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
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 100% | 453ms | 1.04s | 68 tps | 131K | $0.098 / $0.780 |
DeepInfradeepinfra/fp8fp8 | Healthy | 100% | 98.80% | 357ms | 1.19s | 85 tps | 262K | $0.090 / $1.10 |
Googlegoogle-vertex/global | Healthy | 100% | 99.98% | 376ms | 1.61s | 67 tps | 262K | $0.150 / $1.20 |
Novitanovita/bf16bf16 | Healthy | 100% | 99.73% | 614ms | 1.41s | 35 tps | 131K | $0.150 / $1.50 |
Parasailparasail/fp8fp8 | Healthy | 100% | 99.98% | 810ms | 1.72s | 17 tps | 262K | $0.100 / $1.10 |
- Alibaba100%Healthy24h 100%
- p50
- 453ms
- p99
- 1.04s
- Throughput
- 68 tps
- Context
- 131K
- $/Mtok
- $0.098 / $0.780
alibaba - DeepInfra100%Healthy24h 98.80%
- p50
- 357ms
- p99
- 1.19s
- Throughput
- 85 tps
- Context
- 262K
- $/Mtok
- $0.090 / $1.10
deepinfra/fp8fp8 - Google100%Healthy24h 99.98%
- p50
- 376ms
- p99
- 1.61s
- Throughput
- 67 tps
- Context
- 262K
- $/Mtok
- $0.150 / $1.20
google-vertex/global - Novita100%Healthy24h 99.73%
- p50
- 614ms
- p99
- 1.41s
- Throughput
- 35 tps
- Context
- 131K
- $/Mtok
- $0.150 / $1.50
novita/bf16bf16 - Parasail100%Healthy24h 99.98%
- p50
- 810ms
- p99
- 1.72s
- Throughput
- 17 tps
- Context
- 262K
- $/Mtok
- $0.100 / $1.10
parasail/fp8fp8
Measured 4m 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.