DeepSeek V4 Flash is an efficiency-optimized 284B-parameter Mixture-of-Experts model with 13B active parameters and a 1M-token context window. Tuned for fast inference and high-throughput workloads while maintaining strong reasoning and coding performance.
Modalities
In / out price
$0.138 / $0.275per 1M
Cached price
$0.028per 1M
Context
1M
Max output
33K
Providers
1 routeCompare providers by price, privacy, and speed.
| Private | $0.138 | $0.275 | $0.028 | 1M | 33K | — | — |
Privacy
2 / 4Private routing
Private tier
- Anonymous
- Private
- TEE
- E2EE
Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more
Features
7Streaming
Tool calling
Reasoning
JSON/schema
Web search
Code optimized
Prompt caching
Uptime
FAQ
Common questions about DeepSeek V4 Flash 0423.