DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flashInputOutput
Compare its 42 providersIncident RSSCompare with DeepSeek V4 Flash 0731, DeepSeek V4 Flash 0423, DeepSeek V4 Flash Vision Exp
Showing only the open-inference/fp4 provider · show all 42
CompareDeepSeek V4.1 Flash
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Degraded | 98.81% | 90.01% | 97.75% | 98.37% | 4.84s | 21.0s | 28 tps | 1.0M | $0.003 / $2.64 |
- OpenInference98.81%Degraded24h 90.01%
- 7d
- 97.75%
- 30d
- 98.37%
- p50
- 4.84s
- p99
- 21.0s
- Throughput
- 28 tps
- Context
- 1.0M
- $/Mtok
- $0.003 / $2.64
open-inference/fp4fp4
Measured 2m 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.
Jul
Aug
Sep
Oct
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 40 endpoints · 26 days with data, 95 endpoint-days below 90%. Tables and charts above are filtered to open-inference/fp4.
Price changes
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.004 → $0.003 / $3.12 → $2.64cache read $0.004 → $0.0032026-10-06 03:01 UTC
- DeepSeek V4.1 FlashWaferwafer$0.060 → $0.070 / $1.20cache read $0.055 → $0.0602026-10-06 02:30 UTC
- DeepSeek V4.1 FlashWaferwafer$0.070 → $0.060 / $1.20cache read $0.060 → $0.0552026-10-06 01:50 UTC
- DeepSeek V4.1 FlashDeepSeekdeepseek$0.150 → $0.300 / $0.600 → $1.20cache read $0.003 → $0.0062026-10-06 01:05 UTC
- DeepSeek V4.1 FlashWaferwafer$0.075 → $0.070 / $1.202026-10-06 01:05 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.053 → $0.068 / $0.284cache read $0.008 → $0.0092026-10-06 00:55 UTC
- DeepSeek V4.1 FlashWaferwafer$0.090 → $0.075 / $1.202026-10-06 00:55 UTC
- DeepSeek V4.1 FlashAlibabaalibaba$0.150 → $0.300 / $0.600 → $1.20cache read $0.015 → $0.0302026-10-06 00:05 UTC
- DeepSeek V4.1 FlashWaferwafer$0.065 → $0.090 / $0.600 → $1.20cache read $0.030 → $0.0602026-10-05 23:20 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.023 → $0.053 / $0.2842026-10-05 23:10 UTC
- DeepSeek V4.1 FlashWaferwafer$0.065 / $0.600cache read $0.055 → $0.0302026-10-05 23:05 UTC
- DeepSeek V4.1 FlashWaferwafer$0.065 / $0.600cache read $0.030 → $0.0552026-10-05 22:50 UTC
- DeepSeek V4.1 FlashWaferwafer$0.065 / $0.600cache read $0.060 → $0.0302026-10-05 22:45 UTC
- DeepSeek V4.1 FlashWaferwafer$0.065 / $1.20 → $0.6002026-10-05 22:31 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.033 → $0.023 / $0.2842026-10-05 22:05 UTC
- DeepSeek V4.1 FlashWaferwafer$0.075 → $0.065 / $1.202026-10-05 22:05 UTC
- DeepSeek V4.1 FlashIonstreamionstream$0.119 → $0.139 / $1.182026-10-05 21:11 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.053 → $0.033 / $0.2842026-10-05 20:55 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.044 → $0.053 / $0.2842026-10-05 20:25 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.086 → $0.044 / $0.2842026-10-05 20:01 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.128 → $0.086 / $0.450 → $0.2842026-10-05 19:45 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.058 → $0.128 / $0.4502026-10-05 18:41 UTC
- DeepSeek V4.1 FlashInferenceNetinference-net$0.085 → $0.070 / $0.3002026-10-05 17:56 UTC
- DeepSeek V4.1 FlashInferenceNetinference-net$0.070 → $0.085 / $0.3002026-10-05 17:26 UTC
- DeepSeek V4.1 FlashAlibabaalibaba$0.300 → $0.150 / $1.20 → $0.600cache read $0.030 → $0.0152026-10-05 14:05 UTC
- DeepSeek V4.1 FlashIonstreamionstream$0.119 / $1.15 → $1.182026-10-05 12:16 UTC
- DeepSeek V4.1 FlashDeepSeekdeepseek$0.300 → $0.150 / $1.20 → $0.600cache read $0.006 → $0.0032026-10-05 10:06 UTC
- DeepSeek V4.1 FlashWaferwafer$0.090 → $0.075 / $1.202026-10-05 09:50 UTC
- DeepSeek V4.1 FlashWaferwafer$0.075 → $0.090 / $1.202026-10-05 09:45 UTC
- DeepSeek V4.1 FlashWaferwafer$0.090 → $0.075 / $1.202026-10-05 09:16 UTC