OpenAI o3-mini

OpenAI o3-mini: $1.1/1M input tokens, 280 tok/s throughput, 900ms latency. Compare on BenchNode.io.

$1.1

per 1M input tokens

$4.4 / 1M output

Specifications

model id: o3-mini
model family: o3
parameters: undisclosed
context window tokens: 200,000
modality: text
reasoning: Yes

Performance

Latency (TTFT) 900 ms

lower is better

Uptime SLA 99.99%

Throughput 280 tok/s

900

ms latency

99.99%

uptime

Pricing Detail

input per 1m tokens usd: 1.1
output per 1m tokens usd: 4.4
free tier available: No
rate limit tpm: 500,000
rate limit rpm: 500
batch discount pct: 50

AI Analysis · gpt-4o-mini

Technical Verdict

The input cost of $1.1 / 1M tokens and output cost of $4.4 / 1M tokens position this API tier at a mid-range price point, with a throughput of 280 tok/s indicating a slow performance for high-demand applications; the 50% discount on async batch jobs benefits bulk async jobs. The rate limits of 500,000 TPM and 500 RPM suggest suitability for low-volume prototyping, while the first-token latency of 900 ms leans towards batch use rather than real-time applications.