DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flashInputOutput

Compare its 42 providers Incident RSSCompare with DeepSeek V4 Flash 0731, DeepSeek V4 Flash 0423, DeepSeek V4 Flash Vision Exp

Showing only the inference-net provider · show all 42

CompareDeepSeek V4.1 Flash

	State
InferenceNetinference-net	Healthy	99.99%	99.58%	99.33%	98.94%	930ms	6.26s	99 tps	1.0M	$0.070 / $0.300

InferenceNet99.99%
Healthy24h 99.58%
7d
99.33%
30d
98.94%
p50
930ms
p99
6.26s
Throughput
99 tps
Context
1.0M
$/Mtok
$0.070 / $0.300
inference-net

Measured 4m 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.

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, 97 endpoint-days below 90%. Tables and charts above are filtered to inference-net.

Price changes

DeepSeek V4.1 Flash OpenInferenceopen-inference/fp4$0.021 → $0.013 / $1.32cache read $0.016 → $0.0132026-10-06 09:55 UTC
DeepSeek V4.1 Flash Relacerelace$0.019 → $0.011 / $1.202026-10-06 09:50 UTC
DeepSeek V4.1 Flash OpenInferenceopen-inference/fp4$0.029 → $0.021 / $1.322026-10-06 09:46 UTC
DeepSeek V4.1 Flash Relacerelace$0.027 → $0.019 / $1.202026-10-06 09:41 UTC
DeepSeek V4.1 Flash OpenInferenceopen-inference/fp4$0.037 → $0.029 / $1.322026-10-06 09:35 UTC
DeepSeek V4.1 Flash Relacerelace$0.033 → $0.027 / $1.202026-10-06 09:31 UTC
DeepSeek V4.1 Flash OpenInferenceopen-inference/fp4$0.043 → $0.037 / $1.322026-10-06 09:26 UTC
DeepSeek V4.1 Flash Relacerelace$0.040 → $0.033 / $1.202026-10-06 09:20 UTC
DeepSeek V4.1 Flash OpenInferenceopen-inference/fp4$0.050 → $0.043 / $1.322026-10-06 09:16 UTC
DeepSeek V4.1 Flash Relacerelace$0.045 → $0.040 / $1.202026-10-06 09:06 UTC
DeepSeek V4.1 Flash OpenInferenceopen-inference/fp4$0.055 → $0.050 / $1.322026-10-06 08:55 UTC
DeepSeek V4.1 Flash Rekareka$0.200 / $2.00cache read $0.006 → $0.0102026-10-06 08:55 UTC
DeepSeek V4.1 Flash Relacerelace$0.050 → $0.045 / $1.202026-10-06 08:50 UTC
DeepSeek V4.1 Flash OpenInferenceopen-inference/fp4$0.003 → $0.055 / $3.30 → $1.32cache read $0.003 → $0.0162026-10-06 08:46 UTC
DeepSeek V4.1 Flash Relacerelace$0.003 → $0.050 / $3.00 → $1.20cache read $0.003 → $0.0152026-10-06 08:40 UTC
DeepSeek V4.1 Flash Novitanovita/fp8$0.240 → $0.210 / $0.960 → $0.840cache read $0.005 → $0.0042026-10-06 08:31 UTC
DeepSeek V4.1 Flash OpenInferenceopen-inference/fp4$0.003 / $1.32 → $3.302026-10-06 08:20 UTC
DeepSeek V4.1 Flash Relacerelace$0.003 / $1.20 → $3.002026-10-06 08:16 UTC
DeepSeek V4.1 Flash Rekareka$0.300 → $0.200 / $1.20 → $2.002026-10-06 08:06 UTC
DeepSeek V4.1 Flash Waferwafer$0.070 → $0.060 / $1.20cache read $0.060 → $0.0552026-10-06 08:01 UTC
DeepSeek V4.1 Flash Waferwafer$0.060 → $0.070 / $1.20cache read $0.055 → $0.0602026-10-06 07:50 UTC
DeepSeek V4.1 Flash Rekareka$0.141 → $0.300 / $0.564 → $1.20cache read $0.014 → $0.0062026-10-06 07:50 UTC
DeepSeek V4.1 Flash Ionstreamionstream$0.139 / $1.18 → $1.152026-10-06 07:40 UTC
DeepSeek V4.1 Flash OpenInferenceopen-inference/fp4$0.003 / $2.64 → $1.322026-10-06 07:31 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.098 / $0.284 → $0.3902026-10-06 07:25 UTC
DeepSeek V4.1 Flash Relacerelace$0.003 / $2.40 → $1.202026-10-06 07:25 UTC
DeepSeek V4.1 Flash Morphmorph/fp8$0.068 → $0.098 / $0.2842026-10-06 07:11 UTC
DeepSeek V4.1 Flash InferenceNetinference-net$0.070 / $0.400 → $0.3002026-10-06 06:41 UTC
DeepSeek V4.1 Flash DeepSeekdeepseek$0.150 → $0.300 / $0.600 → $1.20cache read $0.003 → $0.0062026-10-06 06:05 UTC
DeepSeek V4.1 Flash InferenceNetinference-net$0.070 / $0.300 → $0.4002026-10-06 05:10 UTC