Qwen3 235B A22B Instruct 2507

qwen/qwen3-235b-a22b-2507InputOutput

Compare its 11 providers Incident RSSCompare with Qwen3 30B A3B Instruct 2507, Qwen3 VL 235B A22B Instruct, Qwen3 Coder 480B A35B

CompareQwen3 235B A22B Instruct 2507

	State
Googlegoogle-vertex/us-south1	Healthy	100%	99.89%	99.60%	99.83%	778ms	15.9s	41 tps	262K	$0.220 / $0.880
Parasailparasail/fp8fp8	Healthy	100%	99.95%	99.91%	99.84%	452ms	2.08s	44 tps	131K	$0.140 / $0.800
StreamLakestreamlake	Healthy	100%	99.16%	98.25%	98.80%	639ms	23.6s	51 tps	128K	$0.210 / $0.840
Venicevenice/fp8fp8	Healthy	100%	91.83%	90.94%	94.26%	639ms	23.6s	21 tps	128K	$0.150 / $0.750
Novitanovita/fp8fp8	Healthy	99.88%	96.94%	96.77%	97.95%	700ms	61.9s	41 tps	131K	$0.090 / $0.580
GMICloudgmicloud/fp8fp8	Healthy	99.63%	99.15%	98.21%	98.53%	1.19s	17.7s	43 tps	262K	$0.087 / $0.350
Alibabaalibaba	Healthy	99.53%	98.79%	97.13%	99.10%	479ms	3.87s	49 tps	131K	$0.150 / $0.598
PrimeIntellectprimeintellect	Healthy	99.24%	94.64%	95.61%	95.61%	766ms	65.9s	35 tps	262K	$0.250 / $1.00
DeepInfradeepinfra/fp8fp8	Healthy	99.08%	90.91%	85.51%	91.07%	521ms	8.10s	16 tps	262K	$0.090 / $0.550
Nebiusnebius/fp8fp8	Healthy	97.76%	90.25%	93.04%	90.91%	455ms	19.8s	49 tps	262K	$0.200 / $0.600
AtlasCloudatlas-cloud/fp8fp8	No data	—	—	—	98.44%	—	—	—	131K	$0.200 / $0.880

Google100%
Healthy24h 99.89%
7d
99.60%
30d
99.83%
p50
778ms
p99
15.9s
Throughput
41 tps
Context
262K
$/Mtok
$0.220 / $0.880
google-vertex/us-south1
Parasail100%
Healthy24h 99.95%
7d
99.91%
30d
99.84%
p50
452ms
p99
2.08s
Throughput
44 tps
Context
131K
$/Mtok
$0.140 / $0.800
parasail/fp8fp8
StreamLake100%
Healthy24h 99.16%
7d
98.25%
30d
98.80%
p50
639ms
p99
23.6s
Throughput
51 tps
Context
128K
$/Mtok
$0.210 / $0.840
streamlake
Venice100%
Healthy24h 91.83%
7d
90.94%
30d
94.26%
p50
639ms
p99
23.6s
Throughput
21 tps
Context
128K
$/Mtok
$0.150 / $0.750
venice/fp8fp8
Novita99.88%
Healthy24h 96.94%
7d
96.77%
30d
97.95%
p50
700ms
p99
61.9s
Throughput
41 tps
Context
131K
$/Mtok
$0.090 / $0.580
novita/fp8fp8
GMICloud99.63%
Healthy24h 99.15%
7d
98.21%
30d
98.53%
p50
1.19s
p99
17.7s
Throughput
43 tps
Context
262K
$/Mtok
$0.087 / $0.350
gmicloud/fp8fp8
Alibaba99.53%
Healthy24h 98.79%
7d
97.13%
30d
99.10%
p50
479ms
p99
3.87s
Throughput
49 tps
Context
131K
$/Mtok
$0.150 / $0.598
alibaba
PrimeIntellect99.24%
Healthy24h 94.64%
7d
95.61%
30d
95.61%
p50
766ms
p99
65.9s
Throughput
35 tps
Context
262K
$/Mtok
$0.250 / $1.00
primeintellect
DeepInfra99.08%
Healthy24h 90.91%
7d
85.51%
30d
91.07%
p50
521ms
p99
8.10s
Throughput
16 tps
Context
262K
$/Mtok
$0.090 / $0.550
deepinfra/fp8fp8
Nebius97.76%
Healthy24h 90.25%
7d
93.04%
30d
90.91%
p50
455ms
p99
19.8s
Throughput
49 tps
Context
262K
$/Mtok
$0.200 / $0.600
nebius/fp8fp8
AtlasCloud—
No data24h —
7d
—
30d
98.44%
p50
—
p99
—
Throughput
—
Context
131K
$/Mtok
$0.200 / $0.880
atlas-cloud/fp8fp8

Measured 2m 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/us-south1

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 11 endpoints · 47 days with data, 160 endpoint-days below 90%.

Price changes

Qwen3 235B A22B Instruct 2507 GMICloudgmicloud/fp8$0.350 → $0.087 / $1.40 → $0.350cache read $0.070 → $0.0182026-09-26 00:50 UTC
Qwen3 235B A22B Instruct 2507 GMICloudgmicloud/fp8$0.087 → $0.350 / $0.350 → $1.40cache read $0.018 → $0.0702026-09-26 00:40 UTC
Qwen3 235B A22B Instruct 2507 GMICloudgmicloud/fp8$0.350 → $0.087 / $1.40 → $0.350cache read $0.070 → $0.0182026-09-09 10:10 UTC
Qwen3 235B A22B Instruct 2507 GMICloudgmicloud/fp8$0.087 → $0.350 / $0.350 → $1.40cache read $0.018 → $0.0702026-09-09 10:05 UTC
Qwen3 235B A22B Instruct 2507 GMICloudgmicloud/fp8$0.350 → $0.087 / $1.40 → $0.350cache read $0.070 → $0.0182026-08-27 18:45 UTC
Qwen3 235B A22B Instruct 2507 GMICloudgmicloud/fp8$0.087 → $0.350 / $0.350 → $1.40cache read $0.018 → $0.0702026-08-27 18:20 UTC
Qwen3 235B A22B Instruct 2507 GMICloudgmicloud/fp8$0.350 → $0.087 / $1.40 → $0.350cache read $0.070 → $0.0182026-08-26 18:31 UTC
Qwen3 235B A22B Instruct 2507 GMICloudgmicloud/fp8$0.087 → $0.350 / $0.350 → $1.40cache read $0.018 → $0.0702026-08-26 14:36 UTC
Qwen3 235B A22B Instruct 2507 GMICloudgmicloud/fp8$0.350 → $0.087 / $1.40 → $0.350cache read $0.070 → $0.0182026-08-26 13:51 UTC
Qwen3 235B A22B Instruct 2507 GMICloudgmicloud/fp8$0.087 → $0.350 / $0.350 → $1.40cache read $0.018 → $0.0702026-08-26 13:46 UTC
Qwen3 235B A22B Instruct 2507 GMICloudgmicloud/fp8$0.350 → $0.087 / $1.40 → $0.350cache read $0.070 → $0.0182026-08-22 20:40 UTC
Qwen3 235B A22B Instruct 2507 GMICloudgmicloud/fp8free → $0.350 / free → $1.40cache read — → $0.0702026-08-19 14:25 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 → $0.220 / $1.00 → $0.8802026-08-19 02:50 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.220 → $0.250 / $0.880 → $1.002026-08-19 02:45 UTC