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% | 99.66%◆ (best) | 99.45% | 772ms◆ (best) | 3.56s◆ (best) | 67 tps◆ (best) | 128K | $0.343 / $1.03 |
| Degraded | 97.17% | 98.56% | 98.24% | 98.15% | 3.08s | 28.9s | 16 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
- 99.66%◆ (best)
- 30d
- 99.45%
- p50
- 772ms◆ (best)
- p99
- 3.56s◆ (best)
- Throughput
- 67 tps◆ (best)
- Context
- 128K
- $/Mtok
- $0.343 / $1.03
streamlake - SiliconFlow97.17%Degraded24h 98.56%
- 7d
- 98.24%
- 30d
- 98.15%
- p50
- 3.08s
- p99
- 28.9s
- Throughput
- 16 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 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.
Throughput
Median tokens per second.