From 3a77713c091846b78076bbd3f965f2ec7fc5fb72 Mon Sep 17 00:00:00 2001
From: Jun Siang Cheah <git@jscheah.me>
Date: Mon, 27 Jan 2025 21:37:07 +0700
Subject: [PATCH] update

---
 README.md                    | 3 ++-
 src/pull_available_models.py | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index beecf4e..f1e0e6c 100644
--- a/README.md
+++ b/README.md
@@ -121,7 +121,7 @@ This lists various services that provide free access or credits towards API-base
     <tr>
         <td>Llama 3.3 70B</td>
         <td>30 requests/minute<br>60,000 tokens/minute<br>900 requests/hour<br>1,000,000 tokens/hour<br>14,400 requests/day<br>1,000,000 tokens/day</td>
-    </tr><tr><td rowspan="15"><a href="https://console.groq.com" target="_blank">Groq</a></td><td rowspan="15"></td><td>Distil Whisper Large v3</td><td>7,200 audio-seconds/minute<br>2,000 requests/day</td></tr>
+    </tr><tr><td rowspan="16"><a href="https://console.groq.com" target="_blank">Groq</a></td><td rowspan="16"></td><td>Distil Whisper Large v3</td><td>7,200 audio-seconds/minute<br>2,000 requests/day</td></tr>
 <tr><td>Gemma 2 9B Instruct</td><td>14,400 requests/day<br>15,000 tokens/minute</td></tr>
 <tr><td>Llama 3 70B</td><td>14,400 requests/day<br>6,000 tokens/minute</td></tr>
 <tr><td>Llama 3 8B</td><td>14,400 requests/day<br>20,000 tokens/minute</td></tr>
@@ -136,6 +136,7 @@ This lists various services that provide free access or credits towards API-base
 <tr><td>Mixtral 8x7B</td><td>14,400 requests/day<br>5,000 tokens/minute</td></tr>
 <tr><td>Whisper Large v3</td><td>7,200 audio-seconds/minute<br>2,000 requests/day</td></tr>
 <tr><td>Whisper Large v3 Turbo</td><td>7,200 audio-seconds/minute<br>2,000 requests/day</td></tr>
+<tr><td>deepseek-r1-distill-llama-70b</td><td>1,000 requests/day<br>6,000 tokens/minute</td></tr>
 <tr><td rowspan="8"><a href="https://console.scaleway.com/generative-api/models" target="_blank">Scaleway Generative APIs (Free Beta)</a></td><td rowspan="8"></td><td>BGE-Multilingual-Gemma2</td><td>100 requests/minute<br>200,000 tokens/minute</td></tr>
 <tr><td>Llama 3.1 70B Instruct</td><td>300 requests/minute<br>100,000 tokens/minute</td></tr>
 <tr><td>Llama 3.1 8B Instruct</td><td>300 requests/minute<br>100,000 tokens/minute</td></tr>
diff --git a/src/pull_available_models.py b/src/pull_available_models.py
index 47df191..754d9f6 100644
--- a/src/pull_available_models.py
+++ b/src/pull_available_models.py
@@ -678,7 +678,7 @@ def fetch_scaleway_models(logger):
     ret_models = sorted(ret_models, key=lambda x: x["name"])
     logger.info("Fetching Scaleway rate limits")
     r = requests.get(
-        "https://www.scaleway.com/en/docs/ai-data/generative-apis/reference-content/rate-limits/"
+        "https://www.scaleway.com/en/docs/generative-apis/reference-content/rate-limits/"
     )
     r.raise_for_status()
     # Extract <main> content