GPT-4.1 Nano

OpenAI released 2025-04-14

$0.175 per million tokens, balanced

DeepSeek V4 Flash 0731 scores higher and costs less — but you would give something up.

+42.2 on the capability index and 40% cheaper ($0.105/M against $0.175/M). What you lose:

  • no image, file input

Capability scores do not measure context length, output ceiling or which inputs a model accepts, so a higher score does not mean a drop-in replacement.

The same model via batch is 50% cheaper ($0.087/M) — same weights, different latency.

Every price dimension

Input$0.100/M
Output$0.400/M
Cached input$0.025/M
Web search$0.01/call

Independent scores

Intelligence9.6
Coding11.1
Agentic1.2

Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.

Capability

Context window1.0M
Max output33K
Input modesimage, text, file
Tool useyes
Reasoningno
Knowledge cutoff2024-06-30

Provenance

Price sourceopenrouter.ai
Fetched2026-08-24
Quality dataverified

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

Markdown for LLMs