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
Compare its 10 providers · Incident RSS
Showing only the atlas-cloud/fp8 provider · show all 10
CompareQwen3 235B A22B Instruct 2507
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Degraded | 90.34% | 99.69% | 99.79% | 99.79% | 944ms | 28.6s | 30 tps | 131K | $0.200 / $0.880 |
- AtlasCloud90.34%Degraded24h 99.69%
- 7d
- 99.79%
- 30d
- 99.79%
- p50
- 944ms
- p99
- 28.6s
- Throughput
- 30 tps
- 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.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 10 endpoints · 3 days with data, 11 endpoint-days below 90%. Tables and charts above are filtered to atlas-cloud/fp8.
Price changes
- Qwen3 235B A22B Instruct 2507GMICloudgmicloud/fp8free → $0.350 / free → $1.40cache read — → $0.0702026-08-19 14:25 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.250 → $0.220 / $1.00 → $0.8802026-08-19 02:50 UTC
- Qwen3 235B A22B Instruct 2507Googlegoogle-vertex/us-south1$0.220 → $0.250 / $0.880 → $1.002026-08-19 02:45 UTC