Back to Models
deepseek logo
deepseek/deepseek-chat-v3-0324
Not Available

DeepSeek 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 on a variety of tasks.

3/24/2025
163,840 tokens
#117 Text (Creative Writing)

Specifications

Modalities

Input
text
Output
text

Supported Parameters

frequency_penalty
logit_bias
logprobs
max_tokens
min_p
presence_penalty
reasoning
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_logprobs
top_p

Max Output Tokens

65,536

Frequently asked questions

Is DeepSeek V3 0324 available on FastMetal?
Not at the moment. DeepSeek V4.1 Flash, from the same lab, is available on the FastMetal API today.
What is the context window of DeepSeek V3 0324?
163,840 tokens, shared between the prompt and the response.
How does DeepSeek V3 0324 rank?
#120 on the public arena's Japanese board (ELO 1,344). Ranks move as the leaderboard is updated.

Leaderboard

Text
OverallELO: 1,396
#151
JapaneseELO: 1,344
#120
ChineseELO: 1,416
#156
KoreanELO: 1,339
#134
EnglishELO: 1,409
#154
frenchELO: 1,416
#135
germanELO: 1,391
#123
spanishELO: 1,378
#155
russianELO: 1,400
#137
CodingELO: 1,429
#173
MathELO: 1,368
#181
Creative WritingELO: 1,389
#117
Instruction FollowingELO: 1,378
#163
Hard PromptsELO: 1,408
#162
Multi-TurnELO: 1,411
#133