Pick a winner in each dimension — change your vote anytime.
Pricing and capabilities synced from the OpenRouter catalogue. Scores are editorial (0–10).
Choose Gemini 3.1 Flash Lite if you want cheap, high-volume steps that still need long context. Choose Llama 4 Maverick if you want self-hosted agents that want the Llama ecosystem.
Editorially it's close: each model leads in 2 of our five dimensions. On price, Gemini 3.1 Flash Lite runs about $0.63 per 1M tokens (blended) and is proprietary; Llama 4 Maverick is about $0.28 and open-weight.
The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.