Qwen3 Next 80B A3B Instruct: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.80% | 99.55% | 99.37% | 681ms | 2.62s | 120 tps | 262K | $0.090 / $1.10◆ (best) | |
Googlegoogle-vertex/global | Healthy | 100%◆ (best) | 99.91% | 99.81% | 99.88% | 570ms | 1.61s | 187 tps◆ (best) | 262K | $0.150 / $1.20 |
| Healthy | 100%◆ (best) | 99.96% | 99.96%◆ (best) | 99.95%◆ (best) | 920ms | 3.55s | 117 tps | 262K | $0.100 / $1.10 | |
Alibabaalibaba | Healthy | 98.82% | 99.85% | 99.78% | 99.92% | 428ms◆ (best) | 1.00s◆ (best) | 98 tps | 131K | $0.098 / $0.780 |
| Down | 79.69% | 85.10% | 88.69% | 93.61% | 1.72s | 27.2s | 123 tps | 131K | $0.150 / $1.50 |
- DeepInfra100%◆ (best)Healthy24h 99.80%
- 7d
- 99.55%
- 30d
- 99.37%
- p50
- 681ms
- p99
- 2.62s
- Throughput
- 120 tps
- Context
- 262K
- $/Mtok
- $0.090 / $1.10◆ (best)
deepinfra/fp8fp8 - Google100%◆ (best)Healthy24h 99.91%
- 7d
- 99.81%
- 30d
- 99.88%
- p50
- 570ms
- p99
- 1.61s
- Throughput
- 187 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.150 / $1.20
google-vertex/global - Parasail100%◆ (best)Healthy24h 99.96%
- 7d
- 99.96%◆ (best)
- 30d
- 99.95%◆ (best)
- p50
- 920ms
- p99
- 3.55s
- Throughput
- 117 tps
- Context
- 262K
- $/Mtok
- $0.100 / $1.10
parasail/fp8fp8 - Alibaba98.82%Healthy24h 99.85%
- 7d
- 99.78%
- 30d
- 99.92%
- p50
- 428ms◆ (best)
- p99
- 1.00s◆ (best)
- Throughput
- 98 tps
- Context
- 131K
- $/Mtok
- $0.098 / $0.780
alibaba - Novita79.69%Down24h 85.10%
- 7d
- 88.69%
- 30d
- 93.61%
- p50
- 1.72s
- p99
- 27.2s
- Throughput
- 123 tps
- Context
- 131K
- $/Mtok
- $0.150 / $1.50
novita/bf16bf16
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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.