Baseten:模型智能、性能与价格

Baseten
Baseten

本分析旨在帮助你根据使用场景,选择 Baseten 提供的最佳模型。

最智能

Updated
#1
GLM-5.3 (max)GLM-5.3 (max)
45
#2
GLM-5.3 (max) (FAST)GLM-5.3 (max) (FAST)
45
#3
Kimi K3 (max)Kimi K3 (max)
44
#4
GLM-5.3-FlashGLM-5.3-Flash
42
#5
DeepSeek V4.1 Flash (max)DeepSeek V4.1 Flash (max)
40

Intelligence Index

共 23 个模型

速度最快

#1
Inkling SmallInkling Small
323 t/s
#2
DeepSeek V4.1 Flash (max)DeepSeek V4.1 Flash (max)
307 t/s
#3
gpt-oss-120b (low)gpt-oss-120b (low)
296 t/s
#4
gpt-oss-120b (high)gpt-oss-120b (high)
285 t/s
#5
GLM-5.2 (max) (FAST)GLM-5.2 (max) (FAST)
277 t/s

输出速度

共 23 个模型

价格最低

#1
DeepSeek V4 Flash 0731 (max)DeepSeek V4 Flash 0731 (max)
$0.07
#2
GLM-5.3-FlashGLM-5.3-Flash
$0.10
#3
gpt-oss-120b (high)gpt-oss-120b (high)
$0.14
#4
gpt-oss-120b (low)gpt-oss-120b (low)
$0.14
#5
DeepSeek V4.1 Flash (max)DeepSeek V4.1 Flash (max)
$0.20

每 100 万 token 的混合价格

共 23 个模型

Baseten 提供 23 个模型,每个模型的智能、性能和价格特征各不相同。 下方对比了各模型的关键指标。

  • 智能方面,Baseten 上表现最好的模型是 GLM-5.3 (max)(45)、GLM-5.3 (max) (FAST)(45)和Kimi K3 (max)(44)。
  • 输出速度方面,最快的模型是 Inkling Small(323 t/s)、DeepSeek V4.1 Flash (max)(307 t/s)和gpt-oss-120b (low)(296 t/s)。
  • 延迟方面,DeepSeek V4 Pro (Non-reasoning)(0.62 秒)、GLM-4.7 (Non-reasoning)(0.71 秒)和GLM-5.2 (Non-reasoning)(1.60 秒) 的首个答案 Token 延迟最低。
  • 价格方面,DeepSeek V4 Flash 0731 (max)($0.07)、GLM-5.3-Flash($0.10)和gpt-oss-120b (high)($0.14) 每 100 万 token 的混合价格最低。 各模型价格最多相差 2.8 倍。
  • 上下文窗口方面,GLM-5.3 (max)(1M)、Kimi K3 (max)(1M)和DeepSeek V4 Flash 0731 (max)(1M) 支持 Baseten 上最大的上下文窗口。

亮点

Updated
Artificial Analysis Intelligence Index · Higher is better
Output tokens per second · Higher is better
USD per 1M tokens (blended) · Lower is better

智能评测

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench v4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1
Estimate (independent evaluation forthcoming)

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
See more

Agentic knowledge work, (Elo-500)/2000

Agentic real-world work tasks, (Elo-500)/2000

Agentic SaaS workflows

Agentic coding & terminal use

Coding

Reasoning & knowledge

Professional document reasoning, All-pass

Physics reasoning

Long context reasoning

Legal agentic work, criterion pass rate

Agentic business operations

Quantitative analysis on spreadsheets & documents

Instruction following

Agentic tool use

Long-horizon agentic tasks

Kubernetes incident root-cause analysis

Visual reasoning

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

上下文窗口

Context Window

Context window: tokens limit · Higher is better

价格

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

性能摘要

Output Speed vs. Price

Output speed: output tokens per second · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

速度

按输出速度(每秒 token 数)衡量

Output Speed

Output tokens per second · Higher is better

延迟

按首 Token 延迟(秒)衡量

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time

端到端响应时间

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time vs. Price

End-to-end response time: end-to-end seconds to output 500 tokens · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

进一步分析
Z AI 标志
GLM-5.3 (max)
1.05M
开放
45
$1.43
126
1.39
21.22
15.86
Z AI 标志
GLM-5.3 (max) (FAST)
1M
开放
45
$2.15
209
1.20
13.15
9.56
Kimi 标志
Kimi K3 (max)
1.05M
开放
44
$2.01
95
0.78
27.18
21.12
Z AI 标志
GLM-5.3-Flash
1.05M
开放
42
$0.30
181
0.73
14.53
11.04
DeepSeek 标志
DeepSeek V4.1 Flash (max)
1M
开放
40
$2.18
307
0.67
8.82
6.52
DeepSeek 标志
DeepSeek V4 Pro 0813 (max)
1M
开放
36
$6.17
162
1.04
16.43
12.32
DeepSeek 标志
DeepSeek V4 Flash 0731 (max)
1.05M
开放
35
$0.44
257
0.64
10.39
7.80
Z AI 标志
GLM-5.2 (max) (FAST)
524k
开放
34
$1.04
277
1.88
10.91
7.23
Z AI 标志
GLM-5.2 (max)
1.05M
开放
34
$0.65
132
1.82
20.74
15.14
Kimi 标志
Kimi K2.6
262k
开放
31*
--
191
0.60
26.51
23.29
DeepSeek 标志
DeepSeek V4 Pro (max)
1M
开放
31
$3.73
141
0.56
35.23
31.12
Kimi 标志
Kimi K3 (low)
1M
开放
30
$1.87
89
0.79
28.93
22.52
DeepSeek 标志
DeepSeek V4 Pro (high)
1M
开放
30*
--
144
0.58
17.87
13.82
Kimi 标志
Kimi K2.7 Code
262k
开放
26
$0.76
219
0.48
12.97
10.20
Thinking Machines 标志
Inkling Small
262k
开放
26
$0.12
323
0.51
8.24
6.18
Thinking Machines 标志
Inkling
262k
开放
26
$0.72
209
0.64
12.63
9.59
Kimi 标志
Kimi K2.6 (Non-reasoning)
262k
开放
24*
--
--
--
--
--
Z AI 标志
GLM-5.2 (Non-reasoning) (FAST)
524k
开放
22*
--
248
1.60
3.61
--
Z AI 标志
GLM-5.2 (Non-reasoning)
1.05M
开放
22*
--
119
1.60
5.78
--
Z AI 标志
GLM-4.7
200k
开放
22*
--
225
0.66
11.75
8.87
DeepSeek 标志
DeepSeek V4 Pro (Non-reasoning)
1M
开放
21*
--
137
0.62
4.27
--
Z AI 标志
GLM-4.7 (Non-reasoning)
200k
开放
17*
--
221
0.71
2.97
--
OpenAI 标志
gpt-oss-120b (high)
128k
开放
12
$0.07
285
0.25
9.02
7.02
OpenAI 标志
gpt-oss-120b (low)
128k
开放
10*
--
296
0.23
8.68
6.76

关键定义

常见问题

关于 Baseten 的常见问题