switch to mini and update readme

Author: truemagic-coder

README.md

@@ -35,7 +35,6 @@
 * `streamlit` apps
 * `tkinter` apps
 * `jupyter notebook`
-* Note: Not all runs will be successful with all models
 
 ## Install 
 
@@ -55,9 +54,13 @@
 ## Usage
 
 ### Providers
-* `openai`: `uvx nemo-agent --provider openai`
+* `openai`: `uvx nemo-agent` (default)
 * `gemini`: `uvx nemo-agent --provider gemini`
 
+### Supported Models 
+* `openai` is `gpt-4.1-mini` (default)
+* `gemini` is `gemini-2.5-flash-preview-04-17`
+
 ### Import Reference Documentation Into Prompt
 * Documentation files must be either: .md (Markdown) or .txt (Text) and be located in a folder
 * `uvx nemo-agent --docs example_folder`
@@ -97,24 +100,6 @@ You many want to skip tests especially if you are generating a UI application.
 
 * `uvx nemo-agent "create a fizzbuzz script" --tests False`
 
-## Models
-
-### Default Models 
-* `openai` is `gpt-4.1`
-* `gemini` is `gemini-2.5-flash-preview-04-17`
-
-### Select Models
-* `uvx nemo-agent "my-prompt" --provider openai --model o4-mini`
-
-### Supported Models
-
-#### OpenAI
-* Supports standard models: `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `gpt-4o`, and `gpt-4o-mini`
-* Supports reasoning models: `o4-mini`, `o3-mini`, `o1-mini`, and `o1`
-
-#### Gemini
-* Supports `gemini-2.5-flash-preview-04-17`, `gemini-2.5-pro-preview-03-25`
-
 ## Contributing
 Contributions to Nemo Agent are welcome! Please feel free to submit a Pull Request.
 

nemo_agent/main.py

@@ -23,22 +23,14 @@ def __init__(self, model):
             raise ValueError("OPENAI_API_KEY environment variable is not set")
         self.openai = OpenAI(api_key=self.api_key)
         self.token_count = 0
-
-        if model == "gpt-4.1" or model == "gpt-4.1-mini" or model == "gpt-4.1-nano":
+        if model == "gpt-4.1-mini":
             self.max_tokens = 32768
             self.max_output_tokens = 32768
-        elif model == "o1-mini":
-            self.max_tokens = 65536
-            self.max_output_tokens = 65536
-        elif model == "gpt-4o" or model == "gpt-4o-mini":
-            self.max_tokens = 16384
-            self.max_output_tokens = 16384
-        else:
-            # Default to other o-models
+        elif model == "o4-mini":
             self.max_tokens = 100000
             self.max_output_tokens = 100000
 
-        self.special_models = ["o1", "o1-mini", "o3-mini", "o4-mini"]
+        self.special_models = ["o4-mini"]
 
     def count_tokens(self, text):
         return len(tiktoken.encoding_for_model("gpt-4o").encode(text))
@@ -106,7 +98,7 @@ def generate(self, prompt):
 
 class GeminiAPI:
     def __init__(self, model):
-        if model == "gpt-4.1":
+        if model == "gpt-4.1-mini":
             model="gemini-2.5-flash-preview-04-17"
         self.model = model
         self.api_key = os.getenv("GEMINI_API_KEY")
@@ -172,7 +164,7 @@ class NemoAgent:
     WRITE_RETRY_DELAY = 1  # second
 
     def __init__(
-        self, task: str, model: str = "gpt-4.1", provider: str = "openai", tests: bool = True
+        self, task: str, model: str = "gpt-4.1-mini", provider: str = "openai", tests: bool = True
     ):
         self.task = task
         self.model = model
@@ -879,7 +871,7 @@ def main
     type=click.Path(exists=True),
     help="Path to a markdown file containing the task",
 )
-@click.option("--model", default="gpt-4.1", help="The model to use for Nemo Agent")
+@click.option("--model", default="gpt-4.1-mini", help="The model to use for Nemo Agent")
 @click.option(
     "--provider",
     default="openai",
@@ -913,7 +905,7 @@ def main
 def cli(
     task: str = None,
     file: str = None,
-    model: str = "gpt-4.1",
+    model: str = "gpt-4.1-mini",
     provider: str = "openai",
     zip: str = None,
     docs: str = None,