DeepSeek

DeepSeek V4 Flash

deepseek
Chat

DeepSeek V4 Flash is an efficiency-focused MoE model with 284B total parameters (13B active) and a 1M-token context window. It's tuned for fast inference and high-throughput use cases while still holding up on reasoning and coding tasks.

Modalities

In / out price

$0.09 / $0.18

per 1M

Cached price

$0.018

per 1M

Context

1M

Max output

66K

Released

Providers

3 routes

The same model can have different pricing and privacy guarantees depending on who serves it. The model's headline privacy uses the strongest available route below. Discovered routes awaiting approval remain listed as not live.

ProviderPrivacyInput / 1MOutput / 1MCache read / 1MContextMax outputUptimeLatencyThroughput
VeniceVeniceNot live
E2EE$0.182$0.373$0.0381M8K
TEE$0.30$0.701M33K
DeepInfraDeepInfra
Private$0.09$0.18$0.0181M66K

Privacy

4 / 4

End-to-end encrypted routing

E2EE tier

  1. Anonymous
  2. Private
  3. TEE
  4. E2EE

Your client encrypts the prompt before it leaves your environment. E2EE includes TEE isolation; only the verified enclave can decrypt the request. Learn more

Features

4
Streaming
Tool calling
Reasoning
Prompt caching

Uptime

DeepSeek V4 Flash — AnonRouter Models