on OpenRouter in a day | 8.7B (for 10 Nov 2026) | 18B Leads (for 10 Nov 2026) |
| Requests on OpenRouter in a day | 3.1M (for 10 Nov 2026) | 5.5M Leads (for 10 Nov 2026) |
| Tool calls on OpenRouter in a day | 222.7K (for 10 Nov 2026) | 235.6K Leads (for 10 Nov 2026) |
| Token usage, last 7 days | Up 5% on the week before (for 10 Nov 2026) | Up 7% on the week before Leads (for 10 Nov 2026) |
- GPT-4.1
- GPT-4.1 Mini
How this works
One link, either order
This link stays the same whichever order you name the two models in, so you can share it as it is. A line appears only when at least one model has a value we confirmed from a source; values we have not confirmed are left out, never guessed. To add a third record of any type, use the open comparison. Read how we check facts.