ModelPriceWatch.com
Last scan 2026-08-01 Models tracked 181 Providers 27 Cheapest paid Granite 4.0 Micro $0.017/Mtok in Every price links to its source

GPT-4.1 nano

by OpenAI

Deprecated budget cheap tier
Deprecated — shuts down Oct 23, 2026. Still purchasable until then, but the provider has announced end-of-life. Don't start new work on it.
Availability: Snapshot gpt-4.1-nano-2025-04-14 is labelled Deprecated; migration target gpt-5.6-luna.

Today's price · per 1M tokens

Input

$0.100

per 1M tokens

Output

$0.400

per 1M tokens

Blended

$0.250

avg of input & output $/1M

Cached input

$0.025

25% of input — prompt caching

Source: official OpenAI pricing · read Jul 4, 2026 MODELPRICEWATCH.COM · 2026-08-01

Overview

Smallest and cheapest GPT-4.1 variant. Ideal for classification and simple tasks at scale.

Capabilities

struck through = not supported
Input 2/5
Text ✓ Image ✓ Audio Video PDF
Output 1/5
Text ✓ Image Audio Video Embedding
Features 3/9
Prompt caching ✓ Reasoning Coding Fast inference Long context ✓ Open weights Multimodal ✓ Web search Realtime

Benchmark performance

accuracy % · higher is better
Avg benchmark score58.6%
Perf per $/Mtok234.4
GPQA Diamond
50.3%
SWE-Bench Verified vendor
15%
Humanity's Last Exam vendor
8%
ARC-AGI 2 vendor
8%
AIME 2025 vendor
25%
MMMLU
66.9%
BFCL vendor
60%
HumanEval vendor
75%
MATH 500 vendor
55%
How it stacks up
  • Ranks #52 of 68 benchmarked models by average score
  • Ranks #109 of 133 comparably-measured models by percentile score, across 2 independent measurements
  • Ranks #35 of 133 comparably-tested models by normalized performance per dollar
  • Strongest at GPQA Diamond — 50.3%, #48 of 57

250 tokens/sec output

Source: Vellum LLM Leaderboard · updated Aug 1, 2026 · See full rankings →

Specifications

Provider
OpenAI
Context window
1M tokens
Modality
text, image
Parameters
Proprietary
Open source
No — proprietary
Released
Apr 14, 2025
Status
Deprecated ends Oct 23, 2026
Last updated
Jul 4, 2026
Tags
budgetmultimodal

Availability verified: Jul 25, 2026 — per OpenAI's own deprecation notice