DeepSeek V3 0324
deepseek/deepseek-chat-v3-0324
Compare with DeepSeek V4 Flash 0731, DeepSeek V4 Flash 0423, DeepSeek V4 Pro 0423
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Crusoecrusoe/bf16bf16 | Healthy | 100% | 99.95% | 407ms | 3.14s | 16 tps | 164K | $0.500 / $1.50 |
Novitanovita/fp8fp8 | Healthy | 97.64% | 97.07% | 1.38s | 5.76s | 31 tps | 164K | $0.270 / $1.12 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 95.17% | 96.10% | 1.46s | 9.62s | 7.0 tps | 164K | $0.250 / $1.00 |
DeepInfradeepinfra/fp4fp4 | Degraded | 95.07% | 91.66% | 792ms | 19.8s | 10 tps | 164K | $0.240 / $0.900 |
GMICloudgmicloud/fp8fp8 | No data | — | — | — | — | — | 164K | $0.290 / $1.14 |
- Crusoe100%Healthy24h 99.95%
- p50
- 407ms
- p99
- 3.14s
- Throughput
- 16 tps
- Context
- 164K
- $/Mtok
- $0.500 / $1.50
crusoe/bf16bf16 - Novita97.64%Healthy24h 97.07%
- p50
- 1.38s
- p99
- 5.76s
- Throughput
- 31 tps
- Context
- 164K
- $/Mtok
- $0.270 / $1.12
novita/fp8fp8 - SiliconFlow95.17%Healthy24h 96.10%
- p50
- 1.46s
- p99
- 9.62s
- Throughput
- 7.0 tps
- Context
- 164K
- $/Mtok
- $0.250 / $1.00
siliconflow/fp8fp8 - DeepInfra95.07%Degraded24h 91.66%
- p50
- 792ms
- p99
- 19.8s
- Throughput
- 10 tps
- Context
- 164K
- $/Mtok
- $0.240 / $0.900
deepinfra/fp4fp4 - GMICloud—No data24h —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 164K
- $/Mtok
- $0.290 / $1.14
gmicloud/fp8fp8
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is omitted from the charts.
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.