openai Vision

GPT-4.1 pricing & benchmarks

Released Apr 14, 2025 · served by 2 providers

Input / 1M tokens$2.00
Output / 1M tokens$8.00
Context window1.0M
Cached input$0.500
1M in + 300K out$4.40

What GPT-4.1 is

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...

Providers and prices for GPT-4.1

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
OpenAIcheapest $2.00 $8.00 1.0M 95.6%
Azure $2.20 $8.80 1.0M 100.0%

GPT-4.1 benchmark results

Design Arena head-to-head results, as reported through the OpenRouter model API.

CategoryArenaRankEloWin rate
gamedev models #72 1136 59.1%
dataviz models #73 1133 59.5%
uicomponent models #90 1038 49.7%
codecategories models #94 1056 50.9%
website models #94 1063 52.3%
3d models #103 907 30.9%

FAQ

How much does the GPT-4.1 API cost?

$2.00 per 1M input tokens and $8.00 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $4.40.

Is GPT-4.1 free?

No. It is a paid model starting at $2.00 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for GPT-4.1?

OpenAI at $2.00 input / $8.00 output per 1M tokens.

Can I self-host GPT-4.1?

No. GPT-4.1 is closed-weight and only available through hosted APIs.