DeepSeek V4 Pro
V4 Pro con reasoning + non-reasoning modes. Cache hit $0.003625. Reemplaza a DeepSeek Reasoner R1.
deepseek/deepseek-v4-pro
- Contexto
- 1M tokens
- Máx. completion
- 384,000
- Tools
- Sí
- JSON
- Sí
- Lanzamiento
- 2026-04-24
Llámalo desde Geek Hub
El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-pro",
"messages": [{"role": "user", "content": "Hola"}]
}'Consigue tu API keyPreguntas frecuentes
- ¿Qué es DeepSeek V4 Pro?
- V4 Pro con reasoning + non-reasoning modes. Cache hit $0.003625. Reemplaza a DeepSeek Reasoner R1. DeepSeek V4 Pro corre en el API de Geek Hub (compatible con OpenAI). Id: deepseek/deepseek-v4-pro.
- ¿DeepSeek V4 Pro es gratis?
- No. El input cuesta $0.4742 / 1M tokens y el output $0.9484 / 1M tokens en Geek Hub (markup incluido).
- ¿Cuál es el contexto de DeepSeek V4 Pro?
- DeepSeek V4 Pro tiene una ventana de 1M tokens. Soporta hasta 384,000 tokens de completion.
- ¿DeepSeek V4 Pro soporta tool calling y structured outputs?
- DeepSeek V4 Pro acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
- ¿Cuándo se lanzó DeepSeek V4 Pro?
- DeepSeek V4 Pro se lanzó el 24 de abril de 2026.
Más modelos de DeepSeek
DeepSeek V4 FlashV4 Flash open-weight, aggressive pricing with 1M context. Cache hit drops input to $0.0028. Replaces DeepSeek Chat V3.
DeepSeek V3DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tok
DeepSeek V3 0324DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/d
DeepSeek V3.1DeepSeek-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 ba
DeepSeek V3.1 TerminusDeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, inc
DeepSeek V3.2DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse At