fix: update gemini max_tokens and use 2.0 model (#1767)

docs ref for max output tokens: https://ai.google.dev/gemini-api/docs/models#gemini-2.0-flash Token limits[*] Input token limit 1,048,576 Output token limit 8,192
2025-03-30 01:53:41 -03:00
parent 76fd19812e
commit 484e473a5a
1 changed files with 2 additions and 2 deletions
--- a/lua/avante/config.lua
+++ b/lua/avante/config.lua
@@ -237,10 +237,10 @@ M._defaults = {
  ---@type AvanteSupportedProvider
  gemini = {
    endpoint = "https://generativelanguage.googleapis.com/v1beta/models",
-    model = "gemini-1.5-flash-latest",
+    model = "gemini-2.0-flash",
    timeout = 30000, -- Timeout in milliseconds
    temperature = 0,
-    max_tokens = 20480,
+    max_tokens = 8192,
  },
  ---@type AvanteSupportedProvider
  vertex = {