MuAPI 上的 DeepSeek AI 模型

探索用于对话、代码、图像和视频生成的 DeepSeek 模型，包括可通过 MuAPI 使用的 Gemini、Nano Banana 和 Veo 风格工作流。

所有模型

6 个模型

对话与语言模型

对话

$0.000 / 1K tokens

deepseek-v4-pro

DeepSeek V4 Pro is an advanced flagship multimodal reasoning model designed for complex coding, mathematical, and multi-step reasoning tasks.

对话

$0.000 / 1K tokens

deepseek-v4-flash

DeepSeek V4 Flash is an ultra-fast multimodal reasoning model optimized for low-latency text and image understanding tasks.

对话

$0.000 / 1K tokens

deepseek-v4-1-flash

DeepSeek V4.1 Flash is a multimodal reasoning model with a 1M-token context window, image understanding, and adjustable reasoning effort.

对话

$0.000 / 1K tokens

deepseek-r1-llama-70b-abliterated

DeepSeek R1 Distill Llama 70B Abliterated is an abliterated DeepSeek R1 reasoning distillation built on Llama 70B with a 16K-token context window.

对话

$0.000 / 1K tokens

deepseek-r1-qwen-32b-abliterated

DeepSeek R1 Distill Qwen 32B Abliterated is a compact abliterated DeepSeek R1 reasoning distillation built on Qwen 32B with a 16K-token context window.

对话

$0.000 / 1K tokens

deepseek-v4-1-flash-abliterated

DeepSeek V4.1 Flash Abliterated is a fast DeepSeek V4.1 Flash reasoning model with a 1M-token context window and tool-calling support, modified with abliteration to reduce refusal behavior; an optional thinking mode enables extended reasoning.