D

Модели DeepSeek на UnoRouter

Моделей: 21

Все модели DeepSeek, доступные на UnoRouter: цены, контекст и возможности.

DDeepSeek
Новинка
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...

РассуждениеИнструментыКэш
1M$0.06входных токенов$0.30скидка 78%$0.26выходных токенов$1.20скидка 78%
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...

РассуждениеИнструментыКэш
1M$0.04входных токенов$0.19скидка 78%$0.21выходных токенов$0.96скидка 78%
DDeepSeek
бесплатно
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...

РассуждениеИнструментыКэш
1M
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.

РассуждениеИнструментыКэш
1M$0.14входных токенов$1.32скидка 89%$0.43выходных токенов$3.96скидка 89%
DDeepSeek
Устарело
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...

РассуждениеИнструментыЗрениеКэш
1M$0.07входных токенов$0.14скидка 49%$0.14выходных токенов$0.28скидка 49%
DDeepSeek
Устарело
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...

РассуждениеИнструментыКэш
1M$0.22входных токенов$1.74скидка 87%$0.44выходных токенов$3.48скидка 87%
DDeepSeek
Устарело
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...

РассуждениеИнструментыЗрениеКэш
1M$0.08входных токенов$0.14скидка 43%$0.16выходных токенов$0.28скидка 43%
DDeepSeek
бесплатноУстарело
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...

РассуждениеИнструментыЗрениеКэш
1M
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,...

РассуждениеИнструменты
163.8K$0.54входных токенов$2.00выходных токенов
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...

РассуждениеИнструменты
163.8K$0.03входных токенов$0.59скидка 95%$0.08выходных токенов$1.72скидка 95%
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...

РассуждениеИнструментыКэш
128K$0.50входных токенов$1.89выходных токенов
DDeepSeek
бесплатно
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...

Рассуждение
131.1K
DDeepSeek
бесплатно
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...

Рассуждение
80K
DDeepSeek
бесплатноУстарело
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...

ИнструментыКэш
131.1K

Сейчас перегружены

Все провайдеры этих моделей достигли лимита запросов. Они станут доступны автоматически, как только лимиты сбросятся.

DDeepSeek
ЗанятобесплатноНовинка
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...

РассуждениеИнструментыКэш
1M
DDeepSeek
Занятобесплатно
deepseek-flash:free

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

РассуждениеИнструментыЗрениеКэш
1M
DDeepSeek
Занятобесплатно
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...

РассуждениеИнструментыКэш
1M
DDeepSeek
ЗанятобесплатноУстарело
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...

РассуждениеИнструментыЗрениеКэш
1M
DDeepSeek
ЗанятобесплатноУстарело
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...

РассуждениеИнструментыКэш
1M
DDeepSeek
ЗанятобесплатноУстарело
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...

РассуждениеИнструментыКэш
1M
DDeepSeek
Занятобесплатно
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...

РассуждениеИнструменты
163.8K

Популярные сравнения