Qwen3 Next 80B A3B Thinking: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
- No data24h 99.11%
- 7d
- 99.98%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 455ms
- p99
- 607ms
- Throughput
- 233 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.150 / $1.20◆ (best)
alibaba - No data24h 99.74%
- 7d
- 99.29%
- 30d
- 99.89%
- p50
- 340ms◆ (best)
- p99
- 541ms◆ (best)
- Throughput
- 123 tps
- Context
- 262K
- $/Mtok
- $0.150 / $1.20◆ (best)
google-vertex/global - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 128K
- $/Mtok
- $0.150 / $1.20◆ (best)
nebius/fp8fp8
Measured 1m 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.