此模型已弃用。我们仅继续对默认的 10k 输入 token 工作负载进行性能测试。其他工作负载的结果为历史数据，不再更新。

Sarvam 已推出更新版本 Sarvam 30B。我们建议考虑使用该版本。

Sarvam

•

Open weights model

•

Released 2025年5月

Sarvam M (Reasoning, Based on Mistral Small 3.1) API 服务商基准测试与分析

模型比较

本分析旨在帮助你根据使用场景，选择 Sarvam M (Reasoning, Based on Mistral Small 3.1) 的最佳 API 服务商。

速度最快

输出速度

共 1 家服务商

延迟最低

首个答案 Token 延迟

共 1 家服务商

价格最低

Sarvam

$0.00

每 100 万 token 的混合价格

共 1 家服务商

可通过 Sarvam 使用 Sarvam M。

该模型暂无服务商基准测试数据。

有关模型详情及其与其他模型的智能比较，请参阅 Sarvam M (Reasoning, Based on Mistral Small 3.1) 的模型页面。

速度

Output tokens per second · Higher is better

No data available

延迟

Seconds to first answer token received · Lower is better

No data available

价格

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

价格

价格：缓存命中、输入和输出: Sarvam M (Reasoning, Based on Mistral Small 3.1)

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

每项 Intelligence Index 任务的成本: Sarvam M (Reasoning, Based on Mistral Small 3.1)

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

No data available

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

输出速度与价格: Sarvam M (Reasoning, Based on Mistral Small 3.1)

Blended at 7:2:1 (cache-input-output) · Output speed: output tokens per second · USD per 1M tokens (blended)

Most attractive quadrant

No data available

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).

速度

按输出速度（每秒 token 数）衡量

输出速度: Sarvam M (Reasoning, Based on Mistral Small 3.1)

输出速度：每秒输出 token 数 · 10,000 input tokens

No data available

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 or the median across providers where a first-party API is not available.

Intelligence Index 每项任务耗时: Sarvam M (Reasoning, Based on Mistral Small 3.1)

Weighted average decode time (minutes) per Intelligence Index task · Excludes TTFT and overhead time · Lower is better

No data available

The weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.

每任务成本与每任务耗时: Sarvam M (Reasoning, Based on Mistral Small 3.1)

Weighted average cost (USD) per Intelligence Index task · Weighted average decode time (minutes) per Intelligence Index task

Most attractive quadrant

No data available

延迟

按首 Token 延迟（秒）衡量

首个答案 Token 延迟: Sarvam M (Reasoning, Based on Mistral Small 3.1)

Seconds to first token received · Lower is better · 10,000 input tokens

No data available

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.

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.

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

端到端响应时间: Sarvam M (Reasoning, Based on Mistral Small 3.1)

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · 10,000 input tokens

No data available

Seconds to receive a 500 token response. Key components:

Input time: Time to receive the first response token
Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
Answer time: Time to generate 500 output tokens, based on output speed

关键比较指标与 API 功能



Sarvam	8.19k			开放	--	--	--	--	--

常见问题

关于 Sarvam M (Reasoning, Based on Mistral Small 3.1) 服务商的常见问题

可通过 1 家 API 服务商使用 Sarvam M (Reasoning, Based on Mistral Small 3.1)：Sarvam。每家服务商的性能特征和价格各不相同。

目前可通过我们进行基准测试和跟踪的 1 家 API 服务商使用 Sarvam M (Reasoning, Based on Mistral Small 3.1)。

按混合价格计算，Sarvam M (Reasoning, Based on Mistral Small 3.1) 最实惠的服务商是 Sarvam（每 100 万 token $0.00）。混合价格采用缓存命中/输入/输出 token 为 7:2:1 的比例。

Sarvam M (Reasoning, Based on Mistral Small 3.1) 输入 token 价格最低的服务商是 Sarvam（每 100 万输入 token $0.00）。

Sarvam M (Reasoning, Based on Mistral Small 3.1) 输出 token 价格最低的服务商是 Sarvam（每 100 万输出 token $0.00）。

提供 Sarvam M (Reasoning, Based on Mistral Small 3.1) 的全部 1 家服务商均支持用于结构化输出的 JSON 模式。

选择 Sarvam M (Reasoning, Based on Mistral Small 3.1) 服务商时，请考虑：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 JSON 模式或函数调用等 API 功能。

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。

有关 Sarvam M (Reasoning, Based on Mistral Small 3.1) 的智能、能力、模态及其与其他模型的比较，请参阅模型概览页面。查看模型概览

Sarvam M (Reasoning, Based on Mistral Small 3.1) API 服务商基准测试与分析

速度最快

延迟最低

价格最低

速度

延迟

价格

价格

价格：缓存命中、输入和输出: Sarvam M (Reasoning, Based on Mistral Small 3.1)

Cache Hit

每项 Intelligence Index 任务的成本: Sarvam M (Reasoning, Based on Mistral Small 3.1)

Cost per Intelligence Index Task

输出速度与价格: Sarvam M (Reasoning, Based on Mistral Small 3.1)

Output Speed

速度

输出速度: Sarvam M (Reasoning, Based on Mistral Small 3.1)

Output Speed

Model Performance Representation

Intelligence Index 每项任务耗时: Sarvam M (Reasoning, Based on Mistral Small 3.1)

Time per Intelligence Index Task

每任务成本与每任务耗时: Sarvam M (Reasoning, Based on Mistral Small 3.1)

Cost per Intelligence Index Task

延迟

首个答案 Token 延迟: Sarvam M (Reasoning, Based on Mistral Small 3.1)

Time to First Answer Token

Median

端到端响应时间

端到端响应时间: Sarvam M (Reasoning, Based on Mistral Small 3.1)

End-to-End Response Time

关键比较指标与 API 功能

常见问题

可以在哪里使用 Sarvam M (Reasoning, Based on Mistral Small 3.1)？

有多少家 API 服务商提供 Sarvam M (Reasoning, Based on Mistral Small 3.1)？

哪家服务商提供的 Sarvam M (Reasoning, Based on Mistral Small 3.1) 最便宜？

哪家服务商提供的 Sarvam M (Reasoning, Based on Mistral Small 3.1) 输入价格最低？

哪家服务商提供的 Sarvam M (Reasoning, Based on Mistral Small 3.1) 输出价格最低？

哪些 Sarvam M (Reasoning, Based on Mistral Small 3.1) 服务商支持 JSON 模式？

如何选择 Sarvam M (Reasoning, Based on Mistral Small 3.1) 服务商？

Sarvam M (Reasoning, Based on Mistral Small 3.1) 的服务商性能会随时间变化吗？

Sarvam M (Reasoning, Based on Mistral Small 3.1) 的整体能力如何？