Capabilities
7-day heat trend
−26.2%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 43% of tracked models
- Faster than 27% of tracked models
- Efficiency rank: #327 of 1105
Best suited for
Complex reasoning, analysis, planning and multi-step problem solving where answer quality matters more than raw cost.
About deepseek-ai/DeepSeek-R1
DeepSeek R1 via Hugging Face Inference Providers is a routed reasoning model with provider pass-through pricing.
deepseek-ai/DeepSeek-R1 is a Reasoning model from Hugging Face (US). HotON.ai tracks it at $0.00 per 1M input tokens and $0.00 per 1M output tokens, with a 128K-token context window, ~136 tokens/sec throughput and 96.5% availability. Its composite efficiency score is 89/100 at an estimated $0.000 per successful task.
Compare deepseek-ai/DeepSeek-R1
Related market news
Frequently asked questions
How much does deepseek-ai/DeepSeek-R1 cost per 1M tokens?+
deepseek-ai/DeepSeek-R1 is tracked at $0.00 per 1M input tokens and $0.00 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.00 per 1M tokens. Figures are illustrative demo data.
What is deepseek-ai/DeepSeek-R1 best for?+
Complex reasoning, analysis, planning and multi-step problem solving where answer quality matters more than raw cost.
How fast is deepseek-ai/DeepSeek-R1?+
deepseek-ai/DeepSeek-R1 delivers about 136 tokens/sec with 96.5% tracked availability, suitable for latency-sensitive, real-time applications.
Is deepseek-ai/DeepSeek-R1 cheaper than other AI models?+
Within the HotON.ai tracked set, deepseek-ai/DeepSeek-R1 is cheaper than 43% of models on input price and ranks #327 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.