tiennm99/cheahjs-free-llm-api-resources
1
0 Fork 0
mirror of https://github.com/tiennm99/cheahjs-free-llm-api-resources.git synced 2026-10-14 16:17:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

openrouter: free models have shared limits

Browse Source
This commit is contained in:
Jun Siang Cheah committed 2024-10-13 10:50:15 +01:00
1 parent b52715cce1
commit 384adcb5d4
2 files changed
+20 -21
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

README.md
+19 -19
View File
@@ -39,25 +39,25 @@ 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 rowspan="19"><a href="https://openrouter.ai" target="_blank">OpenRouter</a></td><td rowspan="19"></td><td>Gemma 2 9B Instruct</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Hermes 3 Llama 3.1 405B</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Liquid LFM 40B</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Llama 3 8B Instruct</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Llama 3.1 405B Instruct</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Llama 3.1 70B Instruct</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Llama 3.1 8B Instruct</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Llama 3.2 11B Vision Instruct</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Llama 3.2 1B Instruct</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Llama 3.2 3B Instruct</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Mistral 7B Instruct</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Mythomax L2 13B</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Mythomist 7B</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>OpenChat 7B</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Phi-3 Medium 128k Instruct</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Phi-3 Mini 128k Instruct</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Qwen 2 7B Instruct</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Toppy M 7B</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td>Zephyr 7B Beta</td><td>20 requests/minute<br>200 requests/day</td></tr>
<tr><td rowspan="19"><a href="https://openrouter.ai" target="_blank">OpenRouter</a></td><td rowspan="19">20 requests/minute<br>200 requests/day</td><td>Gemma 2 9B Instruct</td></tr>
<tr><td>Hermes 3 Llama 3.1 405B</td></tr>
<tr><td>Liquid LFM 40B</td></tr>
<tr><td>Llama 3 8B Instruct</td></tr>
<tr><td>Llama 3.1 405B Instruct</td></tr>
<tr><td>Llama 3.1 70B Instruct</td></tr>
<tr><td>Llama 3.1 8B Instruct</td></tr>
<tr><td>Llama 3.2 11B Vision Instruct</td></tr>
<tr><td>Llama 3.2 1B Instruct</td></tr>
<tr><td>Llama 3.2 3B Instruct</td></tr>
<tr><td>Mistral 7B Instruct</td></tr>
<tr><td>Mythomax L2 13B</td></tr>
<tr><td>Mythomist 7B</td></tr>
<tr><td>OpenChat 7B</td></tr>
<tr><td>Phi-3 Medium 128k Instruct</td></tr>
<tr><td>Phi-3 Mini 128k Instruct</td></tr>
<tr><td>Qwen 2 7B Instruct</td></tr>
<tr><td>Toppy M 7B</td></tr>
<tr><td>Zephyr 7B Beta</td></tr>
<tr>
<td rowspan="9"><a href="https://aistudio.google.com" target="_blank">Google AI Studio</a></td>
<td rowspan="9">Data is used for training (when used outside of the UK/CH/EEA/EU).</td>
src/pull_available_models.py
+1 -2
View File
@@ -553,10 +553,9 @@ def main():
table += f'<td rowspan="{len(openrouter_models)}">'
table += '<a href="https://openrouter.ai" target="_blank">OpenRouter</a>'
table += '</td>'
table += f'<td rowspan="{len(openrouter_models)}"></td>'
table += f'<td rowspan="{len(openrouter_models)}">{get_human_limits(model)}</td>'
table += f"<td>{model['name']}</td>"
table += f"<td>{get_human_limits(model)}</td>"
table += "</tr>\n"
table += f"""<tr>