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 baseten/fast provider · show all 42
CompareDeepSeek V4.1 Flash
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| No data | — | — | 99.84% | 99.84% | — | — | — | 1.0M | $0.600 / $2.40 |
- No data24h —
- 7d
- 99.84%
- 30d
- 99.84%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.600 / $2.40
baseten/fastfp32
No recent measurement.
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, averaged over the hour.
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 · 24 days with data, 86 endpoint-days below 90%. Tables and charts above are filtered to baseten/fast.
Price changes
- DeepSeek V4.1 FlashInferenceNetinference-net$0.025 / $0.300cache read $0.016 → $0.0182026-10-04 21:16 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.059 → $0.058 / $0.506 → $0.5002026-10-04 17:36 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.060 → $0.059 / $0.510 → $0.5062026-10-04 17:21 UTC
- DeepSeek V4.1 FlashIonstreamionstream$0.100 / $1.15 → $1.182026-10-04 17:10 UTC
- DeepSeek V4.1 FlashMakoramakora/fp8$0.200 → $0.270 / $0.990 → $1.15cache read $0.006 → $0.0092026-10-04 16:51 UTC
- DeepSeek V4.1 FlashInferenceNetinference-net$0.025 / $0.300cache read $0.020 → $0.0162026-10-04 16:35 UTC
- DeepSeek V4.1 FlashInferenceNetinference-net$0.025 / $0.300cache read $0.016 → $0.0202026-10-04 15:26 UTC
- DeepSeek V4.1 FlashInferenceNetinference-net$0.020 → $0.025 / $0.350 → $0.300cache read $0.013 → $0.0162026-10-04 14:20 UTC
- DeepSeek V4.1 FlashAlibabaalibaba$0.300 → $0.150 / $1.20 → $0.600cache read $0.030 → $0.0152026-10-04 14:05 UTC
- DeepSeek V4.1 FlashInferenceNetinference-net$0.020 / $0.400 → $0.350cache read $0.010 → $0.0132026-10-04 11:11 UTC
- DeepSeek V4.1 FlashInferenceNetinference-net$0.020 / $0.450 → $0.4002026-10-04 10:01 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.090 → $0.060 / $0.5102026-10-04 08:50 UTC
- DeepSeek V4.1 FlashMorphmorph/fp8$0.026 → $0.090 / $0.377 → $0.5102026-10-04 07:55 UTC
- DeepSeek V4.1 FlashDekaLLMdekallm$0.120 / $0.400 → $2.402026-10-04 07:51 UTC
- DeepSeek V4.1 FlashInferenceNetinference-net$0.020 / $0.450cache read $0.005 → $0.0102026-10-04 07:31 UTC
- DeepSeek V4.1 FlashInferenceNetinference-net$0.020 / $0.450cache read $0.003 → $0.0052026-10-04 07:16 UTC
- DeepSeek V4.1 FlashRelacerelace$0.003 / $1.20 → $2.402026-10-04 05:50 UTC
- DeepSeek V4.1 FlashRelacerelace$0.003 / $2.40 → $1.202026-10-04 05:15 UTC
- DeepSeek V4.1 FlashInferenceNetinference-net$0.020 / $0.600 → $0.4502026-10-04 04:10 UTC
- DeepSeek V4.1 FlashInferenceNetinference-net$0.020 / $0.400 → $0.6002026-10-04 03:20 UTC
- DeepSeek V4.1 FlashAlibabaalibaba$0.150 → $0.300 / $0.600 → $1.20cache read $0.015 → $0.0302026-10-04 00:10 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.004 → $0.004 / $3.12cache read $0.004 → $0.0042026-10-03 23:20 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.004 → $0.004 / $3.12cache read $0.004 → $0.0042026-10-03 23:15 UTC
- DeepSeek V4.1 FlashRelacerelace$0.003 → $0.003 / $2.40cache read $0.003 → $0.0032026-10-03 23:15 UTC
- DeepSeek V4.1 FlashRelacerelace$0.003 → $0.003 / $2.40cache read $0.003 → $0.0032026-10-03 23:10 UTC
- DeepSeek V4.1 FlashOpenInferenceopen-inference/fp4$0.026 → $0.004 / $0.780 → $3.12cache read $0.013 → $0.0042026-10-03 22:25 UTC
- DeepSeek V4.1 FlashRelacerelace$0.020 → $0.003 / $0.600 → $2.40cache read $0.010 → $0.0032026-10-03 22:20 UTC
- DeepSeek V4.1 FlashInferenceNetinference-net$0.040 → $0.020 / $0.600 → $0.400cache read $0.020 → $0.0032026-10-03 20:40 UTC
- DeepSeek V4.1 FlashInferenceNetinference-net$0.025 → $0.040 / $0.400 → $0.600cache read $0.004 → $0.0202026-10-03 19:55 UTC
- DeepSeek V4.1 FlashInferenceNetinference-net$0.100 → $0.025 / $0.600 → $0.400cache read $0.020 → $0.0042026-10-03 18:45 UTC