---
id: "deepseek/deepseek-chat-v3-0324"
also: ["deepseek/deepseek-chat-v3-0324", "deepseek-ai/DeepSeek-V3-0324", "hf/deepseek-ai/DeepSeek-V3-0324"]
cheapest_list_usd_per_m: "0.24 in, 0.9 out, at deepinfra/fp4 on openrouter"
cheapest_effective_usd_per_m: "0.2182 in, 0.8963 out, at deepinfra/fp4 on openrouter"
context: 163840
max_output: 115200
input: ["text"]
output: ["text"]
released: "2025-03-24"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 8
gateways: "openrouter (5), hf (3)"
no_training: 5
trains: 0
retains_prompts: 1
coding: 21.2000
agentic: 0.8000
---
# DeepSeek: 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...