D

UnoRouter 上的 DeepSeek 模型

22 個模型

瀏覽 UnoRouter 上所有可用的 DeepSeek 模型:價格、上下文和功能。

DDeepSeek
deepseek-v4.1-flash-1017

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model from...

推理工具視覺快取
100萬$0.09輸入 Token$0.3070% 優惠$0.36輸出 Token$1.2070% 優惠
DDeepSeek
deepseek-v4.1-flash

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

推理工具視覺快取
100萬$0.04輸入 Token$0.2082% 優惠$0.12輸出 Token$0.6682% 優惠
DDeepSeek
免費
deepseek-v4.1-flash:free

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

推理工具視覺快取
100萬
DDeepSeek
deepseek-v4-pro-0813

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

推理工具快取
100萬$0.16輸入 Token$1.3288% 優惠$0.48輸出 Token$3.9688% 優惠
DDeepSeek
已棄用
deepseek-v4-flash-0731

DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities. It has the same model structure as...

推理工具視覺快取
100萬$0.06輸入 Token$0.1457% 優惠$0.12輸出 Token$0.2857% 優惠
DDeepSeek
已棄用
deepseek-v4-pro

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced...

推理工具快取
100萬$0.17輸入 Token$1.7490% 優惠$0.34輸出 Token$3.4890% 優惠
DDeepSeek
已棄用
deepseek-v4-flash

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for...

推理工具視覺快取
100萬$0.05輸入 Token$0.1462% 優惠$0.11輸出 Token$0.2862% 優惠
DDeepSeek
deepseek-v3.1-terminus

DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities,...

推理工具
16.4萬$0.54輸入 Token$2.00輸出 Token
DDeepSeek
deepseek-v3.1

A hybrid-inference flagship MoE model (671B total, 37B active). It bridges the gap between speed and logic by supporting both Thinking and Non-Thinking modes in a single model, featuring enhanced...

推理工具
16.4萬$0.01輸入 Token$0.2595% 優惠$0.05輸出 Token$0.9595% 優惠
DDeepSeek
deepseek-v3-0324

A state-of-the-art 671B MoE model (37B active) featuring Multi-head Latent Attention (MLA) and auxiliary-loss-free load balancing. It provides a hybrid "Think/Non-think" mode, delivering SOTA...

推理工具快取
12.8萬$0.50輸入 Token$1.87輸出 Token

目前繁忙

這些模型的所有供應商都已達到請求上限。限制解除後會自動恢復。

DDeepSeek
繁忙免費
deepseek-v4.1-flash-1017:free

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

推理工具視覺快取
100萬
DDeepSeek
繁忙免費
deepseek-flash:free

This model always redirects to the latest model in the DeepSeek Flash family.

推理工具視覺快取
100萬
DDeepSeek
繁忙免費
deepseek-v4.1-flash-uncensored-fp8:free

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

推理工具視覺快取
104.9萬
DDeepSeek
繁忙免費
deepseek-v4-pro-0813:free

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced...

推理工具快取
100萬
DDeepSeek
繁忙免費已棄用
deepseek-v4-flash-0731:free

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for...

推理工具視覺快取
100萬
DDeepSeek
繁忙免費已棄用
deepseek-v4-pro-max:free

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced...

推理工具快取
100萬
DDeepSeek
繁忙免費已棄用
deepseek-v4-pro:free

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced...

推理工具快取
100萬
DDeepSeek
繁忙免費已棄用
deepseek-v4-flash:free

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for...

推理工具視覺快取
100萬
DDeepSeek
繁忙免費
deepseek-v3.1:free

A hybrid-inference flagship MoE model (671B total, 37B active). It bridges the gap between speed and logic by supporting both Thinking and Non-Thinking modes in a single model, featuring enhanced...

推理工具
16.4萬
DDeepSeek
繁忙免費
deepseek-r1-distill-llama-70b:free

DeepSeek R1 Distill Llama 70B is a distilled large language model based on Llama-3.3-70B-Instruct, using outputs from DeepSeek R1. The model combines advanced distillation techniques to achieve high...

推理
13.1萬
DDeepSeek
繁忙免費
deepseek-r1-distill-qwen-32b:free

DeepSeek R1 Distill Qwen 32B is a distilled large language model based on Qwen 2.5 32B, using outputs from DeepSeek R1. It outperforms OpenAI's o1-mini across various benchmarks, achieving new...

推理
8萬
DDeepSeek
繁忙免費已棄用
deepseek-chat:free

deepseek-chat is a dynamic model alias for DeepSeek's official API. As of January 2026, it points to the DeepSeek-V3.2 flagship. Utilizing a 671B total parameter MoE architecture with 37B active...

工具快取
13.1萬

熱門比較