DeepSeek V3.1 Terminus

DeepSeek-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, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. Learn more in our docs The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.

ChatDeepSeek164k tokens$0.2943 / $1.0901 · 1M

deepseek/deepseek-v3.1-terminus

Contexto
164k tokens
Máx. completion
32,768
Tools
Sí
JSON
Sí
Lanzamiento
2025-09-22

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-v3.1-terminus",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Consigue tu API key

Preguntas frecuentes

¿Qué es DeepSeek V3.1 Terminus?
DeepSeek-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, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. Learn more in our docs The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. DeepSeek V3.1 Terminus corre en el API de Geek Hub (compatible con OpenAI). Id: deepseek/deepseek-v3.1-terminus.
¿DeepSeek V3.1 Terminus es gratis?
No. El input cuesta $0.2943 / 1M tokens y el output $1.0901 / 1M tokens en Geek Hub (markup incluido).
¿Cuál es el contexto de DeepSeek V3.1 Terminus?
DeepSeek V3.1 Terminus tiene una ventana de 164k tokens. Soporta hasta 32,768 tokens de completion.
¿DeepSeek V3.1 Terminus soporta tool calling y structured outputs?
DeepSeek V3.1 Terminus acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
¿Cuándo se lanzó DeepSeek V3.1 Terminus?
DeepSeek V3.1 Terminus se lanzó el 22 de septiembre de 2025.

Más modelos de DeepSeek