Switching pages
Loading the next view
New deployment
Model
Qwen 2.5 7B Instruct
Mistral 7B Instruct
Llama 3.1 8B Instruct
Hugging Face link or model ID
Objective
Cheapest
Most reliable
Lowest latency
Optional notes
Generate plan
Plan preview
Generate a plan to see provider choice, GPU estimate, uncertainty, and the approval gate.