mirror of
https://github.com/tiennm99/cheahjs-free-llm-api-resources.git
synced 2026-10-14 06:17:32 +00:00
docs: update models
This commit is contained in:
Jun Siang Cheah committed
1 parent
e87aab3769
commit
0577778fda
3 files changed
+94
-28
No files matched your search
@@ -35,6 +35,7 @@ jobs:
|
||||
HYPERBOLIC_API_KEY: ${{ secrets.HYPERBOLIC_API_KEY }}
|
||||
GCP_PROJECT_ID: ${{ secrets.GCP_PROJECT_ID }}
|
||||
GOOGLE_APPLICATION_CREDENTIALS: ${{ steps.auth.outputs.credentials_file_path }}
|
||||
LAMBDA_API_KEY: ${{ secrets.LAMBDA_API_KEY }}
|
||||
run: |
|
||||
python -u src/pull_available_models.py
|
||||
- name: Remove credentials
|
||||
|
||||
@@ -50,6 +50,7 @@ This lists various services that provide free access or credits towards API-base
|
||||
<tr><td>Llama 3.2 11B Vision Instruct</td><td></td></tr>
|
||||
<tr><td>Llama 3.2 1B Instruct</td><td></td></tr>
|
||||
<tr><td>Llama 3.2 3B Instruct</td><td></td></tr>
|
||||
<tr><td>Llama 3.2 90B Vision Instruct</td><td></td></tr>
|
||||
<tr><td>Mistral 7B Instruct</td><td></td></tr>
|
||||
<tr><td>Mythomax L2 13B</td><td></td></tr>
|
||||
<tr><td>Mythomist 7B</td><td></td></tr>
|
||||
@@ -59,7 +60,6 @@ This lists various services that provide free access or credits towards API-base
|
||||
<tr><td>Qwen 2 7B Instruct</td><td></td></tr>
|
||||
<tr><td>Toppy M 7B</td><td></td></tr>
|
||||
<tr><td>Zephyr 7B Beta</td><td></td></tr>
|
||||
<tr><td>meta-llama/llama-3.2-90b-vision-instruct:free</td><td></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>
|
||||
@@ -96,17 +96,18 @@ This lists various services that provide free access or credits towards API-base
|
||||
</tr>
|
||||
<tr>
|
||||
<td>embedding-001</td>
|
||||
</tr><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>
|
||||
<td><a href="https://lambdalabs.com/blog/unveiling-hermes-3-the-first-fine-tuned-llama-3.1-405b-model-is-on-lambdas-cloud" target="_blank">Free for a limited time</a></td>
|
||||
<td>Nous Hermes 3 Llama 3.1 405B (FP8)</td>
|
||||
<td></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td>Liquid LFM 40B</td>
|
||||
<td></td>
|
||||
</tr><tr>
|
||||
</tr><tr><td rowspan="11"><a href="https://docs.lambdalabs.com/on-demand-cloud/using-the-lambda-chat-completions-api" target="_blank">Lambda Labs (Free Preview)</a></td><td rowspan="11">Requires credit card verification.</td><td>DeepSeek Coder v2 Lite Instruct</td><td></td></tr>
|
||||
<tr><td>Dracarys 2 72B Instruct</td><td></td></tr>
|
||||
<tr><td>Hermes 3 405B</td><td></td></tr>
|
||||
<tr><td>Hermes 3 70B</td><td></td></tr>
|
||||
<tr><td>Hermes 3 8B</td><td></td></tr>
|
||||
<tr><td>Liquid LFM 40B</td><td></td></tr>
|
||||
<tr><td>Llama 3.1 405B Instruct (FP8)</td><td></td></tr>
|
||||
<tr><td>Llama 3.1 70B Instruct (FP8)</td><td></td></tr>
|
||||
<tr><td>Llama 3.1 8B Instruct</td><td></td></tr>
|
||||
<tr><td>Llama 3.1 Nemotron 70B Instruct</td><td></td></tr>
|
||||
<tr><td>Llama 3.2 3B Instruct</td><td></td></tr>
|
||||
<tr>
|
||||
<td><a href="https://console.mistral.ai/" target="_blank">Mistral (La Plateforme)</a></td>
|
||||
<td>Free tier (Experiment plan) requires opting into data training, requires phone number verification.</td>
|
||||
<td>Open and Proprietary Mistral models</td>
|
||||
@@ -122,15 +123,23 @@ This lists various services that provide free access or credits towards API-base
|
||||
<td>Various open models</td>
|
||||
<td><a href="https://huggingface.co/docs/api-inference/rate-limits" target="_blank">1,000 requests/day (with an account)</a></td>
|
||||
</tr><tr>
|
||||
<td rowspan="5"><a href="https://cloud.sambanova.ai/" target="_blank">SambaNova Cloud</a></td>
|
||||
<td rowspan="5"></td>
|
||||
<td rowspan="7"><a href="https://cloud.sambanova.ai/" target="_blank">SambaNova Cloud</a></td>
|
||||
<td rowspan="7"></td>
|
||||
<td>Llama 3.1 405B</td>
|
||||
<td>10 requests/minute</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama 3.2 90B</td>
|
||||
<td>1 request/minute</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama 3.1 70B</td>
|
||||
<td>20 requests/minute</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama 3.2 11B</td>
|
||||
<td>10 requests/minute</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama 3.1 8B</td>
|
||||
<td>30 requests/minute</td>
|
||||
@@ -177,6 +186,7 @@ This lists various services that provide free access or credits towards API-base
|
||||
<tr><td>Phi-3-small instruct (8k)</td><td></td></tr>
|
||||
<tr><td>Phi-3.5-mini instruct (128k)</td><td></td></tr>
|
||||
<tr><td rowspan="10"><a href="https://endpoints.ai.cloud.ovh.net/" target="_blank">OVH AI Endpoints (Free Alpha)</a></td><td rowspan="10">Token expires every week.</td><td>CodeLlama 13B Instruct</td><td>12 requests/minute</td></tr>
|
||||
<tr><td>Codestral Mamba 7B v0.1</td><td>12 requests/minute</td></tr>
|
||||
<tr><td>Llama 2 13B Chat</td><td>12 requests/minute</td></tr>
|
||||
<tr><td>Llama 3 70B Instruct</td><td>12 requests/minute</td></tr>
|
||||
<tr><td>Llama 3 8B Instruct</td><td>12 requests/minute</td></tr>
|
||||
@@ -185,7 +195,6 @@ 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>mamba-codestral-7b-v0-1</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"><a href="https://developers.cloudflare.com/workers-ai/platform/pricing/#free-allocation">10,000 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>
|
||||
|
||||
@@ -128,6 +128,20 @@ MODEL_TO_NAME_MAPPING = {
|
||||
"mathstral-7b-v0.1": "Mathstral 7B v0.1",
|
||||
"llama-3.1-70b-instruct": "Llama 3.1 70B Instruct",
|
||||
"gryphe/mythomax-l2-13b:free": "Mythomax L2 13B",
|
||||
"meta-llama/llama-3.2-90b-vision-instruct:free": "Llama 3.2 90B Vision Instruct",
|
||||
"mamba-codestral-7b-v0-1": "Codestral Mamba 7B v0.1",
|
||||
"hermes3-70b": "Hermes 3 70B",
|
||||
"llama3.1-nemotron-70b-instruct": "Llama 3.1 Nemotron 70B Instruct",
|
||||
"llama3.2-3b-instruct": "Llama 3.2 3B Instruct",
|
||||
"llama3.1-8b-instruct": "Llama 3.1 8B Instruct",
|
||||
"llama3.1-70b-instruct-fp8": "Llama 3.1 70B Instruct (FP8)",
|
||||
"llama3.1-405b-instruct-fp8": "Llama 3.1 405B Instruct (FP8)",
|
||||
"hermes3-405b": "Hermes 3 405B",
|
||||
"deepseek-coder-v2-lite-instruct": "DeepSeek Coder v2 Lite Instruct",
|
||||
"hermes3-8b": "Hermes 3 8B",
|
||||
"dracarys2-72b-instruct": "Dracarys 2 72B Instruct",
|
||||
"lfm-40b": "Liquid LFM 40B",
|
||||
|
||||
}
|
||||
|
||||
|
||||
@@ -151,6 +165,11 @@ HYPERBOLIC_IGNORED_MODELS = {
|
||||
"TTS"
|
||||
}
|
||||
|
||||
LAMBDA_IGNORED_MODELS = {
|
||||
"lfm-40b-vllm",
|
||||
"hermes3-405b-fp8-128k"
|
||||
}
|
||||
|
||||
|
||||
def get_model_name(id):
|
||||
id = id.lower()
|
||||
@@ -496,6 +515,32 @@ def fetch_gemini_limits(logger):
|
||||
return models
|
||||
|
||||
|
||||
def fetch_lambda_models(logger):
|
||||
logger.info("Fetching Lambda Labs models...")
|
||||
r = requests.get(
|
||||
"https://api.lambdalabs.com/v1/models",
|
||||
headers={
|
||||
"Authorization": f"Bearer {os.environ['LAMBDA_API_KEY']}",
|
||||
},
|
||||
)
|
||||
r.raise_for_status()
|
||||
models = r.json()["data"]
|
||||
logger.info(f"Fetched {len(models)} models from Lambda Labs")
|
||||
ret_models = []
|
||||
for model in models:
|
||||
if model["id"] in LAMBDA_IGNORED_MODELS:
|
||||
logger.debug(f"Ignoring model {model['id']}")
|
||||
continue
|
||||
ret_models.append(
|
||||
{
|
||||
"id": model["id"],
|
||||
"name": get_model_name(model["id"]),
|
||||
}
|
||||
)
|
||||
ret_models = sorted(ret_models, key=lambda x: x["name"])
|
||||
return ret_models
|
||||
|
||||
|
||||
def get_human_limits(model):
|
||||
if "limits" not in model:
|
||||
return ""
|
||||
@@ -512,6 +557,7 @@ def main():
|
||||
cloudflare_logger = create_logger("Cloudflare")
|
||||
github_logger = create_logger("GitHub")
|
||||
hyperbolic_logger = create_logger("Hyperbolic")
|
||||
lambda_logger = create_logger("Lambda Labs")
|
||||
|
||||
gemini_models = fetch_gemini_limits(google_ai_studio_logger)
|
||||
openrouter_models = fetch_openrouter_models(openrouter_logger)
|
||||
@@ -519,6 +565,7 @@ def main():
|
||||
ovh_models = fetch_ovh_models(ovh_logger)
|
||||
cloudflare_models = fetch_cloudflare_models(cloudflare_logger)
|
||||
github_models = fetch_github_models(github_logger)
|
||||
lambda_models = fetch_lambda_models(lambda_logger)
|
||||
groq_models = fetch_groq_models(groq_logger)
|
||||
|
||||
|
||||
@@ -598,17 +645,18 @@ def main():
|
||||
<td>embedding-001</td>
|
||||
</tr>"""
|
||||
|
||||
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>
|
||||
<td><a href="https://lambdalabs.com/blog/unveiling-hermes-3-the-first-fine-tuned-llama-3.1-405b-model-is-on-lambdas-cloud" target="_blank">Free for a limited time</a></td>
|
||||
<td>Nous Hermes 3 Llama 3.1 405B (FP8)</td>
|
||||
<td></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td>Liquid LFM 40B</td>
|
||||
<td></td>
|
||||
</tr>"""
|
||||
for idx, model in enumerate(lambda_models):
|
||||
table += "<tr>"
|
||||
if idx == 0:
|
||||
table += f'<td rowspan="{len(lambda_models)}">'
|
||||
table += '<a href="https://docs.lambdalabs.com/on-demand-cloud/using-the-lambda-chat-completions-api" target="_blank">Lambda Labs (Free Preview)</a>'
|
||||
table += '</td>'
|
||||
table += f'<td rowspan="{len(lambda_models)}">'
|
||||
table += 'Requires credit card verification.'
|
||||
table += '</td>'
|
||||
table += f"<td>{model['name']}</td>"
|
||||
table += "<td></td>"
|
||||
table += "</tr>\n"
|
||||
|
||||
table += """<tr>
|
||||
<td><a href="https://console.mistral.ai/" target="_blank">Mistral (La Plateforme)</a></td>
|
||||
@@ -632,15 +680,23 @@ def main():
|
||||
</tr>"""
|
||||
|
||||
table += """<tr>
|
||||
<td rowspan="5"><a href="https://cloud.sambanova.ai/" target="_blank">SambaNova Cloud</a></td>
|
||||
<td rowspan="5"></td>
|
||||
<td rowspan="7"><a href="https://cloud.sambanova.ai/" target="_blank">SambaNova Cloud</a></td>
|
||||
<td rowspan="7"></td>
|
||||
<td>Llama 3.1 405B</td>
|
||||
<td>10 requests/minute</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama 3.2 90B</td>
|
||||
<td>1 request/minute</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama 3.1 70B</td>
|
||||
<td>20 requests/minute</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama 3.2 11B</td>
|
||||
<td>10 requests/minute</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Llama 3.1 8B</td>
|
||||
<td>30 requests/minute</td>
|
||||
|
||||
Reference in new issue
Block a user