R1 pricing
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. Fully open-source model & [technical report](https://api-docs.deepseek.com/news/news250120). MIT licensed: Distill & commercialize freely! This page tracks 13 listings in total. Highlighted lows are $0.400 per million input and $0.400 per million output (see table for which seller matches each).
Pricing across providers
Every row is a seller of R1 with token pricing we track. The cheapest input in this snapshot is from Hyperbolic. The bar chart shows the same input and output dollars per million for a quick scan.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
O Openrouter | $0.550 | $2.19 | — | — |
VA Vercel Ai Gateway | $0.550 | $2.19 | — | — |
S Snowflake | N/A | N/A | — | — |
S Sambanova | $5.00 | $7.00 | — | — |
N Nebius | $0.800 | $2.40 | — | — |
H Hyperbolic | $0.400 | $0.400 | — | — |
A Azure | $1.35 | $5.40 | — | — |
N Novita | $0.700 | $2.50 | — | — |
D Deepseeknative | $0.550 | $2.19 | — | — |
D DeepInfra | $0.700 | $2.40 | — | — |
FA Fireworks AI | $3.00 | $8.00 | — | — |
TA Together AI | $3.00 | $7.00 | — | — |
R Replicate | $3.75 | $10.00 | — | — |
Input vs output · per provider
Cost calculator
Pick any of the providers above and type how many tokens you expect per day, week, or year. We turn that into rough dollar totals for R1.
Provider
0.055000¢ / req
0.109500¢ / req
Model specifications
Quick spec sheet for R1 before you dive back into pricing. Family: DeepSeek R1. Reported under Deepseek.
- Context window
- 163,840 tokens
- Max output
- 163,840 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- No
- Released
- Jan 2025
- Primary provider
- Deepseek
- Model family
- DeepSeek R1
Compare R1
Jump into a comparison when you want one table for two models instead of two tabs. 6 curated matches for R1.
Frequently asked questions
Read these after the table if you want plain language around R1 rates. The short model note from our index: 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. Fully open-source model & ...
Also from Deepseek
Other models by Deepseek with live pricing in our catalog.