@@ -18,7 +18,7 @@ Set an asset's `prompt` and `model` and the asset is generated at render time; `
 
 There is no prompt-length limit on the model itself. The API caps `prompt` at 4,000 characters.
 
-**Choosing a generation.** 2.5 for duration (30s against 2.0's 15s), for more reference inputs, and for better prompt adherence. **2.0 for 4K delivery** — it is the only one with a 4K tier — and for cost, running 36–41% cheaper per second at every shared resolution.
+**Choosing a generation.** 2.5 for duration: up to 30 seconds in one take, against 2.0's 15. ByteDance also claims better prompt adherence for 2.5, which its own pages don't corroborate. **2.0 for cost**: it is cheaper per second at every resolution, and both top out at 1080p. `shotstack models` has the current rates.
 
 ## Images — Nano Banana
 
 
@@ -252,7 +252,7 @@ Set `prompt` and `model` on an `image`, `video` or `audio` asset and it is gener
 { "asset": { "type": "video", "prompt": "Slow dolly across a rain-soaked neon street at night", "model": "seedance-2.0-text-to-video", "options": { "resolution": "720p" } }, "start": 0, "length": 5 }
 ```
 
-The models endpoint (`GET /models`) lists each model, whether the account can use it, its price, and the JSON Schema for its `options`. Options outside that schema are rejected. To animate a still, use a model that accepts a starting image and put the image URL in `options.inputSrc`.
+The models endpoint (`GET /models`) lists each model, whether the account can use it, its price, and the JSON Schema for its `options`. Options outside that schema are rejected. To animate a still, use an image-to-video model and put the image URL in `options.startSrc` (`inputSrc` on the original image-to-video models).
 
 Generation is billed per asset **even on the stage endpoint**, which is otherwise free. Renders containing AI assets take longer, because the render waits for each generation.