Saltar al contenido principal
AITier

GPT-4.1 nano

OpenAIGPTProprietary

Descripción

GPT-4.1 nano is OpenAI's fastest and cheapest model available in the GPT-4.1 family. It delivers exceptional performance at a small size with its 1 million token context window. Ideal for tasks like classification or autocompletion.

Fecha de lanzamiento
2025-04-14
Parámetros
—
Longitud del contexto
1.0M
Modalidades
image, text

Radar de capacidades

25
general
19
coding
36
reasoning
37
science
10
agents
85
multimodal

Rankings

Dominio#PosiciónPuntuaciónFuente
Ranking de codificación529
18.0
AA
Ranking general517
27.0
AA
Ranking multimodal114
40.0
LS
Ciencia510
26.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Chat

IFEvalGoogle Research (2023)74.5%Aut.
Multi-IF57.2%Aut.
TAU-bench Retail22.6%Aut.
Multi-Challenge15.0%Aut.

General

MMLU80.1%Aut.
Internal API instruction following (hard)31.6%Aut.
Aider-Polyglot9.8%Aut.
Aider-Polyglot Edit6.2%Aut.

Language

MMMLU66.9%Aut.
COLLIE42.5%Aut.

Long Context

OpenAI-MRCR: 2 needle 128k36.6%Aut.
OpenAI-MRCR: 2 needle 1M12.0%Aut.
ComplexFuncBench5.7%Aut.

Math

MathVista56.2%Aut.
AIME 202429.4%Aut.

Multimodal

MMMU55.4%Aut.

Reasoning

CharXiv-D73.9%Aut.
GPQANYU + Cohere + Anthropic (2023)50.3%Aut.
CharXiv-R40.5%Aut.
Graphwalks BFS <128k25.0%Aut.
TAU-bench Airline14.0%Aut.
Graphwalks parents <128k9.4%Aut.
Graphwalks parents >128k5.6%Aut.
Graphwalks BFS >128k2.9%Aut.

Índices de evaluación AA

(Artificial Analysis)
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
84.8
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
65.7
Gpqa(NYU + Cohere + Anthropic (2023))
51.2
Livecodebench(UC Berkeley + MIT + Cornell (2024))
32.6
Ifbench(Google Research (2023))
32.0
Math Index(Artificial Analysis)
24.0
Aime 25(MAA (Mathematical Association of America))
24.0
Aime(MAA (Mathematical Association of America))
23.7
Lcr(Artificial Analysis)
20.3
Tau2(Sierra + U Toronto + Vector Institute (2025))
17.3
Coding Index(Artificial Analysis)
11.1
Intelligence Index(Artificial Analysis)
7.8
Hle(Center for AI Safety + Scale AI (2025))
3.8
Terminalbench Hard(Stanford × Laude Institute (2026))
3.8
Terminalbench V2 1
3.7
Tau Banking
3.5

Puntuaciones por categoría LLM Stats

(LLM Stats (zeroeval))
Legal
80
Finance
80
Instruction Following
70
Healthcare
70
Language
60
Math
60
Multimodal
60
Vision
60
Physics
50
Structured Output
50
Biology
50
Chemistry
50
Chat
40
Writing
40
Reasoning
30
General
30
Communication
30
Long Context
10
Spatial Reasoning
10
Code
10
Tool Calling
10

Precios

Precio de entrada$0.1 / 1M tokens
Precio de salida$0.4 / 1M tokens
Precio mixto (3:1)$0.175 / 1M tokens
Precio de lectura caché$0.025 / 1M tokens

Velocidad

Tokens/seg0.0
Retraso del primer token0.00s
Tiempo hasta la respuesta0.00s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

22 proveedores

Más barato: OpenAIMás caro: Cortecs
ProveedorEntradaSalida
1OpenAIMás barato
$0
$0
2SAP AI Core
$0.08
$0.26
3Poe
$0.09
$0.36
4Helicone
$0.1
$0.4
5302.AI
$0.1
$0.4
6NanoGPT
$0.1
$0.4
7Abacus
$0.1
$0.4
8OpenRouter
$0.1
$0.4
9Kilo Gateway
$0.1
$0.4
10Cloudflare AI Gateway
$0.1
$0.4
11Azure Cognitive Services
$0.1
$0.4
12Vercel AI Gateway
$0.1
$0.4
13DevPass (LLM Gateway)
$0.1
$0.4
14Azure
$0.1
$0.4
15NEAR AI Cloud
$0.1
$0.4
16OrcaRouter
$0.1
$0.4
17Merge Gateway
$0.1
$0.4
18Pioneer
$0.1
$0.4
19Impossibl
$0.1
$0.4
20Eden AI
$0.1
$0.4
21LLM Gateway
$0.1
$0.4
22Cortecs
$0.111
$0.434

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas

LLM StatsArtificial Analysis