DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flashInputOutput
Compare its 62 providersIncident RSSCompare with DeepSeek V4.1 Flash 1017, DeepSeek V4 Flash 0731, DeepSeek V4 Flash 0423
Showing only the deepinfra/fp8 provider · show all 62
CompareDeepSeek V4.1 Flash
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 100% | 100% | 99.99% | 515ms | 3.02s | 111 tps | 1.0M | $0.140 / $0.420 |
- DeepInfra100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.99%
- p50
- 515ms
- p99
- 3.02s
- Throughput
- 111 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.420
deepinfra/fp8fp8
Measured 1m 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 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.
Aug
Sep
Oct
Nov
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 60 endpoints · 53 days with data, 260 endpoint-days below 90%. 2 more not shown. Tables and charts above are filtered to deepinfra/fp8.
Price changes
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.000 → $0.035 / $0.757 → $0.500cache read $0.000 → $0.0052026-11-01 20:30 UTC
- DeepSeek V4.1 FlashRelacerelace/fp4$0.000 → $0.035 / $0.757 → $0.500cache read $0.000 → $0.0052026-11-01 20:25 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.000 / $0.743 → $0.7572026-11-01 17:25 UTC
- DeepSeek V4.1 FlashRelacerelace/fp4$0.000 / $0.743 → $0.7572026-11-01 17:20 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.000 → $0.000 / $0.743cache read $0.000 → $0.0002026-11-01 17:20 UTC
- DeepSeek V4.1 FlashRelacerelace/fp4$0.000 → $0.000 / $0.743cache read $0.000 → $0.0002026-11-01 17:15 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.000 → $0.000 / $0.743cache read $0.000 → $0.0002026-11-01 17:05 UTC
- DeepSeek V4.1 FlashRelacerelace/fp4$0.000 → $0.000 / $0.743cache read $0.000 → $0.0002026-11-01 16:55 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.000 → $0.000 / $0.743cache read $0.000 → $0.0002026-11-01 16:45 UTC
- DeepSeek V4.1 FlashRelacerelace/fp4$0.000 → $0.000 / $0.743cache read $0.000 → $0.0002026-11-01 16:40 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.001 → $0.000 / $0.743cache read $0.001 → $0.0002026-11-01 16:30 UTC
- DeepSeek V4.1 FlashRelacerelace/fp4$0.001 → $0.000 / $0.743cache read $0.001 → $0.0002026-11-01 16:25 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.001 / $0.729 → $0.7432026-11-01 16:25 UTC
- DeepSeek V4.1 FlashRelacerelace/fp4$0.001 / $0.729 → $0.7432026-11-01 16:20 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.001 → $0.001 / $0.729cache read $0.001 → $0.0012026-11-01 16:15 UTC
- DeepSeek V4.1 FlashRelacerelace/fp4$0.001 → $0.001 / $0.729cache read $0.001 → $0.0012026-11-01 16:11 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.001 → $0.001 / $0.729cache read $0.001 → $0.0012026-11-01 16:00 UTC
- DeepSeek V4.1 FlashRelacerelace/fp4$0.001 → $0.001 / $0.729cache read $0.001 → $0.0012026-11-01 15:55 UTC
- DeepSeek V4.1 FlashBaidubaidu/fp8$0.045 → $0.300 / $0.179 → $1.20cache read $0.001 → $0.0062026-11-01 15:50 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.001 → $0.001 / $0.729cache read $0.001 → $0.0012026-11-01 15:45 UTC
- DeepSeek V4.1 FlashRelacerelace/fp4$0.001 → $0.001 / $0.729cache read $0.001 → $0.0012026-11-01 15:40 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.001 → $0.001 / $0.729cache read $0.001 → $0.0012026-11-01 15:25 UTC
- DeepSeek V4.1 FlashRelacerelace/fp4$0.001 → $0.001 / $0.729cache read $0.001 → $0.0012026-11-01 15:20 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.001 / $0.715 → $0.7292026-11-01 15:20 UTC
- DeepSeek V4.1 FlashRelacerelace/fp4$0.001 / $0.715 → $0.7292026-11-01 15:15 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.001 → $0.001 / $0.715cache read $0.001 → $0.0012026-11-01 15:10 UTC
- DeepSeek V4.1 FlashRelacerelace/fp4$0.001 → $0.001 / $0.715cache read $0.001 → $0.0012026-11-01 15:05 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.001 → $0.001 / $0.715cache read $0.001 → $0.0012026-11-01 15:05 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.001 → $0.001 / $0.715cache read $0.001 → $0.0012026-11-01 14:55 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.001 → $0.001 / $0.715cache read $0.001 → $0.0012026-11-01 14:50 UTC