GPT-4o mini

OK

OpenAI • Regions: us-east, us-west, eu-west

Last updated: 2025-12-30 07:20:21 UTCFreshness: StaleData window: last 24hHow we measure

P95 latency

Error rate

Rate limit

last 60mlast 24hlast 7d

Alert me if degraded Get API endpoint

Reliability score

94/100

Weighted availability + latency

P95 latency

700 ms

Tail latency

Error rate

0.10%

Estimated from uptime

Need fallback recommendations?

Build routing policies with automatic fallbacks across providers.

Create watchlist Sign in

Rate-limit rate

0.60%

429 responses

Availability

99.90%

Measured over last 24h

Confidence: Medium

Latency distribution

Percentiles derived from the latest probe window.

p50

385 ms

p90

595 ms

p95

700 ms

p99

840 ms

Cost snapshot

Cost per 1M tokens

$0.38

Includes input + output

Throughput

140 t/s

Probing baseline

Coverage

Provider: OpenAI

Regions: us-east, us-west, eu-west

Tags: Proprietary, Multimodal, Long Context

Similar models

GPT-4o GPT‑4.1

Compare this model

Add this model to a comparison set and evaluate alternatives side by side.

Compare models