From 3c384326955dc23f3ecef45e669a830283aa9410 Mon Sep 17 00:00:00 2001
From: Zeke Sikelianos <zeke@sikelianos.com>
Date: Mon, 6 Oct 2025 11:35:19 -0700
Subject: [PATCH] docs: remove replicate.stream from README

---
 README.md | 16 ----------------
 1 file changed, 16 deletions(-)

diff --git a/README.md b/README.md
index d4812d4..59d01b5 100644
--- a/README.md
+++ b/README.md
@@ -110,22 +110,6 @@ output = replicate.run("...", input={...}, wait=False)
 
 When `wait=False`, the method returns immediately after creating the prediction, and you'll need to poll for the result manually.
 
-## Run a model and stream its output
-
-For models that support streaming (particularly language models), you can use `replicate.stream()`:
-
-```python
-import replicate
-
-for event in replicate.stream(
-    "meta/meta-llama-3-70b-instruct",
-    input={
-        "prompt": "Please write a haiku about llamas.",
-    },
-):
-    print(str(event), end="")
-```
-
 ## Async usage
 
 Simply import `AsyncReplicate` instead of `Replicate` and use `await` with each API call: