DeepSeek V3 0324
deepseek/deepseek-chat-v3-0324
Compare with DeepSeek V3, DeepSeek V3.1, DeepSeek V3.1 Terminus
CompareDeepSeek V3 0324
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Crusoecrusoe/bf16bf16 | Healthy | 100% | 99.96% | 408ms | 6.83s | 34 tps | 164K | $0.500 / $1.50 |
GMICloudgmicloud/fp8fp8 | Healthy | 100% | 98.65% | 2.83s | 8.27s | 24 tps | 164K | $0.290 / $1.14 |
Novitanovita/fp8fp8 | Healthy | 97.81% | 97.25% | 1.35s | 7.32s | 32 tps | 164K | $0.270 / $1.12 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 96.95% | 95.78% | 1.42s | 10.4s | 21 tps | 164K | $0.250 / $1.00 |
DeepInfradeepinfra/fp4fp4 | Down | — | 91.93% | 1.83s | 21.9s | 26 tps | 164K | $0.240 / $0.900 |
- Crusoe100%Healthy24h 99.96%
- p50
- 408ms
- p99
- 6.83s
- Throughput
- 34 tps
- Context
- 164K
- $/Mtok
- $0.500 / $1.50
crusoe/bf16bf16 - GMICloud100%Healthy24h 98.65%
- p50
- 2.83s
- p99
- 8.27s
- Throughput
- 24 tps
- Context
- 164K
- $/Mtok
- $0.290 / $1.14
gmicloud/fp8fp8 - Novita97.81%Healthy24h 97.25%
- p50
- 1.35s
- p99
- 7.32s
- Throughput
- 32 tps
- Context
- 164K
- $/Mtok
- $0.270 / $1.12
novita/fp8fp8 - SiliconFlow96.95%Healthy24h 95.78%
- p50
- 1.42s
- p99
- 10.4s
- Throughput
- 21 tps
- Context
- 164K
- $/Mtok
- $0.250 / $1.00
siliconflow/fp8fp8 - DeepInfra—Down24h 91.93%
- p50
- 1.83s
- p99
- 21.9s
- Throughput
- 26 tps
- Context
- 164K
- $/Mtok
- $0.240 / $0.900
deepinfra/fp4fp4
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.