GPT-4.1 vs GPT-4o

API pricing, context window and capabilities for GPT-4.1 and GPT-4o, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.

Verdict

computed from the published numbers

GPT-4.1 wins on price, on intelligence and on context window. Benchmark data is unavailable for one or both models.

Price
GPT-4.1
Coding
Not called
Intelligence
GPT-4.1
Context window
GPT-4.1

Key takeaways

who wins on what, from the published numbers

GPT-4.1 wins

  • Cheaper input ($2.00 vs $2.50 /1M)
  • Cheaper output ($8.00 vs $10.00 /1M)
  • Larger context window (1M vs 131K)
  • Higher max output (33K vs 16K)
  • Has web search

GPT-4o wins

  • More serving providers (5 vs 6)
  • Supports audio
Cheaper overall
GPT-4.1
$2.00 + $8.00 /1M
Larger context
GPT-4.1
1M
More providers
GPT-4o
6 providers

Pricing & specs

cheapest serving route · per 1M tokens
GPT-4.1GPT-4o
Input $/1M$2.00 best$2.50
Output $/1M$8.00 best$10.00
Context window1M best131K
Max output33K best16K
Serving providers5 6 best
Releasedn/a 2024-05-13

Benchmarks

Artificial Analysis indices, side by side
GPT-4.1GPT-4o
Intelligence19.4 best11.2
GPQA Diamond67% best54%
Output speed85 t/s 99 t/s best
Latency (TTFT)5.28s 5.19s best

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
GPT-4.1
via Azure
$18
GPT-4o
via Azure
$23

Capabilities

feature support, side by side
FeatureGPT-4.1GPT-4o
Vision
Tool use
Reasoning
Audio
Prompt caching
Structured output
Web search

Related comparisons

Frequently asked questions

Which is cheaper, GPT-4.1 or GPT-4o?
GPT-4.1 is cheaper for input ($2.00 vs $2.50 per 1M tokens). GPT-4.1 is cheaper for output ($8.00 vs $10.00 per 1M tokens).
What is the context window difference between GPT-4.1 and GPT-4o?
GPT-4.1 has a 1M-token context window and GPT-4o has 131K tokens, so GPT-4.1 can take a larger prompt.
How do GPT-4.1 and GPT-4o compare on benchmarks?
On the tracked Artificial Analysis indices, GPT-4.1 leads on intelligence.
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI