DeepSeek V3.1 Terminus: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
StreamLakestreamlake | Healthy | 100%◆ (best) | 99.96% | 99.67%◆ (best) | 99.45% | 841ms◆ (best) | 4.90s◆ (best) | 67 tps◆ (best) | 128K | $0.343 / $1.03 |
| Healthy | 98.31% | 98.53% | 98.24% | 98.15% | 2.36s | 22.8s | 17 tps | 164K | $0.270 / $1.00◆ (best) | |
| No data | — | — | 99.30% | 99.06% | — | — | — | 131K | $0.300 / $1.00 | |
| No data | — | — | — | 99.95%◆ (best) | — | — | — | 131K | $0.270 / $1.00◆ (best) |
- StreamLake100%◆ (best)Healthy24h 99.96%
- 7d
- 99.67%◆ (best)
- 30d
- 99.45%
- p50
- 841ms◆ (best)
- p99
- 4.90s◆ (best)
- Throughput
- 67 tps◆ (best)
- Context
- 128K
- $/Mtok
- $0.343 / $1.03
streamlake - SiliconFlow98.31%Healthy24h 98.53%
- 7d
- 98.24%
- 30d
- 98.15%
- p50
- 2.36s
- p99
- 22.8s
- Throughput
- 17 tps
- Context
- 164K
- $/Mtok
- $0.270 / $1.00◆ (best)
siliconflow/fp8fp8 - No data24h —
- 7d
- 99.30%
- 30d
- 99.06%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.300 / $1.00
atlas-cloud/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 99.95%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.270 / $1.00◆ (best)
novita/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, averaged over the hour.
Throughput
Median tokens per second.