tiennm99/cheahjs-free-llm-api-resources
1
0 Fork 0
mirror of https://github.com/tiennm99/cheahjs-free-llm-api-resources.git synced 2026-10-11 12:08:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

update outdated model list

Browse Source
This commit is contained in:
Jun Siang Cheah committed 2025-12-17 22:21:38 +00:00
1 parent 04673156f6
commit 6a61357455
2 files changed
+5 -20
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

README.md
+2 -5
View File
@@ -148,13 +148,10 @@ Routes to various supported providers.
<table><thead><tr><th>Model Name</th><th>Model Limits</th></tr></thead><tbody>
<tr><td>gpt-oss-120b</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>Qwen 3 235B A22B Instruct</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>Qwen 3 235B A22B Thinking</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>Qwen 3 Coder 480B</td><td>10 requests/minute<br>150,000 tokens/minute<br>100 requests/hour<br>1,000,000 tokens/hour<br>100 requests/day<br>1,000,000 tokens/day</td></tr>
<tr><td>Llama 3.3 70B</td><td>30 requests/minute<br>64,000 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>Qwen 3 32B</td><td>30 requests/minute<br>64,000 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>Llama 3.1 8B</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>Llama 4 Scout</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>Llama 4 Maverick</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>Z.ai GLM-4.6</td><td>10 requests/minute<br>60,000 tokens/minute<br>100 requests/hour<br>100,000 tokens/hour<br>100 requests/day<br>1,000,000 tokens/day</td></tr>
</tbody></table>
### [Groq](https://console.groq.com)
@@ -186,7 +183,7 @@ Routes to various supported providers.
[20 requests/minute<br>1,000 requests/month](https://docs.cohere.com/docs/rate-limits)
Models share a common quota.
Models share a common monthly quota.
- c4ai-aya-expanse-32b
- c4ai-aya-expanse-8b
src/pull_available_models.py
+3 -15
View File
@@ -832,14 +832,6 @@ def main():
"name": "Qwen 3 235B A22B Instruct",
"limits_text": "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"
},
{
"name": "Qwen 3 235B A22B Thinking",
"limits_text": "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"
},
{
"name": "Qwen 3 Coder 480B",
"limits_text": "10 requests/minute<br>150,000 tokens/minute<br>100 requests/hour<br>1,000,000 tokens/hour<br>100 requests/day<br>1,000,000 tokens/day"
},
{
"name": "Llama 3.3 70B",
"limits_text": "30 requests/minute<br>64,000 tokens/minute<br>900 requests/hour<br>1,000,000 tokens/hour<br>14,400 requests/day<br>1,000,000 tokens/day"
@@ -853,12 +845,8 @@ def main():
"limits_text": "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"
},
{
"name": "Llama 4 Scout",
"limits_text": "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"
},
{
"name": "Llama 4 Maverick",
"limits_text": "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"
"name": "Z.ai GLM-4.6",
"limits_text": "10 requests/minute<br>60,000 tokens/minute<br>100 requests/hour<br>100,000 tokens/hour<br>100 requests/day<br>1,000,000 tokens/day"
},
]
for model in cerebras_models:
@@ -883,7 +871,7 @@ def main():
model_list_markdown += "### [Cohere](https://cohere.com)\n\n"
model_list_markdown += "**Limits:**\n\n"
model_list_markdown += "[20 requests/minute<br>1,000 requests/month](https://docs.cohere.com/docs/rate-limits)\n\n"
model_list_markdown += "Models share a common quota.\n\n"
model_list_markdown += "Models share a common monthly quota.\n\n"
if cohere_models:
for model in cohere_models:
model_list_markdown += f"- {model['name']}\n"