DeepInfra Qwen3 32B

DeepInfra Qwen3 32B: $0.4/1M input tokens, 560 tok/s throughput, 290ms latency. Compare on BenchNode.io.

$0.4

per 1M input tokens

$0.4 / 1M output

Free tier available

Specifications

model id: qwen3-32b
model family: Qwen3
parameters: 32B
context window tokens: 32,768
modality: text
reasoning: Yes

Performance

Latency (TTFT) 290 ms

lower is better

Uptime SLA 99.9%

Throughput 560 tok/s

290

ms latency

99.9%

uptime

Pricing Detail

input per 1m tokens usd: 0.4
output per 1m tokens usd: 0.4
free tier available: Yes
rate limit tpm: 15,000
rate limit rpm: 60

AI Analysis · gpt-4o-mini

Technical Verdict

At $0.4 per 1M tokens for both input and output, this pricing is mid-tier for a 32B parameter model, with a throughput of 560 tok/s indicating fast performance. The rate limits of 15,000 TPM and 60 RPM are more suited for low-volume prototyping, while the first-token latency of 290 ms favors batch use over real-time applications.