Model details

DeepSeek R1 Distill Qwen 14B

DeepSeek · deepseek-r1-distill-qwen-14b

DeepSeek R1 Distill Qwen 14B is a large language model distilled based on Qwen 2.5 14B using the outputs of DeepSeek R1. Benchmark results include: AIME 2024 pass@1 of 69.7, MATH-500 pass@1 of 93.9, and a CodeForces Rating of 1481. Fine-tuned using the outputs of DeepSeek R1, this model possesses competitiveness comparable to larger frontier models.

能读 33K能调工具会深度思考
Official price¥0.9629/ ¥2.882每百万 Token
中转最低94% of official¥0.9000 / ¥2.700
3家在卖

The best way to buy DeepSeek R1 Distill Qwen 14B

The best deal for each of three ways to buy. Tap a card to see every option of that kind.

Pay-as-you-go API · relay stationsFor coding and tools like Cursor and Claude Code
For using the web app and mobile app, no coding
Official subscriptionsFor a genuine official plan in your own name
Choose models/DeepSeek R1 Distill Qwen 14B

DeepSeek R1 Distill Qwen 14B

DeepSeek R1 Distill Qwen 14B is a large language model distilled based on Qwen 2.5 14B using the outputs of DeepSeek R1. Benchmark results include: AIME 2024 pass@1 of 69.7, MATH-500 pass@1 of 93.9, and a CodeForces Rating of 1481. Fine-tuned using the outputs of DeepSeek R1, this model possesses competitiveness comparable to larger frontier models.

View intro source
Official price · Input¥0.9629
Official price · Output¥2.882
Sellers3 家

The best way to buy DeepSeek R1 Distill Qwen 14B

The best deal for each of three ways to buy. Tap a card to see every option of that kind.

Pay-as-you-go API · relay stationsFor coding and tools like Cursor and Claude Code
For using the web app and mobile app, no coding
Official subscriptionsFor a genuine official plan in your own name
No reviews yet — write the first oneSee reviews ↓

模型介绍

DeepSeek R1 Distill Qwen 14B is a large language model distilled based on Qwen 2.5 14B using the outputs of DeepSeek R1. Benchmark results include: AIME 2024 pass@1 of 69.7, MATH-500 pass@1 of 93.9, and a CodeForces Rating of 1481. Fine-tuned using the outputs of DeepSeek R1, this model possesses competitiveness comparable to larger frontier models.

模型基础信息

厂商
DeepSeek
模型类型
文本与多模态
一次能读多少
33K Token一次对话能塞进去的最大内容量，长文档、长代码要看这项
一次能写多少
16,384 Token单次回答的长度上限
能接收什么
文本可以发给它的内容类型
能产出什么
文本它能生成的内容类型
能调工具吗
可以能不能自动调用外部函数、查资料、执行动作
怎么计费
按 Token 计费官方按什么单位收钱
现在还能用吗
可以用
这些资料是哪个地区的资料适用地区
中国大陆厂商专门为中国大陆公布的资料。
它会做什么擅长推理回答风格可调会写字会调工具

官方价格

折扣与价格评分按中国大陆的官方价计算

计价项适用范围官方价格
输入中国大陆0.9629 CNY每百万 Token
输出中国大陆2.882 CNY每百万 Token
它还叫这些名字（14 条）
DeepSeek-R1-DISTILL-QWEN-14Bdeepseek-r1-distill-qwen-14b-highdeepseek-r1-distill-qwen-14b-lowdeepseek-r1-distill-qwen-14b-mediumdeepseek-r1-distill-qwen-14b-minimaldeepseek-r1-distill-qwen-14b-non-thinkingdeepseek-r1-distill-qwen-14b-nothinkingdeepseek-r1-distill-qwen-14b-thinkingdeepseek-r1-distill-qwen-14b-thinking-highdeepseek-r1-distill-qwen-14b-thinking-lowdeepseek-r1-distill-qwen-14b-thinking-mediumdeepseek-r1-distill-qwen-14b-thinking-minimaldeepseek-r1-distill-qwen-14b-thinking-xhighdeepseek-r1-distill-qwen-14b-xhigh

不同地方写法可能不一样，列在这里方便你对上号。名字太模糊、认不准的不会公开。

User reviews

No reviews yet. If you have used it, share the first honest review and help others avoid pitfalls.

Review this model

Rating
Optional
编辑器加载中…