모든 모델
6 모델 {count}개 이용 가능텍스트 및 대화 모델
$0.000 / 1,000 토큰당
deepseek-v4-pro
DeepSeek V4 Pro is an advanced flagship multimodal reasoning model designed for complex coding, mathematical, and multi-step reasoning tasks.
$0.000 / 1,000 토큰당
deepseek-v4-flash
DeepSeek V4 Flash is an ultra-fast multimodal reasoning model optimized for low-latency text and image understanding tasks.
$0.000 / 1,000 토큰당
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.
$0.000 / 1,000 토큰당
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.
$0.000 / 1,000 토큰당
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.
$0.000 / 1,000 토큰당
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.