modelstatus.dev

Qwen3 Next 80B A3B Thinking

qwen/qwen3-next-80b-a3b-thinkingInputOutput

Compare its 3 providers Incident RSSCompare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B

CompareQwen3 Next 80B A3B Thinking

	State
Alibabaalibaba	No data	—	94.96%	99.99%	100%	574ms	1.24s	175 tps	131K	$0.150 / $1.20
Googlegoogle-vertex/global	No data	—	99.56%	99.12%	99.89%	535ms	57.0s	126 tps	262K	$0.150 / $1.20
Nebiusnebius/fp8fp8	No data	—	—	—	—	—	—	—	128K	$0.150 / $1.20

Alibaba—
No data24h 94.96%
7d
99.99%
30d
100%
p50
574ms
p99
1.24s
Throughput
175 tps
Context
131K
$/Mtok
$0.150 / $1.20
alibaba
Google—
No data24h 99.56%
7d
99.12%
30d
99.89%
p50
535ms
p99
57.0s
Throughput
126 tps
Context
262K
$/Mtok
$0.150 / $1.20
google-vertex/global
Nebius—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
128K
$/Mtok
$0.150 / $1.20
nebius/fp8fp8

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

Availability

Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.

Time to first token

Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window, averaged over the hour.

Throughput

Median tokens per second.

Daily availability

One row per endpoint · one dot per day · last 90 days.

Jul

Aug

Sep

Oct

google-vertex/global

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 3 endpoints · 34 days with data, none below the red threshold.