(3 × $0.090 + $1.10) ÷ 4 = $0.343/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.090, 3:1 $0.343, 1:1 $0.595, output only $1.10 per 1M.
The board shows this model's cheapest measured offer ($0.343/1M); the smaller figure under it is the mean of the 9 offers listed below ($0.461/1M). Add those up and divide — it matches.
Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/qwen3-next-80b-a3b-instruct.json. Free reuse requires attribution to tkx.org.
About
Qwen3 Next 80B A3B Instruct is a large language model served by multiple inference providers on AI model marketplaces, designed for natural language processing tasks. It specializes in understanding and generating human-like text based on given instructions.
AI-generated summary from public information — is this yours?
FAQ
How much does Qwen3-Next-80B-A3B-Instruct cost?
Cheapest measured offer right now: $0.09/1M input, $1.1/1M output via deepinfra — across 8 tracked providers, refreshed hourly.
Who serves Qwen3-Next-80B-A3B-Instruct?
8 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
Is the price of Qwen3-Next-80B-A3B-Instruct going up or down?
The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.