Qwen3 Next 80B A3B Instruct
qwen/qwen3-next-80b-a3b-instruct
Compare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B
CompareQwen3 Next 80B A3B Instruct
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 100% | 100% | 100% | 572ms | 1.15s | 107 tps | 131K | $0.098 / $0.780 |
| Healthy | 100% | 99.25% | 99.05% | 99.05% | 483ms | 5.04s | 39 tps | 262K | $0.090 / $1.10 | |
Googlegoogle-vertex/global | Healthy | 100% | 99.81% | 99.95% | 99.95% | 608ms | 2.72s | 67 tps | 262K | $0.150 / $1.20 |
| Healthy | 100% | 99.99% | 99.98% | 99.98% | 934ms | 3.71s | 30 tps | 262K | $0.100 / $1.10 | |
| No data | — | 99.74% | 99.77% | 99.77% | 603ms | 4.69s | 28 tps | 131K | $0.150 / $1.50 |
- Alibaba100%Healthy24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 572ms
- p99
- 1.15s
- Throughput
- 107 tps
- Context
- 131K
- $/Mtok
- $0.098 / $0.780
alibaba - DeepInfra100%Healthy24h 99.25%
- 7d
- 99.05%
- 30d
- 99.05%
- p50
- 483ms
- p99
- 5.04s
- Throughput
- 39 tps
- Context
- 262K
- $/Mtok
- $0.090 / $1.10
deepinfra/fp8fp8 - Google100%Healthy24h 99.81%
- 7d
- 99.95%
- 30d
- 99.95%
- p50
- 608ms
- p99
- 2.72s
- Throughput
- 67 tps
- Context
- 262K
- $/Mtok
- $0.150 / $1.20
google-vertex/global - Parasail100%Healthy24h 99.99%
- 7d
- 99.98%
- 30d
- 99.98%
- p50
- 934ms
- p99
- 3.71s
- Throughput
- 30 tps
- Context
- 262K
- $/Mtok
- $0.100 / $1.10
parasail/fp8fp8 - No data24h 99.74%
- 7d
- 99.77%
- 30d
- 99.77%
- p50
- 603ms
- p99
- 4.69s
- Throughput
- 28 tps
- Context
- 131K
- $/Mtok
- $0.150 / $1.50
novita/bf16bf16
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is omitted from the charts.
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.