Add default context for gemini 2 flash. 2x it for small, commercial models

Previously Gemini 2 flash and flash lite were using context window of
10K by default as no defaults were added for it.

Increase default context for small commercial models to 120K from 60K
as cheaper and faster than their pro models equivalents at 60K context.
This commit is contained in:
Debanjum
2025-04-04 16:14:20 +05:30
parent 47a081c7bd
commit 7f18bc0840

View File

@@ -52,12 +52,14 @@ except ImportError:
model_to_prompt_size = {
# OpenAI Models
"gpt-4o": 60000,
"gpt-4o-mini": 60000,
"gpt-4o-mini": 120000,
"o1": 20000,
"o1-mini": 60000,
"o3-mini": 60000,
# Google Models
"gemini-1.5-flash": 60000,
"gemini-2.0-flash": 120000,
"gemini-2.0-flash-lite": 120000,
"gemini-1.5-flash": 120000,
"gemini-1.5-pro": 60000,
# Anthropic Models
"claude-3-5-sonnet-20241022": 60000,