DeepSeek V3.2 Exp: 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 | 99.80%◆ (best) | 96.99% | 96.67% | 96.67% | 1.68s◆ (best) | 11.1s | 24 tps◆ (best) | 164K | $0.270 / $0.410◆ (best) | |
| Healthy | 96.84% | 99.34% | 99.27%◆ (best) | 99.27%◆ (best) | 1.69s | 13.3s | 18 tps | 164K | $0.270 / $0.410◆ (best) | |
| Down | 86.30% | 97.10% | 98.93% | 98.93% | 1.72s | 6.97s◆ (best) | 22 tps | 164K | $0.270 / $0.410◆ (best) |
- AtlasCloud99.80%◆ (best)Healthy24h 96.99%
- 7d
- 96.67%
- 30d
- 96.67%
- p50
- 1.68s◆ (best)
- p99
- 11.1s
- Throughput
- 24 tps◆ (best)
- Context
- 164K
- $/Mtok
- $0.270 / $0.410◆ (best)
atlas-cloud/fp8fp8 - Novita96.84%Healthy24h 99.34%
- 7d
- 99.27%◆ (best)
- 30d
- 99.27%◆ (best)
- p50
- 1.69s
- p99
- 13.3s
- Throughput
- 18 tps
- Context
- 164K
- $/Mtok
- $0.270 / $0.410◆ (best)
novita/fp8fp8 - SiliconFlow86.30%Down24h 97.10%
- 7d
- 98.93%
- 30d
- 98.93%
- p50
- 1.72s
- p99
- 6.97s◆ (best)
- Throughput
- 22 tps
- Context
- 164K
- $/Mtok
- $0.270 / $0.410◆ (best)
siliconflow/fp8fp8
Measured 3m 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.