Per-Task Model Selection
Configure different OpenAI models for different kinds of tasks. Use GPT-5.4 for long-form reasoning, o3-mini for quick replies, and a fine-tuned model for classification — all from WhatsApp.
Conversation example
Route fast replies to o3-mini, long reasoning to gpt-5.4, and classification to the fine-tuned classifier
Updating model routing config...
Model routing updated Reasoning (long): gpt-5.4 Fast reply (under 300 tokens): o3-mini Classification: ft:o3-mini:lunogen:classifier Embeddings: text-embedding-3-large Image generation: dall-e-3 Estimated cost impact: about -38% vs using gpt-5.4 for everything, based on last week's traffic mix. I'll rerun the benchmarks after 24 hours and report back.
More OpenAI use cases
Bring Your Own OpenAI Key for Reasoning
Connect your OpenAI API key and the LunoGen agent uses your account for all its reasoning calls. You keep billing control, access to your fine-tuned models, and your own rate limits.
Embeddings for Memory Recall
The agent uses OpenAI embeddings to remember things across conversations. Ask it anything you've mentioned before — it finds the most relevant snippet and brings it back with context.
OpenAI Cost Tracking Dashboard
The agent pulls your OpenAI usage every morning, breaks it down by model and task, and posts a cost dashboard to WhatsApp. You always know what the agent is spending.
Fine-Tuned Model Deployment
Upload training examples, kick off a fine-tune, and deploy the resulting model to your agent — all from WhatsApp. The agent handles file upload, job monitoring, and deployment.
Image Generation via DALL-E
Ask the agent to generate an image and it calls DALL-E 3 with your OpenAI key, uploads the result to Drive, and sends it to the WhatsApp chat in seconds.
Deploy this in minutes
Create a LunoGen agent, connect OpenAI, and start running this workflow from WhatsApp today.