Not enough recent Qwen 3.5 122B A10B traffic to name a fastest provider yet. This page fills in as real requests flow through the gateway.
Latency, time to first token, throughput, uptime and price for Qwen 3.5 122B A10B — measured across every provider that serves it, from real API traffic.
$0.0046 per request · as of Fri, 21 Aug 2026 19:24:39 UTC
No graded Qwen 3.5 122B A10B traffic in the measured windows yet. Providers appear here once enough real requests have been served to rank them honestly.
Building history. A latency, uptime and price point is recorded for Qwen 3.5 122B A10B every day — trends appear here after the first couple of daily snapshots.
Every figure is measured from real NinjaChat API traffic. Latency percentiles are over successful responses; uptime counts HTTP 5xx as failures and excludes client errors (4xx) and rate limits. Throughput is output tokens over the post-first-token window. A provider with fewer than 30 requests in a window is marked “collecting” and never ranked. History comes from a daily snapshot of these metrics — we publish what we measure.