R1 pricing & benchmarks
Released Jan 20, 2025 · served by 2 providers
What R1 is
DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....
- Model ID:
deepseek/deepseek-r1 - Modality: text->text
- Knowledge cutoff: 2024-07-31
- Tool calling: supported · Structured output: supported
- Weights:
deepseek-ai/DeepSeek-R1on Hugging Face
Providers and prices for R1
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| Novitacheapest | $0.700 | $2.50 | 64K | fp8 | 99.8% | — |
| Azure | $1.49 | $5.94 | 164K | — | 97.0% | — |
Cheaper models in the same class
Models scoring within 4 points of R1 on the Intelligence Index, but with a lower output price.
FAQ
How much does the R1 API cost?
$0.700 per 1M input tokens and $2.50 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $1.45.
Is R1 free?
No. It is a paid model starting at $0.700 per 1M input tokens, though some providers offer trial credits.
Which provider is cheapest for R1?
Novita at $0.700 input / $2.50 output per 1M tokens (fp8 quantization).
Can I self-host R1?
Yes — weights are published as deepseek-ai/DeepSeek-R1 on Hugging Face, so you can run it on your own hardware.