Deepseek R1 (FREE)
wisdom-ai-dsr1
A High-Performance Mixture-of-Experts (MoE) Language Model.
A High-Performance Mixture-of-Experts (MoE) Language Model.
Intelligence
Higher
Speed
Slowest
Price
Free • Free
Input • Output
Input
Text
Output
Text
DeepSeek-R1 is a large language model (LLM) developed by DeepSeek AI. It is specifically designed as a reasoning model, optimized for complex tasks that require logical thinking, problem-solving, and step-by-step analysis. Notice: The free model is provided to let everyone experience its capabilities — with up to 50 requests per day. The original full version remains unlimited in usage but requires a paid plan for access.
4096 context window
2048 max output tokens
knowledge cutoff
Modalities
Text
Input and output
Image
Not supported
Audio
Not supported
Video
Not supported
Endpoints
Chat Completions
v1/chat/completions
Responses
v1/responses
Realtime
v1/realtime
Assistants
v1/assistants
Batch
v1/batch
Fine-tuning
v1/fine-tuning
Embeddings
v1/embeddings
Image generation
v1/images/generations
Videos
v1/videos
Image edit
v1/images/edits
Speech generation
v1/audio/speech
Transcription
v1/audio/transcriptions
Translation
v1/audio/translations
Moderation
v1/moderations
Completions (legacy)
v1/completions
Features
Streaming
Supported
Function calling
Not supported
Structured outputs
Supported
Fine-tuning
Not supported
Distillation
Not supported