DeepInfra DeepSeek V3

DeepInfra DeepSeek V3: $0.27/1M input tokens, 480 tok/s throughput, 350ms latency. Compare on BenchNode.io.

$0.27

per 1M input tokens

$0.27 / 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) 350 ms

lower is better

Uptime SLA 99.9%

Throughput 480 tok/s

350

ms latency

99.9%

uptime

Pricing Detail

input per 1m tokens usd: 0.27
output per 1m tokens usd: 0.27
free tier available: Yes
rate limit tpm: 15,000
rate limit rpm: 60

AI Analysis · gpt-4o-mini

Technical Verdict

The input/output cost of $0.27 per 1M tokens positions this API tier in the mid-range for its class, while the throughput of 480 tok/s is relatively fast. With rate limits of 15,000 TPM and 60 RPM, these constraints are more suited for low-volume prototyping rather than high-volume production, and the first-token latency of 350 ms is better aligned with batch use than real-time applications.