DeepSeek V3
deepseek/deepseek-chatInputOutput
Compare its 3 providersIncident RSSCompare with DeepSeek V4.1 Flash, DeepSeek V4 Flash 0731, DeepSeek V4 Pro 0813
CompareDeepSeek V3
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 99.82% | 95.88% | 95.61% | 94.76% | 929ms | 6.29s | 15 tps | 164K | $0.320 / $0.890 | |
StreamLakestreamlake | Healthy | 99.81% | 98.82% | 98.87% | 98.22% | 1.68s | 6.27s | 42 tps | 128K | $0.257 / $1.03 |
| No data | — | — | — | — | — | — | — | 64K | $0.400 / $1.30 |
- DeepInfra99.82%Healthy24h 95.88%
- 7d
- 95.61%
- 30d
- 94.76%
- p50
- 929ms
- p99
- 6.29s
- Throughput
- 15 tps
- Context
- 164K
- $/Mtok
- $0.320 / $0.890
deepinfra/fp4fp4 - StreamLake99.81%Healthy24h 98.82%
- 7d
- 98.87%
- 30d
- 98.22%
- p50
- 1.68s
- p99
- 6.27s
- Throughput
- 42 tps
- Context
- 128K
- $/Mtok
- $0.257 / $1.03
streamlake - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 64K
- $/Mtok
- $0.400 / $1.30
novita/fp8fp8
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint has no chartable data in this range.
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.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 3 endpoints · 46 days with data, 48 endpoint-days below 90%.