anonrouter
Sign up
DeepSeek

DeepSeek V4 Flash (Preview)

deepseek
Chat

DeepSeek V4 Flash (Preview) is the April 2026 preview release of DeepSeek's efficiency-focused Mixture-of-Experts model, with 284B total and 13B active parameters and a 1M-token context window. It offers a non-thinking mode and two thinking levels (high and max) for fast reasoning and coding workloads.

Modalities

In / out price

$0.09 / $0.18per 1M

Cached price

$0.018per 1M

Context

1M

Max output

66K

Providers

4 routes

Compare providers by price, privacy, and speed.

DeepInfraDeepInfra
Private$0.09$0.18$0.0181M66K——
Relace
Private$0.0277$1.28$0.02771M131K——
Wafer
Private$0.14$0.28—1M131K——
VeniceVenice
Anonymous$0.138$0.275$0.0281M33K——

Privacy

2 / 4

Private routing

Private tier

  1. Anonymous
  2. Private
  3. TEE
  4. 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

4
Streaming
Tool calling
Reasoning
Prompt caching

Uptime

FAQ

Common questions about DeepSeek V4 Flash (Preview).