GPT-4.1 nano
OpenAIGPTProprietary
Описание
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.
Дата выхода
2025-04-14
Параметры
—
Длина контекста
1.0M
Модальности
image, text
Радар способностей
25
general
19
coding
36
reasoning
37
science
10
agents
85
multimodal
Рейтинги
| Домен | #Место | Оценка | Источник |
|---|---|---|---|
| Рейтинг кодинга | 526 | 18.0 | AA |
| Общий рейтинг | 514 | 27.0 | AA |
| Мультимодальный рейтинг | 114 | 40.0 | LS |
| Наука | 507 | 26.0 | AA |
Оценки бенчмарков (LLM Stats)
(LLM Stats (zeroeval))Chat
IFEvalGoogle Research (2023)
74.5%Сам.
Multi-IF
57.2%Сам.
TAU-bench Retail
22.6%Сам.
Multi-Challenge
15.0%Сам.
General
MMLU
80.1%Сам.
Internal API instruction following (hard)
31.6%Сам.
Aider-Polyglot
9.8%Сам.
Aider-Polyglot Edit
6.2%Сам.
Language
MMMLU
66.9%Сам.
COLLIE
42.5%Сам.
Long Context
OpenAI-MRCR: 2 needle 128k
36.6%Сам.
OpenAI-MRCR: 2 needle 1M
12.0%Сам.
ComplexFuncBench
5.7%Сам.
Math
MathVista
56.2%Сам.
AIME 2024
29.4%Сам.
Multimodal
MMMU
55.4%Сам.
Reasoning
CharXiv-D
73.9%Сам.
GPQANYU + Cohere + Anthropic (2023)
50.3%Сам.
CharXiv-R
40.5%Сам.
Graphwalks BFS <128k
25.0%Сам.
TAU-bench Airline
14.0%Сам.
Graphwalks parents <128k
9.4%Сам.
Graphwalks parents >128k
5.6%Сам.
Graphwalks BFS >128k
2.9%Сам.
Индексы оценки 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 13.7
Tau Banking3.5
Оценки категорий LLM Stats
(LLM Stats (zeroeval))Legal80
Finance80
Instruction Following70
Healthcare70
Language60
Math60
Multimodal60
Vision60
Physics50
Structured Output50
Biology50
Chemistry50
Chat40
Writing40
Reasoning30
General30
Communication30
Long Context10
Spatial Reasoning10
Code10
Tool Calling10
Цены
Цена ввода$0.1 / 1M токенов
Цена вывода$0.4 / 1M токенов
Смешанная цена (3:1)$0.175 / 1M токенов
Цена чтения кэша$0.025 / 1M токенов
Скорость
Токенов/сек0.0
Задержка первого токена0.00s
Время до первого ответа0.00s
Рейтинг цен провайдеров
Рейтинг цен провайдеров
22 провайдеров
Самый дешевый: OpenAIСамый дорогой: Cortecs
ПровайдерВводВывод
1OpenAIСамый дешевый
$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
Сравнение цен разных API-провайдеров для этой модели.