Skip to main content
DeepSeek/ DeepSeek

DeepSeek V4 Flash 0731

deepseek/deepseek/v4-flash-0731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.

Released
2026-07-31
Context window
1M
Max output
66K
Weights
Open weight

Modalities

Input
Text
Output
Text

Identity

Version
deepseek-v4-flash-0731

Resources

Providers

ProviderProvider model IDProtocolContextMax outputInputOutputCapabilitiesNotesPricingStreaming
OpenRouterdeepseek/deepseek-v4-flash-0731openai_chat1M66K
Text
Text
ReasoningNativeTool callNativeStructuredNativeTemperatureNativeOpen weightNative
Default reasoning: high, Hugging Face: deepseek-ai/DeepSeek-V4-Flash-0731
input $0.09/M · cache read $0.018/M
output $0.18/M
Yes
NanoGPTdeepseek/deepseek-v4-flash-0731openai_chat1M66K
Text
Text
ReasoningNativeTool callNativeStructuredNativeTemperatureNativeOpen weightNative
-
input $0.14/M · cache read $0.014/M
output $0.28/M
Yes
TensorXdeepseek/deepseek-v4-flash-0731openai_chat1M66K
Text
Text
ReasoningNativeTool callNativeStructuredNativeTemperatureNativeOpen weightNative
-
input $0.25/M · cache read $0.06/M
output $0.3/M
Yes
Kilo Gatewaydeepseek/deepseek-v4-flash-0731openai_chat1M66K
Text
Text
ReasoningNativeTool callNativeStructuredNativeTemperatureNativeOpen weightNative
-
input $0.14/M · cache read $0.028/M
output $0.28/M
Yes
Vercel AI Gatewaydeepseek/deepseek-v4-flash-0731openai_chat1M66K
Text
Text
ReasoningNativeTool callNativeStructuredNativeTemperatureNativeOpen weightNative
-
input $0.13/M · cache read $0.028/M
output $0.26/M
Yes
Ambientdeepseek/deepseek-v4-flash-0731openai_chat1M66K
Text
Text
ReasoningNativeTool callNativeStructuredNativeTemperatureNativeOpen weightNative
-
input $0.14/M · cache read $0.028/M
output $0.28/M · cache write $0/M
Yes

Capabilities

ReasoningNativeTool callNativeStructuredNativeTemperatureNativeOpen weightNative

FAQ