DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2.
Modalities
In / out price
$0.32 / $0.89per 1M
Context
164K
Max output
16K
Updated
Oct 22, 2026
Providers
1 routeCompare providers by price, privacy, and speed.
| Private | $0.32 | $0.89 | — | 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
2Streaming
Tool calling
Uptime
FAQ
Common questions about DeepSeek V3.