ModelPriceWatch.com
Last scan 2026-10-30 Models tracked 303 Providers 41 Cheapest paid pplx-decider-flash-v1.2 $0.010/Mtok in Every price links to its source

GPT-4.1 nano

by OpenAI

Retired budget cheap tier
Email me when GPT-4.1 nano gets cheaper
Retired on . No longer served on the endpoint we price — the figures below are kept for historical reference only. Replaced by GPT-5.6 Luna. Full retirement status & replacements →
Availability: OpenAI shut down gpt-4.1-nano (gpt-4.1-nano-2025-04-14) on 2026-10-23 (deprecations page, section "2026-04-22: Legacy GPT model snapshots": "Access to these models was shut down on October 23, 2026"). The substitute it names is GPT-5.6 Luna (gpt-5.6-luna). The rate shown is the last public price; you can no longer buy this model from OpenAI. Checked against OpenAI's deprecations page on 2026-10-24.

Today's price · per 1M tokens

Input

$0.100

per 1M tokens

Output

$0.400

per 1M tokens

Blended

$0.175

blended $/1M — 3:1 weighted input:output

Cached input

$0.025

25% of input — prompt caching

Source: official OpenAI pricing · read MODELPRICEWATCH.COM · 2026-10-30

Price receipt

Historical price.This model is retired — withdrawn on — so the provider no longer sells it and its page can no longer confirm this number: a price for a model no longer on sale is unconfirmable by definition, not missing. The figures above are the last prices we recorded for this model, kept as a historical record rather than a live quote.

Overview

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

Capabilities

struck through = not supported
Input 2/4
Text ✓ Image ✓ Audio Video
Output
Text ✓
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 $/Mtok334.9
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%
Independent composite scores
  • AA-Omniscience Index: -57.6 (−100–100)
  • GDPval-AA v2: -206 ELO (Real-world work tasks, human baseline = 1000)
How it stacks up
  • Ranks #68 of 100 benchmarked models by average score
  • Ranks #180 of 194 comparably-measured models by percentile score, across 4 independent measurements
  • Ranks #104 of 194 comparably-tested models by normalized performance per dollar
  • Strongest at GPQA Diamond — 50.3%, #66 of 71

250 tokens/sec output

Source: Vellum LLM Leaderboard · updated · See full rankings →

Specifications

Provider
OpenAI
Context window
1M tokens
Modality
text, image
Parameters
Proprietary
Open source
No — proprietary
Released
Status
Retired ended
Last updated
Tags
budgetmultimodalretired

Availability verified: — per OpenAI's own deprecation notice

Try on OpenAI Official pricing page