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

DeepSeek V3

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models. For model details, please visit [the DeepSeek-V3 repo](https://github.com/deepseek-ai/DeepSeek-V3) for more information, or see the [launch announcement](https://api-docs.deepseek.com/news/news1226).

12/26/2024
163,840 tokens
#151 Text (spanish)

Specifications

Modalities

Input
text
Output
text

Supported Parameters

frequency_penalty
max_tokens
min_p
presence_penalty
repetition_penalty
response_format
seed
stop
temperature
tool_choice
tools
top_k
top_p

Max Output Tokens

163,840

Frequently asked questions

Is DeepSeek V3 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?
163,840 tokens, shared between the prompt and the response.
How does DeepSeek V3 rank?
#160 on the public arena's Japanese board (ELO 1,287). Ranks move as the leaderboard is updated.

Leaderboard

Text
OverallELO: 1,358
#192
JapaneseELO: 1,287
#160
ChineseELO: 1,370
#201
KoreanELO: 1,283
#174
EnglishELO: 1,370
#205
frenchELO: 1,371
#172
germanELO: 1,352
#161
spanishELO: 1,381
#151
russianELO: 1,356
#184
CodingELO: 1,387
#209
MathELO: 1,310
#221
Creative WritingELO: 1,348
#165
Instruction FollowingELO: 1,343
#199
Hard PromptsELO: 1,350
#220
Multi-TurnELO: 1,374
#175