Pick a winner in each dimension — change your vote anytime.
Pricing and capabilities synced from the OpenRouter catalogue. Scores are editorial (0–10).
Choose DeepSeek R1 (0528) if you want reasoning-heavy planning where cost matters. Choose DeepSeek V3.2 if you want dependable open-weight output on a tight budget.
In our editorial scoring, DeepSeek V3.2 leads in 4 of five dimensions (output quality, agentic ability, speed and value for $), while DeepSeek R1 (0528) leads in 0. On price, DeepSeek R1 (0528) runs about $0.99 per 1M tokens (blended) and is open-weight; DeepSeek V3.2 is about $0.26 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.