SiliconFlow DeepSeek V3

SiliconFlow DeepSeek V3: $0.14/1M input tokens, 430 tok/s throughput, 380ms latency. Compare on BenchNode.io.

$0.14

per 1M input tokens

$0.14 / 1M output

Free tier available

Specifications

model id: deepseek-v3
model family: DeepSeek V3
parameters: 685B MoE
context window tokens: 128,000
modality: text
reasoning: No

Performance

Latency (TTFT) 380 ms

lower is better

Uptime SLA 99.9%

Throughput 430 tok/s

380

ms latency

99.9%

uptime

Pricing Detail

input per 1m tokens usd: 0.14
output per 1m tokens usd: 0.14
free tier available: Yes
rate limit tpm: 30,000
rate limit rpm: 60

AI Analysis · gpt-4o-mini

Technical Verdict

With an input and output cost of $0.14 per 1M tokens, this pricing is mid-tier for a model with 685B parameters, while the throughput of 430 tok/s is relatively fast. The rate limits of 30,000 TPM and 60 RPM suggest suitability for low-volume prototyping, and the first-token latency of 380 ms is more favorable for batch use than for real-time applications.