DeepSeek: DeepSeek V3 0324

deepseek/deepseek-chat-v3-0324

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...

Prompt $/1M

$0.270

Completion $/1M

$1.120

Context

163,840 tok

Best provider

73 tok/s · SambaNova

Specs

Model id: deepseek/deepseek-chat-v3-0324
Display name: DeepSeek: DeepSeek V3 0324
Modality: text->text
Tokenizer: DeepSeek
Instruct type: —
Context length: 163,840
Max completion: 65,536
Prompt $/1M: $0.270
Completion $/1M: $1.120
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionno
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
SambaNovafastest	73	790 ms	1,101 ms
BaseTenfastest	72	698 ms	800 ms
ModelRunfastest	30	1,514 ms	1,969 ms
Novitafastest	29	1,244 ms	1,385 ms
AtlasCloud	27	1,152 ms	1,386 ms
DeepInfra	25	742 ms	1,197 ms
GMICloud	19	2,763 ms	3,050 ms
SiliconFlow	15	1,535 ms	1,882 ms
Chutes	3	1,198 ms	1,438 ms