Qwen3 32B
qwen/qwen3-32bInputOutput
Compare its 6 providersIncident RSSCompare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B
CompareQwen3 32B
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.83% | 99.82% | 99.78% | 403ms | 2.14s | 24 tps | 41K | $0.080 / $0.280 | |
| Healthy | 100% | 98.52% | 98.01% | 97.53% | 1.15s | 2.33s | 33 tps | 131K | $0.140 / $0.570 | |
| Healthy | 100% | 99.01% | 100% | 100% | 850ms | 7.73s | 35 tps | 41K | $0.070 / $0.200 | |
Groqgroq | No data | — | — | — | — | — | — | — | 131K | $0.290 / $0.590 |
| No data | — | — | — | 99.67% | — | — | — | 41K | $0.100 / $0.300 | |
| No data | — | — | 95.56% | 95.56% | — | — | — | 41K | $0.070 / $0.200 |
- DeepInfra100%Healthy24h 99.83%
- 7d
- 99.82%
- 30d
- 99.78%
- p50
- 403ms
- p99
- 2.14s
- Throughput
- 24 tps
- Context
- 41K
- $/Mtok
- $0.080 / $0.280
deepinfra/fp8fp8 - SiliconFlow100%Healthy24h 98.52%
- 7d
- 98.01%
- 30d
- 97.53%
- p50
- 1.15s
- p99
- 2.33s
- Throughput
- 33 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.570
siliconflow/fp8fp8 - Tenstorrent100%Healthy24h 99.01%
- 7d
- 100%
- 30d
- 100%
- p50
- 850ms
- p99
- 7.73s
- Throughput
- 35 tps
- Context
- 41K
- $/Mtok
- $0.070 / $0.200
tenstorrent/fp8fp8 - Groq—No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.290 / $0.590
groq - No data24h —
- 7d
- —
- 30d
- 99.67%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 41K
- $/Mtok
- $0.100 / $0.300
nebius/basefp8 - No data24h —
- 7d
- 95.56%
- 30d
- 95.56%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 41K
- $/Mtok
- $0.070 / $0.200
tenstorrent/bf16bf16
Measured 1m 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 is OpenRouter's rolling 30-minute window, averaged over the hour.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 6 endpoints · 46 days with data, 40 endpoint-days below 90%.