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/M25.0 t/s396 ms
NovitanovitaAi128K16K$0.33/M$1.30/M23.3 t/s1344 ms
KlusterklusterAi164K164K$0.33/M$1.40/M20.3 t/s1208 ms
Lambdalambda164K164K$0.34/M$0.88/M31.7 t/s699 ms
Atomaatoma100K90K$0.35/M$1.25/M12.7 t/s1638 ms
Cent-MLcentMl33K164K$0.43/M$1.40/M7.5 t/s890 ms
InferenceNetinferenceNet128K33K$0.45/M$1.45/M38.0 t/s1274 ms
NebiusnebiusAiStudio164K-$0.50/M$1.50/M27.8 t/s768 ms
GMICloudgmiCloud131K-$0.74/M$0.90/M53.6 t/s810 ms
BaseTenbaseten164K131K$0.77/M$0.77/M105.6 t/s332 ms
Parasailparasail164K164K$0.79/M$1.15/M51.1 t/s751 ms
Fireworksfireworks164K-$0.90/M$0.90/M59.5 t/s725 ms
Hyperbolichyperbolic164K-$1.25/M$1.25/M26.6 t/s1660 ms
Togethertogether131K12K$1.25/M$1.25/M27.7 t/s1072 ms
SambaNovasambaNova33K7K$3.00/M$4.50/M211.1 t/s1915 ms
DeepSeekdeepSeek64K8K$0.27/M$1.10/M19.4 t/s4931 ms
Standard Pricing

Do Work. With AI.