Replicate：模型智能、性能与价格

Replicate

分析 Replicate 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 Replicate 提供的最佳模型。

最智能

Granite 4.0 H Small

Granite 3.3 8B

Intelligence Index

共 2 个模型

速度最快

Granite 4.0 H Small

46 t/s

Granite 3.3 8B

15 t/s

输出速度

共 2 个模型

价格最低

Granite 3.3 8B

$0.05

Granite 4.0 H Small

$0.08

每 100 万 token 的混合价格

共 2 个模型

Replicate 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，Replicate 上表现最好的模型是 Granite 4.0 H Small（5）和Granite 3.3 8B（2）。
输出速度方面，最快的模型是 Granite 4.0 H Small（46 t/s）和Granite 3.3 8B（15 t/s）。
延迟方面，Granite 4.0 H Small（10.49 秒）和Granite 3.3 8B（26.82 秒）的首个答案 Token 延迟最低。
价格方面，Granite 3.3 8B（$0.05）和Granite 4.0 H Small（$0.08）每 100 万 token 的混合价格最低。
上下文窗口方面，Granite 4.0 H Small（128k）和Granite 3.3 8B（128k）支持 Replicate 上最大的上下文窗口。
Granite 4.0 H Small 在智能与速度之间取得了最佳平衡。若要优化成本，Granite 3.3 8B 的价格最具竞争力。

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

Estimate (independent evaluation forthcoming)

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

No data available

𝜏³-Banking

Agentic tool use

No data available

Terminal-Bench v2.1

Agentic coding & terminal use

No data available

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

No data available

AutomationBench-AA

Agentic SaaS workflows

No data available

Harvey LAB-AA

Legal agentic work, criterion pass rate

No data available

EnterpriseOps-Gym-AANew

Agentic business operations

No data available

IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

No data available

ITBench-AA

Kubernetes incident root-cause analysis

No data available

MMMU-Pro

Visual reasoning

No data available

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.

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

Pareto line

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 Token

Seconds to first token received · Lower is better

Reasoning models are indicated by a lightbulb icon

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

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).

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

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
DeepSeek V3 0324	128k	开放	15	$0.24	--	--	--	--	模型服务商
Granite 4.0 H Small	128k	开放	5*	--	46	10.49	21.45	--	模型服务商
Llama 2 Chat 7B	4.1k	开放	4*	--	--	--	--	--	模型服务商
Llama 3 70B	8.19k	开放	3*	--	--	--	--	--	模型服务商
Granite 3.3 8B	128k	开放	2*	--	15	26.82	59.29	--	模型服务商
Llama 3 8B	8.19k	开放	1*	--	--	--	--	--	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 Replicate 的常见问题

Replicate 提供我们跟踪的 2 个模型：Granite 4.0 H Small和Granite 3.3 8B。

Replicate 上最智能的模型是 Granite 4.0 H Small，Intelligence Index 得分为 5。

按输出速度计算，Replicate 上最快的模型是 Granite 4.0 H Small，速度为每秒 45.6 个 token。

Replicate 上首个答案 Token 延迟最低的模型是 Granite 4.0 H Small，延迟为 10.49 秒。延迟越低，初始响应越快。

按混合价格计算，Replicate 上最实惠的模型是 Granite 3.3 8B，每 100 万 token 的价格为 $0.05（缓存命中/输入/输出比例为 7:2:1）。

Replicate 上各模型价格最多相差 2 倍，从最实惠的 Granite 3.3 8B（每 100 万 token $0.05）到最昂贵的 Granite 4.0 H Small（每 100 万 token $0.08）。

是，Replicate 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，Replicate 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 Replicate 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。

Replicate：模型智能、性能与价格

最智能

速度最快

价格最低

智能

速度

价格

智能评测

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Intelligence Index vs. Price

Price-Quality Variance

上下文窗口

Context Window

Context Window for RAG

Context Window

价格

Intelligence Index vs. Price

Price-Quality Variance

性能摘要

Output Speed vs. Price

Output Speed

Price

速度

Output Speed

Output Speed

Model Performance Representation

延迟

Latency: Time To First Token

Latency (Time to First Token)

Model Performance Representation

端到端响应时间

End-to-End Response Time vs. Price

Price

关键定义

Context Window

常见问题

Replicate 提供哪些模型？

Replicate 上最智能的模型是什么？

Replicate 上速度最快的模型是什么？

Replicate 上哪个模型的延迟最低？

Replicate 上最便宜的模型是什么？

Replicate 上各模型之间的价格差异有多大？

Replicate 是否兼容 OpenAI？

Replicate 是否提供开放权重模型？

Replicate 的性能会随时间变化吗？

如何选择 Replicate 上的模型？