modelstatus.dev

Qwen3 14B

qwen/qwen3-14bInputOutput

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

CompareQwen3 14B

	State
Alibabaalibaba	Healthy	100%	99.99%	99.43%	99.78%	298ms	549ms	60 tps	131K	$0.227 / $0.910
DeepInfradeepinfra/fp8fp8	Healthy	100%	99.85%	96.78%	98.50%	1.20s	16.7s	28 tps	41K	$0.120 / $0.240
NextBitnextbit/int4int4	No data	—	99.97%	99.78%	99.57%	1.24s	3.47s	56 tps	41K	$0.100 / $0.220

Alibaba100%
Healthy24h 99.99%
7d
99.43%
30d
99.78%
p50
298ms
p99
549ms
Throughput
60 tps
Context
131K
$/Mtok
$0.227 / $0.910
alibaba
DeepInfra100%
Healthy24h 99.85%
7d
96.78%
30d
98.50%
p50
1.20s
p99
16.7s
Throughput
28 tps
Context
41K
$/Mtok
$0.120 / $0.240
deepinfra/fp8fp8
NextBit—
No data24h 99.97%
7d
99.78%
30d
99.57%
p50
1.24s
p99
3.47s
Throughput
56 tps
Context
41K
$/Mtok
$0.100 / $0.220
nextbit/int4int4

Measured 1m 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.

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 · 3 endpoints · 48 days with data, 24 endpoint-days below 90%.