DeepSeek

DeepSeek V3 0324

deepseek
Chat

DeepSeek-V3-0324, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token, an improved iteration over DeepSeek-V3.

DeepInfra returned engine_overloaded for repeated Chat Completions probes; this route is temporarily disabled pending a successful re-test.

Modalities

In / out price

$0.24 / $0.90

per 1M

Cached price

$0.135

per 1M

Context

164K

Max output

16K

Released

Providers

1 route

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
DeepInfraDeepInfra
Private$0.24$0.90$0.135164K16K

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

3
Streaming
Tool calling
Prompt caching

Uptime

DeepSeek V3 0324 — AnonRouter Models