Loading...
Sobre
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
Modelos Relacionados
DeepSeek: DeepSeek V4 Pro2026-04-24DeepSeek V4 Pro (Reasoning, High Effort)2026-04-24DeepSeek: DeepSeek V4 Flash2026-04-24DeepSeek V4 Flash (Reasoning, High Effort)2026-04-24DeepSeek V4 Pro (Non-reasoning)2026-04-24DeepSeek V4 Flash (Non-reasoning)2026-04-24DeepSeek: DeepSeek V4 Flash (free)2026-04-24DeepSeek V3.2 (Reasoning)2025-12-01
Preços
Entrada
$0.21
por 1M tokens
Saída
$0.79
por 1M tokens
Combinado
$0.35
por 1M tokens
Mais barato que 59% dos modelos. Preço mediano é $0.54/1M tokens.
Calculadora de Custo
Tokens por dia1M
100K100M
Diário
$0.35
Mensal
$10.65
vs. Modelos Similares
Qwen: Qwen3.6 35B A3B
$0.350%
Qwen: Qwen3.5-35B-A3B
$0.35-0%
Qwen3 235B A22B 2507 Instruct
$0.36+0%
Grok 3 mini Reasoning (high)
$0.35-1%
Desempenho
Janela de Contexto
164K
tokens
Maior que 49% dos modelos
Saída Máxima
33K
tokens
20% do contexto
Comparação de Janela de Contexto
DeepSeek: DeepSeek V3.2 Speciale
164KIgual
DeepSeek: DeepSeek V3.1 Terminus
164KIgual
DeepSeek: R1
164KIgual