Groq DeepSeek R1 Distill 70B

Groq DeepSeek R1 Distill 70B: $0.75/1M input tokens, 500 tok/s throughput, 400ms latency. Compare on BenchNode.io.

$0.75

per 1M input tokens

$0.99 / 1M output

Free tier available

Specifications

model id: deepseek-r1-70b
model family: DeepSeek R1
parameters: 70B
context window tokens: 128,000
modality: text
reasoning: Yes

Performance

Latency (TTFT) 400 ms

lower is better

Uptime SLA 99.9%

Throughput 500 tok/s

400

ms latency

99.9%

uptime

Pricing Detail

input per 1m tokens usd: 0.75
output per 1m tokens usd: 0.99
free tier available: Yes
rate limit tpm: 6,000
rate limit rpm: 30

AI Analysis · gpt-4o-mini

Technical Verdict

The input cost of $0.75 / 1M tokens and output cost of $0.99 / 1M tokens position this API tier at a mid-range price point for its model class, with a throughput of 500 tok/s indicating fast processing capabilities. The rate limits of 6,000 TPM and 30 RPM suggest suitability for low-volume prototyping rather than high-volume production, while the first-token latency of 400 ms leans towards real-time applications like chat or streaming rather than batch processing.