thinkingmachines logo
thinkingmachines

Thinking Machines: Inkling Small (batch)

来源介绍(英文)

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...

模型概览

模型规格

上下文
524,288 tokens
最大输出
262,144 tokens
架构
text+image+audio->text
分词器
Other
知识截止时间
暂未提供
内容审核
否
OPENROUTER

完整价格

同步自 OpenRouter。Token 价格均按每百万 Token 展示。

输入
$0.36
每百万 Token
输出
$0.96
每百万 Token
缓存读取
$0.08
每百万 Token
API

模型配置

推理能力

是否必须推理
否
默认参数
high
能力与模态
max, high, medium, low, minimal, none
API

快速调用

在本地设置 OPENROUTER_API_KEY。Python 需安装 requests;JavaScript 在 Node.js 中运行。密钥应保存在服务端。

此请求使用基础模型 ID 提交异步批处理。返回任务 ID 表示已提交,不表示已完成。

API 文档

curl --fail-with-body https://openrouter.ai/api/beta/batches \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"endpoint":"/v1/chat/completions","model":"thinkingmachines/inkling-small","requests":[{"custom_id":"request-1","body":{"messages":[{"role":"user","content":"Hello!"}]}}]}'

# Replace JOB_ID with the returned id to check progress.
curl --fail-with-body "https://openrouter.ai/api/beta/batches/JOB_ID" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY"
能力与模态

输入 → 输出

输入
textimageaudio
输出
text
推理能力

是 · max · high · medium · low · minimal · none

API

支持的 API 参数

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyseedstoptemperaturetool_choicetoolstop_ktop_p
可用提供方

1 提供方

核验日期: 2026年11月7日

在 OpenRouter 查看实时 Provider

Provider 可用性、延迟、吞吐量和路由会持续变化,请前往来源页面查看实时运行数据。

OpenRouter

DeepInfra

fp8
上下文
524K
最大输出
262K
输入
$0.36
输出
$0.96
缓存读取
$0.08
缓存写入
暂未提供
thinkingmachines

4 个模型

全部模型
thinkingmachines logothinkingmachines

Thinking Machines: Inkling 2 Small

Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second...

上下文
1.0M
输入
text · image
输出
text
输入: $0.3输出: $1每百万 Token
查看模型详情 →
thinkingmachines logothinkingmachines

Thinking Machines: Inkling 2 Small (free)

Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second...

上下文
1.0M
输入
text · image
输出
text
输入: 免费输出: 免费每百万 Token
查看模型详情 →
thinkingmachines logothinkingmachines

Thinking Machines: 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...

上下文
524K
输入
text · image · audio
输出
text
输入: $0.45输出: $1.2每百万 Token
查看模型详情 →
thinkingmachines logothinkingmachines

Thinking Machines: 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,...

上下文
524K
输入
text · image · audio
输出
text
输入: $1输出: $4.05每百万 Token
查看模型详情 →