Back

DeepSeek: DeepSeek V3 0324 (free)

DeepSeek
Input: text
Output: text
Released: Mar 24, 2025Updated: Mar 28, 2025

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 model and performs really well on a variety of tasks.

163,840 Token Context

Process and analyze large documents and conversations.

Advanced Coding

Improved capabilities in front-end development and full-stack updates.

Agentic Workflows

Autonomously navigate multi-step processes with improved reliability.

Available On

ProviderModel IDContextMax OutputInput CostOutput CostThroughputLatency
DeepInfradeepInfra164K-$0.30/M$0.88/M17.8 t/s532 ms
NovitanovitaAi128K16K$0.33/M$1.30/M23.8 t/s1251 ms
KlusterklusterAi164K164K$0.33/M$1.40/M18.7 t/s1403 ms
Lambdalambda164K164K$0.34/M$0.88/M31.2 t/s738 ms
Cent-MLcentMl33K164K$0.43/M$1.40/M7.0 t/s898 ms
InferenceNetinferenceNet128K33K$0.45/M$1.45/M27.2 t/s1271 ms
NebiusnebiusAiStudio164K-$0.50/M$1.50/M26.1 t/s759 ms
GMICloudgmiCloud131K-$0.74/M$0.90/M58.2 t/s765 ms
BaseTenbaseten164K131K$0.77/M$0.77/M117.8 t/s367 ms
Parasailparasail164K164K$0.79/M$1.15/M81.3 t/s747 ms
Fireworksfireworks164K-$0.90/M$0.90/M57.1 t/s933 ms
Hyperbolichyperbolic164K-$1.25/M$1.25/M25.3 t/s1648 ms
Togethertogether131K12K$1.25/M$1.25/M26.5 t/s1144 ms
SambaNovasambaNova33K7K$3.00/M$4.50/M213.7 t/s1914 ms
DeepSeekdeepSeek64K8K$0.27/M$1.10/M19.4 t/s4688 ms
Standard Pricing

Do Work. With AI.