modelbenchmark.io

GPT-4.1 mini

OpenAI · gpt-4-1-mini

Compare

Affordable GPT-4.1 lane for fast coding help and structured extraction

Specification

openai listing

Context
1M
Max output
33K
Released
2025-04-14
Knowledge cutoff
2024-04
Retires
2027-01-14
Open weights
no
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · openai list price

Input
$0.40
Output
$1.60
Cache read
$0.10
Cache write
free

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputazure$0.20
Batch inputazure$0.22
Batch outputazure$0.80
Batch outputazure$0.88
Priority inputazure$0.70
Priority inputazure$0.77
Priority outputazure$2.80
Priority outputazure$3.08

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

Quality

10 benchmarks · 3 sources

Composite
27th
percentile of 344 scored models
Rank
253 / 344
±0.04 sd
Evidence
10 × 3
3 or more benchmarks, from 2 or more sources
Effort range
—
one configuration only
coding17th2/3 bench
reasoning27th3/4 bench
math39th4/7 bench
knowledge7th1/1 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
MATH level 587.3 ±0.7defaultEpoch AI2025-04-14
GPQA diamond65.8 ±2.7defaultEpoch AI2025-04-14
OTIS Mock AIME 2024-202544.7 ±6.1defaultEpoch AI2025-04-14
Aider polyglot32.4default · aider diffAider2025-04-14
FrontierMath-v17.2 ±10.0default · 2 runsEpoch AI2025-04-14
Mystery Game Puzzles7.0 ±2.6defaultEpoch AI2026-08-27
Chess Puzzles1.0 ±1.0defaultEpoch AI2026-10-13
FrontierMath-Tiers-1-3-v26.7 ±1.5defaultEpoch AI2026-08-27
SWE-Bench verified23.9default · mini-SWE-agentSWE-bench—
SimpleQA Verified12.7 ±1.1defaultEpoch 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 30 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openaivendor$0.40$1.60$0.10—1M33K2027-01-14
poe$0.3636$1.4545$0.0909—1M33K—
302ai$0.40$1.60——1M33K—
abacus$0.40$1.60$0.10—1M33K—
aimlapi$0.40$1.60$0.10—1M33K—
azure
$0.40
$0.44
$1.60
$1.76
$0.10
$0.11
—1M33K2027-04-14
azure-cognitive-services$0.40$1.60$0.10—1M33K—
cloudflare-ai-gateway$0.40$1.60$0.10—1M33K—
edenai$0.40$1.60$0.10—1M33K—
helicone$0.40$1.60$0.10—1M33K—
impossibl$0.40$1.60$0.10—1M33K—
kilo$0.40$1.60$0.10—1M33K—
llmgateway$0.40$1.60$0.10—1M33K—
llmgateway-providers$0.40$1.60$0.10—1M33K—
lowrouter · auto$0.40$1.60$0.10—1M33K—
merge-gateway$0.40$1.60$0.10—1M33K—
nano-gpt$0.40$1.60$0.10—1M33K—
nearai$0.40$1.60$0.10—1M33K—
ofox$0.40$1.60$0.10—1M33K—
openrouter$0.40$1.60$0.10—1M33K—
orcarouter$0.40$1.60$0.10—1M33K—
prime$0.40$1.60——1M33K—
replicate · replicate$0.40$1.60—————
sap-ai-core$0.40$1.60$0.10—1M33K—
vercel$0.40$1.60$0.10—1M33K—
vercel_ai_gateway · vercel-ai-gateway$0.40$1.60$0.10free1M33K—
zerogpu · zerogpu$0.40$1.60$0.10—1M33K—
cortecs$0.434$1.704$0.134—1M33K—
anyapi————1M33K—
model-oracle-ai————1M33K—

Price history

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

DateHostField$/M
2026-09-02ofoxCache read$0.10
2026-09-19ofoxCache read$0.08
2026-10-17ofoxCache read$0.10
2026-09-02openrouterCache read$0.10
2026-10-10openrouterCache read$0.10
2026-09-02poeCache read$0.09
2026-10-22poeCache read$0.0909
2026-09-02ofoxInput$0.40
2026-09-19ofoxInput$0.32
2026-10-17ofoxInput$0.40
2026-09-02openrouterInput$0.40
2026-10-10openrouterInput$0.40
2026-09-02poeInput$0.36
2026-10-22poeInput$0.3636
2026-09-02ofoxOutput$1.60
2026-09-19ofoxOutput$1.28
2026-10-17ofoxOutput$1.60
2026-09-02openrouterOutput$1.60
2026-10-10openrouterOutput$1.60
2026-09-02poeOutput$1.40
2026-10-22poeOutput$1.4545
2026-10-13aimlapiCache read$0.13
2026-10-23aimlapiCache read$0.10
2026-10-13aimlapiInput$0.52
2026-10-23aimlapiInput$0.40
2026-10-13aimlapiOutput$2.08
2026-10-23aimlapiOutput$1.60

More from OpenAI

most-hosted first