跳转到内容
Alpha
  • 模型
  • 排行榜
  • Ori
联系销售

页脚

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

产品

  • 聊天
  • 排行榜
  • 基准测试
  • 应用
  • 发现
  • 模型
  • Ori
  • 合集
  • 提供商
  • 工具
  • 定价
  • Business
  • Enterprise
  • 实验室

公司

  • 关于
  • 博客
  • 客户
  • 招聘
    招聘
  • 隐私
  • 服务条款
  • 信任中心
  • 支持
  • 兼容 OR
  • 数据
  • 品牌

开发者

  • 文档
  • API 参考
  • 开发者平台
  • 状态
  • AI 站点地图

连接

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube

The free Inkling Small endpoint is only available for use with agentic harnesses. Do not upload any confidential information or personal data (e.g., voices and images of people's faces). Your usage of this free endpoint, including prompts and outputs, is logged and used to improve Thinking Machines Lab's models, products, and services. The logged session data will be disassociated from your account and other persistent identifiers before being used for these purposes.

By using this free endpoint, you agree to the TML Free Research API Terms of ServiceOpens in new tab. For more information about Thinking Machines Lab's data processing practices, see this Privacy NoticeOpens in new tab.

thinkingmachines 的网站图标

Thinking Machines: Inkling Small (free)

将于 2026年11月4日 下线

thinkingmachines/inkling-small:free

模型权重
比较

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.

模态
价格
免费
上下文
1.0M
发布时间
2026年7月30日
比较
提供商性能正常运行时间基准测试应用活动常见问题探索

提供商

此模型由一家提供商托管。OpenRouter 将每个请求直接转发给该提供商，无需做出路由决策。

性能

吞吐量是模型生成内容的速度（每秒 token 数，越高越好）。延迟是完整的往返时间（越低越好）。TTFT 是首个 token 的响应时间，即您看到内容出现前需要等待的时间（越低越好）。

正常运行时间

正常运行时间是指过去 3 天中至少有一家提供商响应请求的时间百分比。可用性是指成功提供推理服务的时间百分比。OpenRouter 会持续监控，并在某家提供商返回错误时使用次优提供商。

基准测试

标准化评测得分，以及此模型针对共用基准测试提示词的实际输出。百分比越高越好，每项排名显示此模型在该来源所评测的模型中的位置。

基准测试得分摘要： Thinking Machines: Inkling Small (free) （Artificial Analysis 和 Vals AI）
来源基准测试得分
Artificial AnalysisInkling Small Intelligence Index12.9
Artificial AnalysisInkling Small Coding Index52.9
Artificial AnalysisInkling Small Agentic Index23.5
Artificial AnalysisInkling Small GPQA Diamond89.5%
Artificial AnalysisInkling Small HLE33.3%
Artificial AnalysisInkling Small AA-LCR75.7%
Artificial AnalysisInkling Small τ-Bench Banking18.8%
Artificial AnalysisInkling Small GDPval-AA31.6%
Artificial AnalysisInkling Small CritPt8.3%
Artificial AnalysisInkling Small SciCode49.7%
Artificial AnalysisInkling Small Terminal-Bench 4.01.0%
Artificial AnalysisInkling Small Terminal-Bench 2.155.1%
Artificial AnalysisInkling Small AA-Omniscience Accuracy31.8%
Artificial AnalysisInkling Small AA-Omniscience Non-Hallucination Rate39.5%
Vals AIInkling Small Code Migration v1.110.4%
Vals AIInkling Small CorpFin v269.6%
Vals AIInkling Small CyberBench v1.164.1%
Vals AIInkling Small EMB v1.140.8%
Vals AIInkling Small Finance Agent v2.144.8%
Vals AIInkling Small Vals Finance Index36.3%
Vals AIInkling Small GPQA Diamond83.6%
Vals AIInkling Small HLAB-Vals-1.12.9%
Vals AIInkling Small IOI9.3%
Vals AIInkling Small LiveCodeBench85.9%
Vals AIInkling Small LegalBench83.0%
Vals AIInkling Small Vals Legal Index57.8%
Vals AIInkling Small Legal Research Bench25.5%
Vals AIInkling Small MedCode37.9%
Vals AIInkling Small MedScribe84.1%
Vals AIInkling Small MMLU Pro85.6%
Vals AIInkling Small MortgageTax62.3%
Vals AIInkling Small ProgramBench0.5%
Vals AIInkling Small ProofBench v1.16.0%
Vals AIInkling Small Public Benefits Bench v1.159.4%
Vals AIInkling Small SAGE v132.7%
Vals AIInkling Small SkillsBench33.6%
Vals AIInkling Small SWE-bench82.2%
Vals AIInkling Small Tax Agent Bench15.4%
Vals AIInkling Small TaxEval v275.5%
Vals AIInkling Small Terminal-Bench 4.00.0%
Vals AIInkling Small Vals Index27.6%
Vals AIInkling Small Vals Multimodal Index50.1%
Vals AIInkling Small Vibe Code Bench v1.119.1%

应用

向此模型发送最多流量的公开应用。这能很好地反映实际生产工作负载的情况，也能提示此模型最适合哪些用例。

活动

此模型的 token 用量和请求流量随时间的变化。

API

可直接用于调用此模型的代码。OpenRouter 的 API 与 OpenAI 兼容——大多数 SDK 只需替换基础 URL 即可使用。切换模型时，唯一需要更改的是下方的模型标识符。

目前无法通过 EU 区域内路由使用。 区域内路由文档

探索更多模型

OpenRouter 上的免费 AI 模型集合具备视觉能力的 AI 模型：用于图像理解的多模态大语言模型集合AI 模型排行榜排名
延迟 / 吞吐量
免费免费1.42s83 tps
99.86%
吞吐量
83token/秒

P50，所有提供商中最佳

延迟
1.42秒

P50，最佳提供商

AutoExacto 基准测试
GPQA DiamondTAU-BenchDeepInfra86.0%57.3%
正常运行时间（3 天）模型可访问。请求已路由至提供商。
100.00%
可用性（3 天）模型通过任意提供商返回了推理结果。错误和空响应均计为失败。
98.60%

过去 3 天的可用性

最近 72 小时
可用性 98.60%
3 天前2 天前昨天现在

过去 24 小时的可用性

OpenRouter Availability
99.25%

当上游提供商发生错误时，如果您的请求筛选条件允许，我们可以通过路由到另一家健康的提供商来恢复服务。您可以通过以下接口以编程方式访问各提供商的正常运行时间数据： 端点 API。了解更多有关我们的 负载均衡和提供商路由选项。

1.
https://nousresearch.com 的网站图标
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
148Btoken
2.
https://pi.dev/ 的网站图标
pi
There are many coding agents, but this one is yours.
31Btoken
3.
https://github.com/deepseek-ai/deepseek-harness 的网站图标
DeepSeek Harness
新增
30.6Btoken
4.
https://claude.ai/apple-touch-icon.png 的网站图标
Claude Code
Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.
27.6Btoken
5.
https://openclaw.ai/ 的网站图标
OpenClaw
OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.
22.3Btoken

常见问题

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.

是的。此页面显示的 Inkling Small (free) 定价为零，因此您无需为 提示或补全 token 付费。免费端点受速率限制约束，请参阅速率限制文档。

Inkling Small (free) 的上下文窗口为 1,048,576 个 token。它最多支持 262,144 个补全 token。

是的。Inkling Small (free) 支持通过 tools 进行函数调用。 它不支持 response_format，因此不会强制输出 JSON 格式。

Inkling Small (free) 接受 文本、图像和音频 作为输入，并返回 文本。

Inkling 是 Thinking Machines 推出的另一款 文本 模型。

Inkling Small (free) 于 2026年7月30日 发布。

更多模型，来自 thinkingmachines

Inkling Small

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.

文本524K 上下文US$0.45 / US$1.20
Inkling Small (free)

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.

文本1.0M 上下文Free
Inkling

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.

文本524K 上下文US$1 / US$4.05
Inkling (free)

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.

文本1.0M 上下文Free