modelstatus.dev

Qwen3 235B A22B Thinking 2507

qwen/qwen3-235b-a22b-thinking-2507InputOutput

Compare its 4 providers Incident RSSCompare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 VL 235B A22B Instruct

CompareQwen3 235B A22B Thinking 2507

	State
Alibabaalibaba	No data	—	99.64%	99.80%	99.88%	503ms	3.93s	77 tps	131K	$0.230 / $2.30
DeepInfradeepinfra/fp8fp8	No data	—	—	—	—	—	—	—	262K	$0.230 / $2.30
Novitanovita/fp8fp8	No data	—	99.97%	99.20%	98.10%	1.71s	4.30s	45 tps	131K	$0.300 / $3.00
Venicevenice/fp8fp8	No data	—	99.82%	95.54%	95.93%	566ms	1.01s	99 tps	128K	$0.450 / $3.50

Alibaba—
No data24h 99.64%
7d
99.80%
30d
99.88%
p50
503ms
p99
3.93s
Throughput
77 tps
Context
131K
$/Mtok
$0.230 / $2.30
alibaba
DeepInfra—
No data24h —
7d
—
30d
—
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.230 / $2.30
deepinfra/fp8fp8
Novita—
No data24h 99.97%
7d
99.20%
30d
98.10%
p50
1.71s
p99
4.30s
Throughput
45 tps
Context
131K
$/Mtok
$0.300 / $3.00
novita/fp8fp8
Venice—
No data24h 99.82%
7d
95.54%
30d
95.93%
p50
566ms
p99
1.01s
Throughput
99 tps
Context
128K
$/Mtok
$0.450 / $3.50
venice/fp8fp8

Measured 5m 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

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 4 endpoints · 47 days with data, 26 endpoint-days below 90%.