JevMade Sign in
← Back to videos

JevMade field notes / Video guide

OpenRouter State Of Models: Jev, Open-Weights, and Tokenomics

IndyDevDan discusses model usage on OpenRouter and describes adding Jev to his Pi coding agent. His rough 20% token-spend saving is a personal estimate, not a controlled comparison of cost, speed or work quality.

Original by IndyDevDanAgent workflowsIntermediate26 min 8 sec Published

Before you press play

What you’ll find in the video

  1. Combine models with different jobs. In the Jev chapter, the creator describes adding quick decisions to his Pi coding agent rather than replacing its language model.
  2. Ask what a saving actually measures. The creator estimates about 20% lower token spend with Jev; he says the comparison screen shows cost and still needs a speed measure.
  3. Choose an agent setup you can change. The creator connects Pi's customizable harness—the software around its model—to adding tools. OpenRouter's app rankings cover its own traffic, not all use of those apps.
Worth knowing

Mostly model-market commentary, with Jev discussed in the 10:27–15:22 chapter and Pi revisited from 19:15. The saving is the creator's rough personal estimate; comparable task quality, repeatability and measured speed are not established. His claims about Jev's reliability are opinions, not an independent uptime or security endorsement. OpenRouter rankings do not represent the whole AI market. The video promotes the creator's paid course.

OpenRouter State Of Models: Jev, Open-Weights, and Tokenomics

Keep this for later

Sign in to bookmark experiments, guides and videos, and keep notes only you can see.

Continue to sign in

We’ll bring you back to this listing.