DeepSeek V3.2

DeepSeek-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 Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. Learn more in our docs

ChatDeepSeek164k tokens$0.2834 / $0.4142 · 1M

deepseek/deepseek-v3.2

Contexto
164k tokens
Máx. completion
163,840
Tools
Sí
JSON
Sí
Lanzamiento
2025-12-01

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-v3.2",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Consigue tu API key

Preguntas frecuentes

¿Qué es DeepSeek V3.2?
DeepSeek-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 Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. Learn more in our docs DeepSeek V3.2 corre en el API de Geek Hub (compatible con OpenAI). Id: deepseek/deepseek-v3.2.
¿DeepSeek V3.2 es gratis?
No. El input cuesta $0.2834 / 1M tokens y el output $0.4142 / 1M tokens en Geek Hub (markup incluido).
¿Cuál es el contexto de DeepSeek V3.2?
DeepSeek V3.2 tiene una ventana de 164k tokens. Soporta hasta 163,840 tokens de completion.
¿DeepSeek V3.2 soporta tool calling y structured outputs?
DeepSeek V3.2 acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
¿Cuándo se lanzó DeepSeek V3.2?
DeepSeek V3.2 se lanzó el 1 de diciembre de 2025.

Más modelos de DeepSeek