Qwen3 235B A22B Instruct 2507

qwen/qwen3-235b-a22b-2507

Compare with Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B, Qwen3 Next 80B A3B Instruct

Showing only the novita/fp8 provider · show all 10

CompareQwen3 235B A22B Instruct 2507

	State
Novitanovita/fp8fp8	Degraded	91.72%	98.16%	98.76%	98.76%	776ms	11.1s	25 tps	131K	$0.090 / $0.580

Novita91.72%
Degraded24h 98.16%
7d
98.76%
30d
98.76%
p50
776ms
p99
11.1s
Throughput
25 tps
Context
131K
$/Mtok
$0.090 / $0.580
novita/fp8fp8

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

Price history

Input $/Mtok

Step line — each recorded price holds until the next change.

Output $/Mtok

Step line — each recorded price holds until the next change.

Price changes

Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 14:20 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 14:15 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 14:10 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 14:05 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 14:00 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 13:55 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 13:50 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 13:45 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 13:40 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 13:35 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 13:30 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 13:25 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 13:20 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 13:16 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 13:10 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 13:05 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 13:00 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 12:55 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 12:50 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 12:45 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 12:40 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 12:35 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 12:30 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 12:25 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 12:20 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 12:15 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 12:10 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 12:05 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 12:00 UTC
Qwen3 235B A22B Instruct 2507 Googlegoogle-vertex/us-south1$0.250 / $1.00 → $0.220 / $0.8802026-08-21 11:55 UTC

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

Half a year, one cell per UTC day.

Feb

Mar

Apr

May

Jun

Jul

Aug

Mon

Wed

Fri

worst hour ≥ 95%90–95%< 90%no data

Colour by worst endpoint-hour of each UTC day · 3 days with data, 3 with at least one endpoint-hour below 90%.