Saltar al contenido principal

GPT-5.4 nano (medium)

OpenAIGPTProprietary

Descripción

GPT-5.4 nano is OpenAI's cheapest GPT-5.4-class model for simple high-volume tasks. It is optimized for classification, data extraction, ranking, and lightweight coding subagents, while preserving strong reasoning, multimodal understanding, and tool use for latency-sensitive workloads.

Fecha de lanzamiento
2026-03-17
Parámetros
Longitud del contexto
400K
Modalidades
image, text

Radar de capacidades

28
general
38
coding
76
reasoning
51
science
60
agents
85
multimodal

Rankings

Dominio#PosiciónPuntuaciónFuente
Capacidad agéntica145
22.0
LS
Ranking de codificación140
65.0
AA
Ranking general192
56.0
AA
Razonamiento matemático14
91.0
LB
Ranking multimodal56
43.0
LS
Razonamiento24
81.0
LB
Ciencia187
56.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

MCP Atlas56.1%Aut.
SWE-Bench ProPrinceton NLP (2024)52.4%Aut.
Terminal-Bench 2.0Stanford × Laude Institute (2026)46.3%Aut.
OSWorld-Verified39.0%Aut.
Finance Agent v238.2%
Toolathlon35.5%Aut.

Biology

GPQANYU + Cohere + Anthropic (2023)82.8%Aut.

Communication

Tau2 Telecom92.5%Aut.

General

LiveBench70.1%
MMMU-Pro66.1%Aut.
MRCR v2 (8-needle)33.1%Aut.

Math

Humanity's Last Exam24.3%Aut.

Multimodal

OmniDocBench 1.575.8%Aut.

Reasoning

Graphwalks BFS <128k73.4%Aut.
Graphwalks parents <128k50.8%Aut.

Índices de evaluación AA

(Artificial Analysis)
Intelligence Index(Artificial Analysis)
30.8
Gpqa(NYU + Cohere + Anthropic (2023))
0.8
Lcr(Artificial Analysis)
0.7
Ifbench(Google Research (2023))
0.6
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.5
Scicode(UIUC + Argonne National Lab (2024))
0.4
Terminalbench Hard(Stanford × Laude Institute (2026))
0.3
Hle(Center for AI Safety + Scale AI (2025))
0.2

Puntuaciones por categoría LLM Stats

(LLM Stats (zeroeval))
Spatial Reasoning
9
Vision
6
Reasoning
3
General
2
Communication
90
Physics
80
Structured Output
80
Biology
80
Chemistry
80
Multimodal
70
Tool Calling
60
Long Context
50
Math
50
Code
50
Finance
40
Agents
40
Healthcare
30

Precios

Precio de entrada$0.2 / 1M tokens
Precio de salida$1.25 / 1M tokens
Precio mixto (3:1)$0.463 / 1M tokens
Precio de lectura caché$0.02 / 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

10 proveedores

Más barato: OpenAIMás caro: Pioneer
ProveedorEntradaSalida
1OpenAIMás barato
$0
$0
2302.AI
$0.2
$1.25
3Abacus
$0.2
$1.25
4Vivgrid
$0.2
$1.25
5GitHub Copilot
$0.2
$1.25
6OpenCode Zen
$0.2
$1.25
7Azure Cognitive Services
$0.2
$1.25
8LLM Gateway
$0.2
$1.25
9Azure
$0.2
$1.25
10Pioneer
$0.2
$1.25

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas