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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100%◆ (best) | 99.86% | 99.78% | 99.92% | 401ms◆ (best) | 786ms◆ (best) | 93 tps | 131K | $0.098 / $0.780 |
| Healthy | 100%◆ (best) | 99.80% | 99.55% | 99.37% | 683ms | 5.69s | 88 tps | 262K | $0.090 / $1.10◆ (best) | |
Googlegoogle-vertex/global | Healthy | 100%◆ (best) | 99.92% | 99.81% | 99.88% | 582ms | 1.73s | 159 tps◆ (best) | 262K | $0.150 / $1.20 |
| Healthy | 100%◆ (best) | 99.96% | 99.96%◆ (best) | 99.95%◆ (best) | 815ms | 3.12s | 103 tps | 262K | $0.100 / $1.10 | |
| Degraded | 93.84% | 83.78% | 88.72% | 93.62% | 1.30s | 10.5s | 81 tps | 131K | $0.150 / $1.50 |
- Alibaba100%◆ (best)Healthy24h 99.86%
- 7d
- 99.78%
- 30d
- 99.92%
- p50
- 401ms◆ (best)
- p99
- 786ms◆ (best)
- Throughput
- 93 tps
- Context
- 131K
- $/Mtok
- $0.098 / $0.780
alibaba - DeepInfra100%◆ (best)Healthy24h 99.80%
- 7d
- 99.55%
- 30d
- 99.37%
- p50
- 683ms
- p99
- 5.69s
- Throughput
- 88 tps
- Context
- 262K
- $/Mtok
- $0.090 / $1.10◆ (best)
deepinfra/fp8fp8 - Google100%◆ (best)Healthy24h 99.92%
- 7d
- 99.81%
- 30d
- 99.88%
- p50
- 582ms
- p99
- 1.73s
- Throughput
- 159 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
- 815ms
- p99
- 3.12s
- Throughput
- 103 tps
- Context
- 262K
- $/Mtok
- $0.100 / $1.10
parasail/fp8fp8 - Novita93.84%Degraded24h 83.78%
- 7d
- 88.72%
- 30d
- 93.62%
- p50
- 1.30s
- p99
- 10.5s
- Throughput
- 81 tps
- Context
- 131K
- $/Mtok
- $0.150 / $1.50
novita/bf16bf16
Measured 2m 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.
Throughput
Median tokens per second.