modelbenchmark.io

GPT-4.1 nano

OpenAI · gpt-4-1-nano

Compare

Tiny GPT-4.1 option for classification, routing, and very high-volume tasks

Specification

openai listing

Context
1M
Max output
33K
Released
2025-04-14
Knowledge cutoff
2024-04
Retires
2026-10-23
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · openai list price

Input
$0.10
Output
$0.40
Cache read
$0.025
Cache write
free

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputazure$0.05
Batch inputazure$0.055
Batch outputazure$0.20
Batch outputazure$0.22
Priority inputopenai$0.20
Priority outputopenai$0.80

Batch input is 50% below the interactive input price at the same listing.

Quality

7 benchmarks · 2 sources

Composite
19th
percentile of 344 scored models
Rank
278 / 344
±0.05 sd
Evidence
7 × 2
3 or more benchmarks, from 2 or more sources
Effort range
—
one configuration only
coding6th1/3 bench
reasoning18th2/4 bench
math38th3/7 bench
knowledge0th1/1 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
MATH level 570.0 ±1.0defaultEpoch AI2025-04-14
GPQA diamond48.9 ±2.5defaultEpoch AI2025-04-14
OTIS Mock AIME 2024-202528.9 ±6.0defaultEpoch AI2025-04-14
FrontierMath-v10.5 ±0.0default · 2 runsEpoch AI2025-04-14
Chess Puzzles0.0 ±0.0defaultEpoch AI2026-10-13
Aider polyglot8.9default · aider wholeAider2025-04-14
SimpleQA Verified6.0 ±0.8defaultEpoch AI2026-08-31

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 21 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openaivendor$0.10$0.40$0.025—1M33K2026-10-23
poe$0.09$0.36$0.022—1M33K—
302ai$0.10$0.40——1M33K—
abacus$0.10$0.40$0.025—1M33K—
azure
$0.10
$0.11
$0.40
$0.44
$0.025
$0.028
—1M33K2027-04-14
azure-cognitive-services$0.10$0.40$0.025—1M33K—
cloudflare-ai-gateway$0.10$0.40$0.025—1M33K—
edenai$0.10$0.40$0.025—1M33K—
helicone$0.10$0.40$0.025—1M33K—
impossibl$0.10$0.40$0.025—1M33K—
kilo$0.10$0.40$0.03—1M943K—
merge-gateway$0.10$0.40$0.025—1M33K—
nano-gpt$0.10$0.40$0.025—1M33K—
openrouter$0.10$0.40$0.03—1M943K—
orcarouter$0.10$0.40$0.025—1M33K—
prime$0.10$0.40——1M943K—
replicate · replicate$0.10$0.40—————
sap-ai-core$0.10$0.40——1M33K—
vercel$0.10$0.40$0.03—1M33K—
vercel_ai_gateway · vercel-ai-gateway$0.10$0.40$0.025free1M33K—
cortecs$0.111$0.434$0.056—1M33K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02azureCache read$0.025
2026-09-17azureCache read$0.025
2026-09-02kiloCache read$0.025
2026-10-29kiloCache read$0.03
2026-09-02openrouterCache read$0.025
2026-10-10openrouterCache read$0.025
2026-10-26openrouterCache read$0.03
2026-09-02vercelCache read$0.025
2026-10-24vercelCache read$0.03
2026-09-02openrouterInput$0.10
2026-10-10openrouterInput$0.10
2026-09-02sap-ai-coreInput$0.08
2026-10-22sap-ai-coreInput$0.10
2026-09-02openrouterOutput$0.40
2026-10-10openrouterOutput$0.40
2026-09-02sap-ai-coreOutput$0.26
2026-10-22sap-ai-coreOutput$0.40
2026-10-13aimlapiCache read$0.0325
2026-10-23aimlapiCache read$0.025
2026-10-13aimlapiInput$0.13
2026-10-23aimlapiInput$0.10
2026-10-13aimlapiOutput$0.52
2026-10-23aimlapiOutput$0.40

More from OpenAI

most-hosted first