DeepSeek-R1
By
Top open-source reasoning LLM rivaling OpenAI's o1 model; delivers top-tier performance across math, code, and reasoning tasks at a fraction of the cost. All data you provide this bot will not be used in training, and is sent only to Together AI, a US-based company. Supports 164k tokens of input context and 33k tokens of output context. Uses the latest May 28th snapshot (DeepSeek-R1-0528).
Powered by a server managed by @togetherai. Learn more
Build with DeepSeek-R1 using the Poe API
Start by creating an API key, for use with any bot on Poe:
See the full documentation for comprehensive guidance on getting started.
More from Together AI
New
Minimax-M2.7-T
New
Gemma-4-31B-T
New
GLM-5.1-T
New
GLM-5-T
Qwen3.5-9B-T
MiniMax-M2.5-T
Qwen3.5-397B-A17B-T
Qwen-3-Coder-Next-T
EssentialAI-Rnj-1-T
Whisper-V3-Large-T