DeepSeek V3.1 Terminus
deepseek/deepseek-v3.1-terminus
Compare with DeepSeek V3.1, DeepSeek V3, DeepSeek V3.2
CompareDeepSeek V3.1 Terminus
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
AtlasCloudatlas-cloud/fp8fp8 | Healthy | 100% | 99.39% | 1.69s | 5.21s | 40 tps | 131K | $0.300 / $0.950 |
Novitanovita/fp8fp8 | Healthy | 100% | 99.97% | 2.08s | 10.4s | 22 tps | 131K | $0.270 / $1.00 |
StreamLakestreamlake | Healthy | 100% | 99.91% | 1.44s | 5.06s | 37 tps | 128K | $0.343 / $1.03 |
SiliconFlowsiliconflow/fp8fp8 | Degraded | 93.93% | 97.69% | 1.54s | 9.85s | 17 tps | 164K | $0.270 / $1.00 |
- AtlasCloud100%Healthy24h 99.39%
- p50
- 1.69s
- p99
- 5.21s
- Throughput
- 40 tps
- Context
- 131K
- $/Mtok
- $0.300 / $0.950
atlas-cloud/fp8fp8 - Novita100%Healthy24h 99.97%
- p50
- 2.08s
- p99
- 10.4s
- Throughput
- 22 tps
- Context
- 131K
- $/Mtok
- $0.270 / $1.00
novita/fp8fp8 - StreamLake100%Healthy24h 99.91%
- p50
- 1.44s
- p99
- 5.06s
- Throughput
- 37 tps
- Context
- 128K
- $/Mtok
- $0.343 / $1.03
streamlake - SiliconFlow93.93%Degraded24h 97.69%
- p50
- 1.54s
- p99
- 9.85s
- Throughput
- 17 tps
- Context
- 164K
- $/Mtok
- $0.270 / $1.00
siliconflow/fp8fp8
Measured 52s 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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.