跳转到主要内容

GPT-4.1 nano

OpenAIGPTProprietary

描述

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.

发布日期
2025-04-14
参数规模
上下文长度
1.0M
支持模态
image, text

能力雷达图

26
general
20
coding
36
reasoning
33
science
10
agents
85
multimodal

排行榜排名

领域#排名分数来源
代码能力榜445
18.0
AA
通用能力榜442
29.0
AA
多模态榜77
29.0
LS
科学能力418
32.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)50.3%自报

Code

Aider-Polyglot9.8%自报
Aider-Polyglot Edit6.2%自报

Communication

Multi-IF57.2%自报
TAU-bench Retail22.6%自报
Multi-Challenge15.0%自报
TAU-bench Airline14.0%自报

Finance

MMLU80.1%自报

General

IFEvalGoogle Research (2023)74.5%自报
MMMLU66.9%自报
MMMU55.4%自报
Internal API instruction following (hard)31.6%自报

Language

COLLIE42.5%自报

Long Context

OpenAI-MRCR: 2 needle 128k36.6%自报
OpenAI-MRCR: 2 needle 1M12.0%自报
ComplexFuncBench5.7%自报
Graphwalks parents >128k5.6%自报
Graphwalks BFS >128k2.9%自报

Math

MathVista56.2%自报
AIME 202429.4%自报

Multimodal

CharXiv-D73.9%自报
CharXiv-R40.5%自报

Reasoning

Graphwalks BFS <128k25.0%自报
Graphwalks parents <128k9.4%自报

AA 评测指数

(Artificial Analysis)
Math Index(Artificial Analysis)
24.0
Coding Index(Artificial Analysis)
11.1
Intelligence Index(Artificial Analysis)
9.6
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
0.8
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.7
Gpqa(NYU + Cohere + Anthropic (2023))
0.5
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.3
Ifbench(Google Research (2023))
0.3
Scicode(UIUC + Argonne National Lab (2024))
0.3
Aime 25(MAA (Mathematical Association of America))
0.2
Aime(MAA (Mathematical Association of America))
0.2
Lcr(Artificial Analysis)
0.2
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.2
Hle(Center for AI Safety + Scale AI (2025))
0.0
Terminalbench Hard(Stanford × Laude Institute (2026))
0.0
Terminalbench V2 1
0.0
Tau Banking
0.0

LLM Stats 分类评分

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

定价

输入价格$0.1 / 1M tokens
输出价格$0.4 / 1M tokens
混合价格(3:1)$0.175 / 1M tokens
缓存读取价格$0.025 / 1M tokens

速度

Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s

供应商价格排行

供应商价格排行

19 个供应商

最便宜: OpenAI最贵: Cortecs
供应商输入输出
1OpenAI最便宜
$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
10Azure Cognitive Services
$0.1
$0.4
11Vercel AI Gateway
$0.1
$0.4
12LLM Gateway
$0.1
$0.4
13Azure
$0.1
$0.4
14NEAR AI Cloud
$0.1
$0.4
15OrcaRouter
$0.1
$0.4
16Merge Gateway
$0.1
$0.4
17Pioneer
$0.1
$0.4
18Impossibl
$0.1
$0.4
19Cortecs
$0.111
$0.434

比较该模型在不同 API 供应商之间的定价。

外部链接