D

Modelos DeepSeek no UnoRouter

22 modelos

Explore todos os modelos DeepSeek disponíveis no UnoRouter: preços, contexto e recursos.

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...

RaciocínioFerramentasVisãoCache
1M$0.09tokens de entrada$0.3070% de desconto$0.36tokens de saída$1.2070% de desconto
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...

RaciocínioFerramentasVisãoCache
1M$0.04tokens de entrada$0.2082% de desconto$0.12tokens de saída$0.6682% de desconto
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.

RaciocínioFerramentasCache
1M$0.16tokens de entrada$1.3288% de desconto$0.48tokens de saída$3.9688% de desconto
DDeepSeek
Descontinuado
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...

RaciocínioFerramentasVisãoCache
1M$0.06tokens de entrada$0.1457% de desconto$0.12tokens de saída$0.2857% de desconto
DDeepSeek
Descontinuado
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...

RaciocínioFerramentasCache
1M$0.17tokens de entrada$1.7490% de desconto$0.34tokens de saída$3.4890% de desconto
DDeepSeek
Descontinuado
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...

RaciocínioFerramentasVisãoCache
1M$0.05tokens de entrada$0.1462% de desconto$0.11tokens de saída$0.2862% de desconto
DDeepSeek
grátisDescontinuado
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...

RaciocínioFerramentasVisãoCache
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,...

RaciocínioFerramentas
163.8K$0.54tokens de entrada$2.00tokens de saída
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...

RaciocínioFerramentas
163.8K$0.06tokens de entrada$0.2578% de desconto$0.21tokens de saída$0.9578% de desconto
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...

RaciocínioFerramentasCache
128K$0.50tokens de entrada$1.87tokens de saída

Ocupados no momento

Todos os provedores desses modelos atingiram o limite de requisições. Eles voltam automaticamente assim que os limites são liberados.

DDeepSeek
Ocupadográtis
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...

RaciocínioFerramentasVisãoCache
1M
DDeepSeek
Ocupadográtis
deepseek-flash:free

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

RaciocínioFerramentasVisãoCache
1M
DDeepSeek
Ocupadográtis
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...

RaciocínioFerramentasVisãoCache
1.0M
DDeepSeek
Ocupadográtis
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...

RaciocínioFerramentasVisãoCache
1M
DDeepSeek
Ocupadográtis
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...

RaciocínioFerramentasCache
1M
DDeepSeek
OcupadográtisDescontinuado
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...

RaciocínioFerramentasVisãoCache
1M
DDeepSeek
OcupadográtisDescontinuado
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...

RaciocínioFerramentasCache
1M
DDeepSeek
OcupadográtisDescontinuado
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...

RaciocínioFerramentasCache
1M
DDeepSeek
Ocupadográtis
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...

RaciocínioFerramentas
163.8K
DDeepSeek
Ocupadográtis
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...

Raciocínio
131.1K
DDeepSeek
Ocupadográtis
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...

Raciocínio
80K
DDeepSeek
OcupadográtisDescontinuado
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...

FerramentasCache
131.1K

Comparações populares