DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flashInputOutput
Compare its 23 providersIncident RSSCompare with DeepSeek V4 Flash 0731, DeepSeek V4 Flash 0423, DeepSeek V4 Flash Vision Exp
CompareDeepSeek V4.1 Flash
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.89% | 99.78% | 99.78% | 1.54s | 20.0s | 91 tps | 1.0M | $0.150 / $0.600 |
| Healthy | 100% | 99.53% | 99.87% | 99.87% | 453ms | 4.74s | 62 tps | 1.0M | $0.300 / $1.20 | |
DeepSeekdeepseek | Healthy | 100% | 99.99% | 98.19% | 98.19% | 806ms | 3.37s | 95 tps | 1.0M | $0.150 / $0.600 |
| Healthy | 100% | 99.71% | 98.05% | 98.05% | 2.98s | 11.6s | 98 tps | 1.0M | $0.285 / $1.14 | |
| Healthy | 100% | 99.16% | 93.53% | 93.53% | 1.66s | 10.4s | 24 tps | 1.0M | $0.210 / $0.840 | |
| Healthy | 100% | 99.97% | 98.68% | 98.68% | 1.70s | 14.2s | 124 tps | 1.0M | $0.300 / $1.20 | |
| Healthy | 100% | 99.96% | 96.17% | 96.17% | 1.65s | 16.7s | 96 tps | 1.0M | $0.300 / $1.20 | |
| Healthy | 100% | 99.11% | 98.76% | 98.76% | 1.07s | 18.0s | 96 tps | 1.0M | $0.375 / $1.50 | |
Waferwafer | Healthy | 100% | 99.96% | 99.20% | 99.20% | 607ms | 4.42s | 119 tps | 1.0M | $0.300 / $1.20 |
Fireworksfireworks | Healthy | 99.89% | 99.76% | 99.15% | 99.15% | 1.23s | 13.0s | 70 tps | 1.0M | $0.220 / $0.660 |
| Healthy | 99.77% | 99.90% | 99.80% | 99.80% | 1.68s | 30.3s | 81 tps | 1.0M | $0.300 / $1.20 | |
| Healthy | 99.76% | 99.14% | 98.40% | 98.40% | 2.63s | 18.6s | 31 tps | 1.0M | $0.150 / $0.600 | |
Phalaphala | Healthy | 99.70% | 99.75% | 96.67% | 96.67% | 1.89s | 6.54s | 101 tps | 1.0M | $0.345 / $1.38 |
| Healthy | 99.31% | 99.47% | 95.53% | 95.53% | 1.71s | 21.8s | 36 tps | 1.0M | $0.200 / $0.600 | |
Togethertogether | Healthy | 99.15% | 99.83% | 97.93% | 97.93% | 475ms | 21.1s | 156 tps | 1.0M | $0.300 / $1.20 |
| Healthy | 99.01% | 97.68% | 96.78% | 96.78% | 833ms | 12.0s | 100 tps | 1.0M | $0.300 / $1.20 | |
Modalmodal | Healthy | 97.42% | 98.96% | 97.61% | 97.61% | 867ms | 17.6s | 155 tps | 1.0M | $0.300 / $1.20 |
DigitalOceandigitalocean | Healthy | 97.39% | 96.66% | 95.55% | 95.55% | 1.10s | 11.3s | 18 tps | 1.0M | $0.300 / $1.20 |
Makoramakora | Healthy | 95.83% | 96.38% | 96.48% | 96.48% | 892ms | 33.4s | 125 tps | 1.0M | $0.300 / $1.20 |
| No data | — | — | 96.52% | 96.52% | — | — | — | 262K | $0.285 / $1.14 | |
| No data | — | — | 90.32% | 90.32% | — | — | — | 1.0M | $0.225 / $0.900 | |
| No data | — | — | — | — | — | — | — | 1.0M | $0.300 / $1.20 | |
| No data | — | — | 87.31% | 87.31% | — | — | — | 262K | $0.290 / $1.16 |
- Alibaba100%Healthy24h 99.89%
- 7d
- 99.78%
- 30d
- 99.78%
- p50
- 1.54s
- p99
- 20.0s
- Throughput
- 91 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.600
alibaba - BaseTen100%Healthy24h 99.53%
- 7d
- 99.87%
- 30d
- 99.87%
- p50
- 453ms
- p99
- 4.74s
- Throughput
- 62 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
baseten/fp8fp8 - DeepSeek100%Healthy24h 99.99%
- 7d
- 98.19%
- 30d
- 98.19%
- p50
- 806ms
- p99
- 3.37s
- Throughput
- 95 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.600
deepseek - GMICloud100%Healthy24h 99.71%
- 7d
- 98.05%
- 30d
- 98.05%
- p50
- 2.98s
- p99
- 11.6s
- Throughput
- 98 tps
- Context
- 1.0M
- $/Mtok
- $0.285 / $1.14
gmicloud/fp8fp8 - Morph100%Healthy24h 99.16%
- 7d
- 93.53%
- 30d
- 93.53%
- p50
- 1.66s
- p99
- 10.4s
- Throughput
- 24 tps
- Context
- 1.0M
- $/Mtok
- $0.210 / $0.840
morph/fp8fp8 - Novita100%Healthy24h 99.97%
- 7d
- 98.68%
- 30d
- 98.68%
- p50
- 1.70s
- p99
- 14.2s
- Throughput
- 124 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
novita/fp8fp8 - SiliconFlow100%Healthy24h 99.96%
- 7d
- 96.17%
- 30d
- 96.17%
- p50
- 1.65s
- p99
- 16.7s
- Throughput
- 96 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
siliconflow/fp8fp8 - Venice100%Healthy24h 99.11%
- 7d
- 98.76%
- 30d
- 98.76%
- p50
- 1.07s
- p99
- 18.0s
- Throughput
- 96 tps
- Context
- 1.0M
- $/Mtok
- $0.375 / $1.50
venice/fp8fp8 - Wafer100%Healthy24h 99.96%
- 7d
- 99.20%
- 30d
- 99.20%
- p50
- 607ms
- p99
- 4.42s
- Throughput
- 119 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
wafer - Fireworks99.89%Healthy24h 99.76%
- 7d
- 99.15%
- 30d
- 99.15%
- p50
- 1.23s
- p99
- 13.0s
- Throughput
- 70 tps
- Context
- 1.0M
- $/Mtok
- $0.220 / $0.660
fireworks - AtlasCloud99.77%Healthy24h 99.90%
- 7d
- 99.80%
- 30d
- 99.80%
- p50
- 1.68s
- p99
- 30.3s
- Throughput
- 81 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
atlas-cloud/fp8fp8 - Relace99.76%Healthy24h 99.14%
- 7d
- 98.40%
- 30d
- 98.40%
- p50
- 2.63s
- p99
- 18.6s
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.600
relace/fp4fp4 - Phala99.70%Healthy24h 99.75%
- 7d
- 96.67%
- 30d
- 96.67%
- p50
- 1.89s
- p99
- 6.54s
- Throughput
- 101 tps
- Context
- 1.0M
- $/Mtok
- $0.345 / $1.38
phala - DeepInfra99.31%Healthy24h 99.47%
- 7d
- 95.53%
- 30d
- 95.53%
- p50
- 1.71s
- p99
- 21.8s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.600
deepinfra/fp8fp8 - Together99.15%Healthy24h 99.83%
- 7d
- 97.93%
- 30d
- 97.93%
- p50
- 475ms
- p99
- 21.1s
- Throughput
- 156 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
together - Parasail99.01%Healthy24h 97.68%
- 7d
- 96.78%
- 30d
- 96.78%
- p50
- 833ms
- p99
- 12.0s
- Throughput
- 100 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
parasail/fp8fp8 - Modal97.42%Healthy24h 98.96%
- 7d
- 97.61%
- 30d
- 97.61%
- p50
- 867ms
- p99
- 17.6s
- Throughput
- 155 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
modal - DigitalOcean97.39%Healthy24h 96.66%
- 7d
- 95.55%
- 30d
- 95.55%
- p50
- 1.10s
- p99
- 11.3s
- Throughput
- 18 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
digitalocean - Makora95.83%Healthy24h 96.38%
- 7d
- 96.48%
- 30d
- 96.48%
- p50
- 892ms
- p99
- 33.4s
- Throughput
- 125 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
makora - No data24h —
- 7d
- 96.52%
- 30d
- 96.52%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.285 / $1.14
io-net/fp8fp8 - Krea—No data24h —
- 7d
- 90.32%
- 30d
- 90.32%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.225 / $0.900
krea/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.300 / $1.20
nebius/fp8fp8 - Reka—No data24h —
- 7d
- 87.31%
- 30d
- 87.31%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.290 / $1.16
reka/fp4fp4
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
2 endpoints have 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 · 23 endpoints · 7 days with data, 31 endpoint-days below 90%.
Price changes
- DeepSeek V4.1 FlashMorphmorph/fp8$0.150 → $0.210 / $0.600 → $0.840cache read $0.004 → $0.0062026-09-17 20:30 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.180 → $0.150 / $0.720 → $0.600cache read $0.005 → $0.0042026-09-17 19:20 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.195 → $0.180 / $0.780 → $0.720cache read $0.006 → $0.0052026-09-17 18:50 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.240 → $0.195 / $0.960 → $0.780cache read $0.007 → $0.0062026-09-17 17:20 UTC
- DeepSeek V4.1 FlashAlibabaalibaba$0.300 → $0.150 / $1.20 → $0.600cache read $0.030 → $0.0152026-09-17 14:05 UTC
- DeepSeek V4.1 FlashDeepSeekdeepseek$0.300 → $0.150 / $1.20 → $0.600cache read $0.006 → $0.0032026-09-17 10:05 UTC
- DeepSeek V4.1 FlashDeepSeekdeepseek$0.150 → $0.300 / $0.600 → $1.20cache read $0.003 → $0.0062026-09-17 06:05 UTC
- DeepSeek V4.1 FlashDeepSeekdeepseek$0.300 → $0.150 / $1.20 → $0.600cache read $0.006 → $0.0032026-09-17 04:06 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.180 → $0.240 / $0.720 → $0.960cache read $0.005 → $0.0072026-09-17 02:41 UTC
- DeepSeek V4.1 FlashDeepSeekdeepseek$0.150 → $0.300 / $0.600 → $1.20cache read $0.003 → $0.0062026-09-17 01:06 UTC
- DeepSeek V4.1 FlashAlibabaalibaba$0.150 → $0.300 / $0.600 → $1.20cache read $0.015 → $0.0302026-09-17 00:06 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.210 → $0.180 / $0.840 → $0.720cache read $0.006 → $0.0052026-09-16 22:51 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.180 → $0.210 / $0.720 → $0.840cache read $0.005 → $0.0062026-09-16 21:11 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.270 → $0.180 / $1.08 → $0.720cache read $0.008 → $0.0052026-09-16 20:01 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.255 → $0.270 / $1.02 → $1.08cache read $0.008 → $0.0082026-09-16 18:41 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.240 → $0.255 / $0.960 → $1.02cache read $0.007 → $0.0082026-09-16 17:21 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.225 → $0.240 / $0.900 → $0.960cache read $0.007 → $0.0072026-09-16 16:31 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.210 → $0.225 / $0.840 → $0.900cache read $0.006 → $0.0072026-09-16 16:01 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.195 → $0.210 / $0.780 → $0.840cache read $0.006 → $0.0062026-09-16 15:41 UTC
- DeepSeek V4.1 FlashAlibabaalibaba$0.300 → $0.150 / $1.20 → $0.600cache read $0.030 → $0.0152026-09-16 14:06 UTC
- DeepSeek V4.1 FlashDeepSeekdeepseek$0.300 → $0.150 / $1.20 → $0.600cache read $0.006 → $0.0032026-09-16 10:05 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.240 → $0.195 / $0.960 → $0.780cache read $0.007 → $0.0062026-09-16 08:30 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.255 → $0.240 / $1.02 → $0.960cache read $0.025 → $0.0072026-09-16 07:50 UTC
- DeepSeek V4.1 FlashGMICloudgmicloud/fp8$0.210 → $0.285 / $0.840 → $1.14cache read $0.004 → $0.0062026-09-16 07:40 UTC
- DeepSeek V4.1 FlashKreakrea/fp8$0.225 / $0.900cache read — → $0.0062026-09-16 06:55 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.270 → $0.255 / $1.08 → $1.02cache read $0.027 → $0.0252026-09-16 06:35 UTC
- DeepSeek V4.1 FlashDeepSeekdeepseek$0.150 → $0.300 / $0.600 → $1.20cache read $0.003 → $0.0062026-09-16 06:05 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.180 → $0.270 / $0.720 → $1.08cache read $0.018 → $0.0272026-09-16 05:35 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.240 → $0.180 / $0.960 → $0.720cache read $0.024 → $0.0182026-09-16 04:20 UTC
- DeepSeek V4.1 FlashDeepSeekdeepseek$0.300 → $0.150 / $1.20 → $0.600cache read $0.006 → $0.0032026-09-16 04:05 UTC