DeepSeek V4 Flash 0423
deepseek/deepseek-v4-flash
- context
- 1.05M
- modalities
- text → text
- capabilities
- Tool use, Reasoning, Structured output, Long context, Low cost
Overview
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...
Providers
- AlibabaView Alibaba
- AtlasCloudView AtlasCloud
- AzureView Azure
- BaiduView Baidu
- CloudflareView Cloudflare
- DeepInfraView DeepInfra
- DigitalOceanView DigitalOcean
- GMICloudView GMICloud
- Mancer 2View Mancer 2
- NextBitView NextBit
- NovitaView Novita
- OpenInferenceView OpenInference
- ParasailView Parasail
- RelaceView Relace
- SiliconFlowView SiliconFlow
- StreamLakeView StreamLake
- VeniceView Venice
- WaferView Wafer
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| Alibaba | $0.15 | $0.30 |
| AtlasCloud | $0.14 | $0.28 |
| Azure | $0.21 | $0.56 |
| Baidu | $0.14 | $0.28 |
| Cloudflare | $0.44 | $1.32 |
| DeepInfra | $0.09 | $0.18 |
| DigitalOcean | $0.098 | $0.196 |
| GMICloud | $0.091 | $0.182 |
| Mancer 2 | $0.19 | $0.50 |
| NextBit | $0.15 | $0.30 |
| Novita | $0.14 | $0.28 |
| OpenInferenceopen-inference/fp4 · fp4 | $0.045 | $1.152 |
| OpenInferenceopen-inference/fp8 · fp8 | $0.0002 | $1.60 |
| Parasail | $0.14 | $0.28 |
| Relace | $0.05 | $1.28 |
| SiliconFlow | $0.13 | $0.28 |
| StreamLake | $0.0826 | $0.1652 |
| Venice | $0.0966 | $0.1925 |
| Wafer | $0.37 | $0.17 |
Alibaba
- input / 1M
- $0.15
- output / 1M
- $0.30
AtlasCloud
- input / 1M
- $0.14
- output / 1M
- $0.28
Azure
- input / 1M
- $0.21
- output / 1M
- $0.56
Baidu
- input / 1M
- $0.14
- output / 1M
- $0.28
Cloudflare
- input / 1M
- $0.44
- output / 1M
- $1.32
DeepInfra
- input / 1M
- $0.09
- output / 1M
- $0.18
DigitalOcean
- input / 1M
- $0.098
- output / 1M
- $0.196
GMICloud
- input / 1M
- $0.091
- output / 1M
- $0.182
Mancer 2
- input / 1M
- $0.19
- output / 1M
- $0.50
NextBit
- input / 1M
- $0.15
- output / 1M
- $0.30
Novita
- input / 1M
- $0.14
- output / 1M
- $0.28
OpenInference
open-inference/fp4 · fp4
- input / 1M
- $0.045
- output / 1M
- $1.152
OpenInference
open-inference/fp8 · fp8
- input / 1M
- $0.0002
- output / 1M
- $1.60
Parasail
- input / 1M
- $0.14
- output / 1M
- $0.28
Relace
- input / 1M
- $0.05
- output / 1M
- $1.28
SiliconFlow
- input / 1M
- $0.13
- output / 1M
- $0.28
StreamLake
- input / 1M
- $0.0826
- output / 1M
- $0.1652
Venice
- input / 1M
- $0.0966
- output / 1M
- $0.1925
Wafer
- input / 1M
- $0.37
- output / 1M
- $0.17
Use this model
through Nautili
Route requests to DeepSeek V4 Flash 0423 through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.