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 / $0.90per 1M
Cached price
$0.135per 1M
Context
164K
Max output
16K
Providers
1 routeCompare providers by price, privacy, and speed.
| Private | $0.24 | $0.90 | $0.135 | 164K | 16K | — | — |
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
3Streaming
Tool calling
Prompt caching
Uptime
FAQ
Common questions about DeepSeek V3 0324.