Qwen3 32B: 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) | 99.93% | 99.85%◆ (best) | 99.78%◆ (best) | 393ms◆ (best) | 2.75s◆ (best) | 27 tps | 41K | $0.080 / $0.280 | |
| Healthy | 100%◆ (best) | 95.06% | 98.71% | 97.45% | 1.08s | 6.99s | 27 tps | 131K | $0.140 / $0.570 | |
| Healthy | 99.74% | 97.92% | 97.24% | 97.24% | 512ms | 7.41s | 34 tps◆ (best) | 41K | $0.140 / $0.400 | |
Groqgroq | No data | — | — | — | — | — | — | — | 131K | $0.290 / $0.590 |
| No data | — | — | — | — | — | — | — | 41K | $0.100 / $0.300 | |
| No data | — | — | 95.56% | 95.56% | — | — | — | 41K | $0.070 / $0.200◆ (best) |
- DeepInfra100%◆ (best)Healthy24h 99.93%
- 7d
- 99.85%◆ (best)
- 30d
- 99.78%◆ (best)
- p50
- 393ms◆ (best)
- p99
- 2.75s◆ (best)
- Throughput
- 27 tps
- Context
- 41K
- $/Mtok
- $0.080 / $0.280
deepinfra/fp8fp8 - SiliconFlow100%◆ (best)Healthy24h 95.06%
- 7d
- 98.71%
- 30d
- 97.45%
- p50
- 1.08s
- p99
- 6.99s
- Throughput
- 27 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.570
siliconflow/fp8fp8 - Tenstorrent99.74%Healthy24h 97.92%
- 7d
- 97.24%
- 30d
- 97.24%
- p50
- 512ms
- p99
- 7.41s
- Throughput
- 34 tps◆ (best)
- Context
- 41K
- $/Mtok
- $0.140 / $0.400
tenstorrent/fp8fp8 - Groq—No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.290 / $0.590
groq - No data24h —
- 7d
- —
- 30d
- —
- 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◆ (best)
tenstorrent/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, averaged over the hour.
Throughput
Median tokens per second.