Mark the hosted API as coming soon

README.md

@@ -31,7 +31,7 @@ time-series encoder onto a pretrained LLM.
 - 📄 **Paper:** [Chronicle: A Multimodal Foundation Model for Joint Language and Time
   Series Understanding](https://arxiv.org/abs/2605.20268) (Quinlan, Levasseur, Li, Zhu)
 - 💻 **Code & finetuning examples:** [github.com/InertialAI/Chronicle](https://github.com/InertialAI/Chronicle)
-- ☁️ **Hosted API with self-serve finetuning:** [inertialai.com](https://www.inertialai.com/platform)
+- ☁️ **Hosted API with self-serve finetuning *(coming soon)*:** [inertialai.com](https://www.inertialai.com/platform)
 
 ## Checkpoints in this repo
 
@@ -94,8 +94,8 @@ print(tokenizer.decode(ids[1:]))
 
 For the time-series pathway (quantile forecasting via `ts_patches`) and
 `forecast()` / `embed()` conveniences, use the **transformers-native port (in
-progress)** or the [hosted API](https://docs.inertialai.com), which serves these
-models today. The finetuning recipes in the
+progress)** or the [hosted API](https://docs.inertialai.com) (coming soon), which
+will serve these models. The finetuning recipes in the
 [GitHub repo](https://github.com/InertialAI/Chronicle) show the downstream-task
 protocols used in the paper.