Thinking Machines：模型智能、性能与价格

Thinking Machines
Thinking Machines

分析 Thinking Machines 各模型的关键指标，包括质量、价格、输出速度、延迟、上下文窗口等。 本分析旨在帮助你根据使用场景，选择 Thinking Machines 提供的最佳模型。

最智能

#1
Inkling
Inkling
41
#2
Inkling Small
Inkling Small
40

Intelligence Index

共 2 个模型

速度最快

#1
Inkling Small
Inkling Small
137 t/s
#2
Inkling
Inkling
80 t/s

输出速度

共 2 个模型

价格最低

#1
Inkling Small
Inkling Small
$0.22
#2
Inkling
Inkling
$0.72

每 100 万 token 的混合价格

共 2 个模型

表示推理模型

Thinking Machines 提供 2 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，Thinking Machines 上表现最好的模型是 Inkling（41）和Inkling Small（40）。
  • 输出速度方面，最快的模型是 Inkling Small（137 t/s）和Inkling（80 t/s）。
  • 延迟方面，Inkling Small（16.22 秒）和Inkling（26.71 秒） 的首个答案 Token 延迟最低。
  • 价格方面，Inkling Small（$0.22）和Inkling（$0.72） 每 100 万 token 的混合价格最低。
  • 上下文窗口方面，Inkling（262k）和Inkling Small（256k） 支持 Thinking Machines 上最大的上下文窗口。
  • Inkling Small 同时拥有最快输出和最佳价格，对吞吐量敏感且注重成本的应用很有吸引力。对于要求最高质量的任务，Inkling 在智能方面领先。

亮点

智能

Artificial Analysis Intelligence Index · Higher is better

速度

Output tokens per second · Higher is better

价格

USD per 1M tokens (blended) · Lower is better

智能评测

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
GDPval-AA v2

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

𝜏³-Banking

Agentic tool use

Terminal-Bench v2.1

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR

Long context reasoning

AA-Briefcase

Agentic knowledge work, Elo

AutomationBench-AA

Agentic SaaS workflows

Harvey LAB-AA

Legal agentic work, criterion pass rate

No data available
EnterpriseOps-Gym-AANew

Agentic business operations

IFBench

Instruction following

No data available
APEX-Agents-AA

Long-horizon agentic tasks

No data available
ITBench-AA

Kubernetes incident root-cause analysis

No data available
MMMU-Pro

Visual reasoning

Reasoning models are indicated by a lightbulb icon

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line
Reasoning models are indicated by a lightbulb icon

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

上下文窗口

Context Window

Context window: tokens limit · Higher is better
Reasoning models are indicated by a lightbulb icon

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

价格

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line
Reasoning models are indicated by a lightbulb icon

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

性能摘要

Output Speed vs. Price

Output speed: output tokens per second · USD per 1M tokens (blended)
Most attractive quadrant
Reasoning models are indicated by a lightbulb icon

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

速度

按输出速度（每秒 token 数）衡量

Output Speed

Output tokens per second · Higher is better
Reasoning models are indicated by a lightbulb icon

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

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
Reasoning models are indicated by a lightbulb icon

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

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
Reasoning models are indicated by a lightbulb icon

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

进一步分析
Thinking Machines 标志
Inkling
262k
开放
41
--
80
1.84
32.93
24.87
模型
服务商
Thinking Machines 标志
Inkling Small
256k
开放
40
$0.07
137
1.58
19.88
14.64
模型
服务商

关键定义

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

常见问题

关于 Thinking Machines 的常见问题

Thinking Machines 提供我们跟踪的 2 个模型：Inkling和Inkling Small。

Thinking Machines 上最智能的模型是 Inkling，Intelligence Index 得分为 41。

按输出速度计算，Thinking Machines 上最快的模型是 Inkling Small，速度为每秒 136.6 个 token。

Thinking Machines 上首个答案 Token 延迟最低的模型是 Inkling Small，延迟为 16.22 秒。延迟越低，初始响应越快。

按混合价格计算，Thinking Machines 上最实惠的模型是 Inkling Small，每 100 万 token 的价格为 $0.22（缓存命中/输入/输出比例为 7:2:1）。

Thinking Machines 上各模型价格最多相差 3 倍，从最实惠的 Inkling Small（每 100 万 token $0.22）到最昂贵的 Inkling（每 100 万 token $0.72）。

是，Thinking Machines 提供兼容 OpenAI 的 API，可以轻松从 OpenAI 切换，或继续使用现有的 OpenAI SDK 集成。

是，Thinking Machines 上全部 2 个模型均支持用于结构化输出的 JSON 模式。

是，Thinking Machines 上全部 2 个模型均支持函数调用（工具使用）。

是，Thinking Machines 提供 2 个推理模型：Inkling和Inkling Small。推理模型会先进行扩展思考来解决复杂问题，再给出答案。

是，Thinking Machines 上全部 2 个模型均为开放权重模型。

会。服务商性能可能因基础设施变化、负载均衡和更新而随时间波动。我们持续对所有服务商进行基准测试，并在“随时间变化”图表中展示历史性能趋势。

选择 Thinking Machines 上的模型时，请考虑：智能（适合质量敏感型任务）、输出速度（适合吞吐量密集型任务）、延迟（适合需要快速首次响应的交互式应用）、价格（适合成本敏感型工作负载），以及上下文窗口大小、JSON 模式或函数调用支持等功能。