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
24
general
31
coding
36
reasoning
33
scienceest.
10
agents
85
multimodal
Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Ranking de codificación | 356 | 21.0 | AA |
| Ranking general | 392 | 28.0 | AA |
| Razonamiento matemático | 242 | 36.0 | AA |
| Ranking multimodal | 78 | 60.0 | LS |
| Razonamiento | 107 | 17.0 | LS |
| Ciencia | 355 | 32.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
Biology
GPQA
50.3%Aut.
Code
Aider-Polyglot
9.8%Aut.
Aider-Polyglot Edit
6.2%Aut.
Communication
Multi-IF
57.2%Aut.
TAU-bench Retail
22.6%Aut.
Multi-Challenge
15.0%Aut.
TAU-bench Airline
14.0%Aut.
Finance
MMLU
80.1%Aut.
General
IFEval
74.5%Aut.
MMMLU
66.9%Aut.
MMMU
55.4%Aut.
Internal API instruction following (hard)
31.6%Aut.
Language
COLLIE
42.5%Aut.
Long Context
OpenAI-MRCR: 2 needle 128k
36.6%Aut.
OpenAI-MRCR: 2 needle 1M
12.0%Aut.
ComplexFuncBench
5.7%Aut.
Graphwalks parents >128k
5.6%Aut.
Graphwalks BFS >128k
2.9%Aut.
Math
MathVista
56.2%Aut.
AIME 2024
29.4%Aut.
Multimodal
CharXiv-D
73.9%Aut.
CharXiv-R
40.5%Aut.
Reasoning
Graphwalks BFS <128k
25.0%Aut.
Graphwalks parents <128k
9.4%Aut.
Índices de evaluación AA
Math Index24.0
Intelligence Index7.3
Math 5000.8
Mmlu Pro0.7
Gpqa0.5
Livecodebench0.3
Ifbench0.3
Scicode0.3
Aime 250.2
Aime0.2
Tau20.2
Lcr0.2
Hle0.0
Terminalbench Hard0.0
Puntuaciones por categoría LLM Stats
Legal80
Finance80
Instruction Following70
Healthcare70
Language60
Math60
Multimodal60
Vision60
Physics50
Structured Output50
General50
Biology50
Chemistry50
Writing40
Reasoning30
Communication30
Long Context10
Spatial Reasoning10
Code10
Tool Calling10
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/seg185.4
Retraso del primer token0.50s
Tiempo hasta la respuesta0.50s
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
15 proveedores
Más barato: OpenAIMás caro: Merge Gateway
ProveedorEntradaSalida
1OpenAIMás barato
$0
$0
2Poe
$0.09
$0.36
3Helicone
$0.1
$0.4
4302.AI
$0.1
$0.4
5NanoGPT
$0.1
$0.4
6Abacus
$0.1
$0.4
7OpenRouter
$0.1
$0.4
8Kilo Gateway
$0.1
$0.4
9Azure Cognitive Services
$0.1
$0.4
10Vercel AI Gateway
$0.1
$0.4
11LLM Gateway
$0.1
$0.4
12Azure
$0.1
$0.4
13NEAR AI Cloud
$0.1
$0.4
14OrcaRouter
$0.1
$0.4
15Merge Gateway
$0.1
$0.4
Comparar precios entre diferentes proveedores de API para este modelo.