DeepSeek V4 Flash 0423
- Input / output
- $0.0274 / $0.0549
- Providers
- 13
- Spread
- 3.4×
- 7 days
- −45.1%
- 30 days
- −46.4%
- Context
- 1M
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
BaiduCheapest fp8·−80% discount | $0.0274 | $0.0549 | $0.0343 | −61% | |||
| fp8·−50% discount | $0.07 | $0.14 | $0.0875 | ref | |||
DeepInfrafp8/flex fp8 | $0.072 | $0.144 | $0.09 | +2.9% | |||
| fp8 | $0.09 | $0.18 | $0.113 | +29% | |||
| fp8·−35% discount | $0.091 | $0.182 | $0.114 | +30% | |||
| −30% discount | $0.0966 | $0.193 | $0.121 | +38% | |||
| $0.105 | $0.21 | $0.131 | +50% | ||||
| mxfp4 | $0.12 | $0.17 | $0.133 | +51% | |||
| fp4 | $0.0275 | $0.45 | $0.133 | +52% | |||
| fp8 | $0.13 | $0.28 | $0.168 | +91% | |||
DeepInfrafp8/priority fp8 | $0.135 | $0.27 | $0.169 | +93% | |||
| fp4 | $0.14 | $0.28 | $0.175 | +100% | |||
| fp8 | $0.14 | $0.28 | $0.175 | +100% | |||
| fp8 | $0.15 | $0.50 | $0.238 | +171% | |||
Azureus | $0.21 | $0.56 | $0.298 | +240% |
- BaiduCheapest$0.0343$0.0274 in · $0.0549 out−61% vs ref1M ctx94.9% uptimefp8·−80% discount
- $0.0875$0.07 in · $0.14 outref vs ref1M ctx99.7% uptimefp8·−50% discount
- fp8/flex$0.09$0.072 in · $0.144 out+2.9% vs ref1M ctx100% uptimefp8
- $0.113$0.09 in · $0.18 out+29% vs ref1M ctx100% uptimefp8
- $0.114$0.091 in · $0.182 out+30% vs ref1M ctx99.7% uptimefp8·−35% discount
- $0.121$0.0966 in · $0.193 out+38% vs ref1M ctx100% uptime−30% discount
- $0.131$0.105 in · $0.21 out+50% vs ref1M ctx92.3% uptime
- $0.133$0.12 in · $0.17 out+51% vs ref1M ctx100% uptimemxfp4
- $0.133$0.0275 in · $0.45 out+52% vs ref1M ctx99.9% uptimefp4
- $0.168$0.13 in · $0.28 out+91% vs ref1M ctx98.6% uptimefp8
- fp8/priority$0.169$0.135 in · $0.27 out+93% vs ref1M ctx100% uptimefp8
- $0.175$0.14 in · $0.28 out+100% vs ref1M ctx99.2% uptimefp4
- $0.175$0.14 in · $0.28 out+100% vs ref1M ctx99.7% uptimefp8
- $0.238$0.15 in · $0.50 out+171% vs ref1M ctx100% uptimefp8
- us$0.298$0.21 in · $0.56 out+240% vs ref1M ctx99.5% uptime
Blended = (3 × input + output) / 4. Ref $0.0875 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
Other pricing
| Offered by | Cache read |
|---|---|
| Baidu | $0.00549 |
| StreamLake | $0.014 |
| DeepInfra (fp8/flex) | $0.0144 |
| DeepInfra | $0.018 |
| GMICloud | $0.0182 |
| Venice | $0.0196 |
| Fireworks | $0.021 |
| Wafer | $0.024 |
| Relace | $0.0275 |
| SiliconFlow, AtlasCloud | $0.028 |
| DeepInfra (fp8/priority) | $0.027 |
| Parasail | $0.07 |
| Mancer 2 | $0.075 |
| Azure (us) | $0.031 |
Changes
- PriceDiscount price,41%→50%+22.0%
- PriceCache read price,$0.0165→$0.014−15.3%
- PriceOutput price,$0.165→$0.14−15.3%
- PriceInput price,$0.0826→$0.07−15.3%
- PriceCache read price,$0.05→$0.0275−45.0%
- PriceInput price,$0.05→$0.0275−45.0%
- PriceDiscount price,—→80%—
- PriceCache read price,$0.028→$0.00549−80.4%
- PriceOutput price,$0.28→$0.0549−80.4%
- PriceInput price,$0.14→$0.0274−80.4%
- PriceDiscount price,64%→——
- PriceCache read price,$0.01→$0.028+180%
- PriceOutput price,$0.10→$0.28+180%
- PriceInput price,$0.05→$0.14+180%
- PriceDiscount price,50%→41%−18.0%
About
The cheapest provider for DeepSeek V4 Flash 0423 is Baidu at $0.0343 per 1M tokens (blended), charging $0.0274 per 1M input and $0.0549 per 1M output tokens. 13 providers serve it; the most expensive charges 3.4× the typical price. Its best price fell 46.4% over the last 30 days. Context window: 1M tokens. Prices tracked since Oct 3, 2026.
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
- Released
- Apr 24, 2026
- First tracked
- Oct 3, 2026
- Canonical slug
- deepseek/deepseek-v4-flash-20260423
- Weights
- deepseek-ai/DeepSeek-V4-Flash