DeepSeek: R1
deepseek/deepseek-r1DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens.
Modalities
In / out per 1M$0.70 / $2.50
Context63K
ReleasedJan 20, 2025
Providers
1 provider serves this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.70 | $2.50 | Variable | 1.20s | 21 tps | 100% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves R1 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what R1 costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.70
per 1M tokens
Output
$2.50
per 1M tokens
Cache read
—
not published
Included in every pass
R1 is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s25.0s50.0s75.0s100.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Median 90th percentile 99th percentile
0 tok/s20 tok/s40 tok/s60 tok/s80 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Median 90th percentile 99th percentile
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.2%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.04%
100% 95% 90% 85%
Oct 13, 2:40 PMNow
Apps
Tools that most often run R1, by tokens this week.
Activity
8.8B tokens processed market-wide in the last month.
0200.0M400.0M600.0M800.0M
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for R1?
deepseek/deepseek-r1. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does R1 hold?
64,000 tokens per request, of which up to 16,000 can be the response.
What can it accept and return?
Input: text. Output: text.
What does R1 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.70 per 1M input tokens and $2.50 per 1M output tokens.
How current is its knowledge?
Training data runs to Jul 2024. Anything later has to come from your prompt or a tool call.
Who built R1?
DeepSeek, in the R1 family.
Explore
Other models your pass can call.
