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 08:18:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

cloudflare: change from neurons to token usage

Browse Source
This commit is contained in:
Jun Siang Cheah committed 2024-10-03 09:18:36 +01:00
1 parent 465386ff19
commit 00330ca2f1
2 files changed
+2 -2
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

README.md
+1 -1
View File
@@ -139,7 +139,7 @@ This lists various services that provide free access or credits towards API-base
<tr><td>Mistral 7B Instruct</td><td>12 requests/minute</td></tr>
<tr><td>Mixtral 8x22B Instruct</td><td>12 requests/minute</td></tr>
<tr><td>Mixtral 8x7B Instruct</td><td>12 requests/minute</td></tr>
<tr><td rowspan="40"><a href="https://developers.cloudflare.com/workers-ai" target="_blank">Cloudflare Workers AI</a></td><td rowspan="40">10000 neurons/day<br>Beta models have unlimited usage.<br>Typically 300 requests/min for text models.</td><td>Deepseek Coder 6.7B Base (AWQ)</td><td></td></tr>
<tr><td rowspan="40"><a href="https://developers.cloudflare.com/workers-ai" target="_blank">Cloudflare Workers AI</a></td><td rowspan="40"><a href="https://developers.cloudflare.com/workers-ai/platform/pricing/#free-allocation">10000 tokens/day</a></td><td>Deepseek Coder 6.7B Base (AWQ)</td><td></td></tr>
<tr><td>Deepseek Coder 6.7B Instruct (AWQ)</td><td></td></tr>
<tr><td>Deepseek Math 7B Instruct</td><td></td></tr>
<tr><td>Discolm German 7B v1 (AWQ)</td><td></td></tr>
src/pull_available_models.py
+1 -1
View File
@@ -625,7 +625,7 @@ def main():
table += f"<tr>{f'<td rowspan="{len(ovh_models)}"><a href="https://endpoints.ai.cloud.ovh.net/" target="_blank">OVH AI Endpoints (Free Alpha)</a></td>' if idx == 0 else ''}{ f'<td rowspan="{len(ovh_models)}">Token expires every 2 weeks.</td>' if idx == 0 else ''}<td>{model['name']}</td><td>{get_human_limits(model)}</td></tr>\n"
for idx, model in enumerate(cloudflare_models):
table += f"<tr>{f'<td rowspan="{len(cloudflare_models)}"><a href="https://developers.cloudflare.com/workers-ai" target="_blank">Cloudflare Workers AI</a></td>' if idx == 0 else ''}{ f'<td rowspan="{len(cloudflare_models)}">10000 neurons/day<br>Beta models have unlimited usage.<br>Typically 300 requests/min for text models.</td>' if idx == 0 else ''}<td>{model['name']}</td><td></td></tr>\n"
table += f"<tr>{f'<td rowspan="{len(cloudflare_models)}"><a href="https://developers.cloudflare.com/workers-ai" target="_blank">Cloudflare Workers AI</a></td>' if idx == 0 else ''}{ f'<td rowspan="{len(cloudflare_models)}"><a href="https://developers.cloudflare.com/workers-ai/platform/pricing/#free-allocation">10000 tokens/day</a></td>' if idx == 0 else ''}<td>{model['name']}</td><td></td></tr>\n"
table += """<tr>
<td rowspan="2"><a href="https://docs.lambdalabs.com/on-demand-cloud/using-the-lambda-chat-completions-api" target="_blank">Lambda Labs (Free Preview)</a></td>