diff --git a/README.md b/README.md
index 2e1d2ea..e056060 100644
--- a/README.md
+++ b/README.md
@@ -81,8 +81,8 @@ _See [config.lua#L9](./lua/avante/config.lua) for the full config_
 
 ```lua
 {
-  ---@alias Provider "openai" | "claude" | "azure"
-  provider = "claude", -- "claude" or "openai" or "azure"
+  ---@alias Provider "openai" | "claude" | "azure" | "deepseek"
+  provider = "claude", -- "claude" or "openai" or "azure" or "deepseek"
   openai = {
     endpoint = "https://api.openai.com",
     model = "gpt-4o",
@@ -167,6 +167,12 @@ Given its early stage, `avante.nvim` currently supports the following basic func
 > ```sh
 > export AZURE_OPENAI_API_KEY=your-api-key
 > ```
+>
+> For DeepSeek
+>
+> ```sh
+> export DEEPSEEK_API_KEY=you-api-key
+> ```
 
 1. Open a code file in Neovim.
 2. Use the `:AvanteAsk` command to query the AI about the code.
diff --git a/lua/avante/ai_bot.lua b/lua/avante/ai_bot.lua
index 5e33f43..8ee3131 100644
--- a/lua/avante/ai_bot.lua
+++ b/lua/avante/ai_bot.lua
@@ -17,6 +17,7 @@ local E = {
     openai = "OPENAI_API_KEY",
     claude = "ANTHROPIC_API_KEY",
     azure = "AZURE_OPENAI_API_KEY",
+    deepseek = "DEEPSEEK_API_KEY",
   },
   _once = false,
 }
@@ -298,6 +299,23 @@ local function call_openai_api_stream(question, code_lang, code_content, selecte
       max_tokens = Config.azure.max_tokens,
       stream = true,
     }
+  elseif Config.provider == "deepseek" then
+    api_key = os.getenv(E.key("deepseek"))
+    url = Utils.trim_suffix(Config.deepseek.endpoint, "/") .. "/chat/completions"
+    headers = {
+      ["Content-Type"] = "application/json",
+      ["Authorization"] = "Bearer " .. api_key,
+    }
+    body = {
+      model = Config.deepseek.model,
+      messages = {
+        { role = "system", content = system_prompt },
+        { role = "user", content = user_prompt },
+      },
+      temperature = Config.deepseek.temperature,
+      max_tokens = Config.deepseek.max_tokens,
+      stream = true,
+    }
   else
     url = Utils.trim_suffix(Config.openai.endpoint, "/") .. "/v1/chat/completions"
     headers = {
@@ -364,7 +382,7 @@ end
 ---@param on_chunk fun(chunk: string): any
 ---@param on_complete fun(err: string|nil): any
 function M.call_ai_api_stream(question, code_lang, code_content, selected_content_content, on_chunk, on_complete)
-  if Config.provider == "openai" or Config.provider == "azure" then
+  if Config.provider == "openai" or Config.provider == "azure" or Config.provider == "deepseek" then
     call_openai_api_stream(question, code_lang, code_content, selected_content_content, on_chunk, on_complete)
   elseif Config.provider == "claude" then
     call_claude_api_stream(question, code_lang, code_content, selected_content_content, on_chunk, on_complete)
diff --git a/lua/avante/config.lua b/lua/avante/config.lua
index 95cb593..325dde9 100644
--- a/lua/avante/config.lua
+++ b/lua/avante/config.lua
@@ -6,8 +6,8 @@ local M = {}
 
 ---@class avante.Config
 M.defaults = {
-  ---@alias Provider "openai" | "claude" | "azure"
-  provider = "claude", -- "claude" or "openai" or "azure"
+  ---@alias Provider "openai" | "claude" | "azure" | "deepseek"
+  provider = "claude", -- "claude" or "openai" or "azure" or "deepseek"
   openai = {
     endpoint = "https://api.openai.com",
     model = "gpt-4o",
@@ -27,6 +27,12 @@ M.defaults = {
     temperature = 0,
     max_tokens = 4096,
   },
+  deepseek = {
+    endpoint = "https://api.deepseek.com",
+    model = "deepseek-coder",
+    temperature = 0,
+    max_tokens = 4096,
+  },
   behaviour = {
     auto_apply_diff_after_generation = false, -- Whether to automatically apply diff after LLM response.
   },