diff --git a/README.md b/README.md index 530d66d..0c10798 100644 --- a/README.md +++ b/README.md @@ -16,7 +16,7 @@ This lists various services that provide free access or credits towards API-base -GroqGemma 2 9B Instruct14400 requests/day
15000 tokens/minute +GroqGemma 2 9B Instruct14400 requests/day
15000 tokens/minute Gemma 7B Instruct14400 requests/day
15000 tokens/minute Llama 3 70B14400 requests/day
6000 tokens/minute Llama 3 70B - Groq Tool Use Preview14400 requests/day
15000 tokens/minute @@ -27,7 +27,7 @@ This lists various services that provide free access or credits towards API-base Llama Guard 3 8B14400 requests/day
15000 tokens/minute Mixtral 8x7B14400 requests/day
5000 tokens/minute Whisper Large v37200 audio-seconds/minute
2000 requests/day -OpenRouterGemma 2 9B Instruct20 requests/minute
200 requests/day +OpenRouterGemma 2 9B Instruct20 requests/minute
200 requests/day Gemma 7B Instruct20 requests/minute
200 requests/day Llama 3 8B Instruct20 requests/minute
200 requests/day Llama 3.1 8B Instruct20 requests/minute
200 requests/day @@ -41,7 +41,7 @@ This lists various services that provide free access or credits towards API-base Toppy M 7B20 requests/minute
200 requests/day Zephyr 7B Beta20 requests/minute
200 requests/day - Google AI Studio + Google AI Studio Free tier Gemini API access not available within UK/CH/EEA/EU/
Data is used for training. Gemini 1.5 Flash 15 requests/min
1500 requests/day
1 million tokens/min @@ -67,12 +67,12 @@ This lists various services that provide free access or credits towards API-base embedding-001 1500 requests/min
100 content/batch - glhf.chat (Free Beta) + glhf.chat (Free Beta) Any model on Hugging Face runnable on vLLM and fits on a A100 node (~640GB VRAM), including Llama 3.1 405B at FP8 - Cohere + Cohere 10 requests/min
1000 requests/month Command-R Shared Limit @@ -81,24 +81,24 @@ This lists various services that provide free access or credits towards API-base Command-R+ Shared Limit - HuggingFace Serverless Inference + HuggingFace Serverless Inference Dynamic Rate Limits.
Limited to models smaller than 10GB.
Some popular models are supported even if they exceed 10GB. Various open models - Hyperbolic (Free Testing Period)Llama 3 70B Instruct200 requests/minute + Hyperbolic (Free Testing Period)Llama 3 70B Instruct200 requests/minute Hermes 3 Llama 3.1 70B200 requests/minute Llama 3.1 70B Instruct200 requests/minute Llama 3.1 405B Instruct200 requests/minute Llama 3.1 405B Base (FP8)200 requests/minute Llama 3.1 8B Instruct200 requests/minute -OVH AI Endpoints (Free Alpha)Token expires every 2 weeks.CodeLlama 13B Instruct12 requests/minute +OVH AI Endpoints (Free Alpha)Token expires every 2 weeks.CodeLlama 13B Instruct12 requests/minute Llama 2 13B Chat12 requests/minute Llama 3 70B Instruct12 requests/minute Llama 3 8B Instruct12 requests/minute Mistral 7B Instruct12 requests/minute Mixtral 8x22B Instruct12 requests/minute Mixtral 8x7B Instruct12 requests/minute -Cloudflare Workers AI10000 neurons/day
Beta models have unlimited usage.
Typically 300 requests/min for text models.Deepseek Coder 6.7B Base (AWQ) +Cloudflare Workers AI10000 neurons/day
Beta models have unlimited usage.
Typically 300 requests/min for text models.Deepseek Coder 6.7B Base (AWQ) Deepseek Coder 6.7B Instruct (AWQ) Deepseek Math 7B Instruct Discolm German 7B v1 (AWQ) @@ -135,7 +135,12 @@ This lists various services that provide free access or credits towards API-base TinyLlama 1.1B Chat v1.0 Una Cybertron 7B v2 (BF16) Zephyr 7B Beta (AWQ) - + + Lambda Labs (Free Preview) + Free for a limited time + Nous Hermes 3 Llama 3.1 405B (FP8) + + ## Providers with trial credits diff --git a/src/pull_available_models.py b/src/pull_available_models.py index ce0e5c6..680c371 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -376,12 +376,12 @@ def main(): groq_models = fetch_groq_models() for idx, model in enumerate(groq_models): # markdown_table += f"|{'[Groq](https://console.groq.com)' if idx == 0 else '^'}|{ ' ' if idx == 0 else '^'}|{model['name']}|{get_human_limits(model)}|\n" - table += f"{f'Groq' if idx == 0 else ''}{ f'' if idx == 0 else ''}{model['name']}{get_human_limits(model)}\n" + table += f"{f'Groq' if idx == 0 else ''}{ f'' if idx == 0 else ''}{model['name']}{get_human_limits(model)}\n" openrouter_models = fetch_openrouter_models() for idx, model in enumerate(openrouter_models): # markdown_table += f"|{'[OpenRouter](https://openrouter.ai)' if idx == 0 else '^'}|{ ' ' if idx == 0 else '^'}|{model['name']}|{get_human_limits(model)}|\n" - table += f"{f'OpenRouter' if idx == 0 else ''}{ f'' if idx == 0 else ''}{model['name']}{get_human_limits(model)}\n" + table += f"{f'OpenRouter' if idx == 0 else ''}{ f'' if idx == 0 else ''}{model['name']}{get_human_limits(model)}\n" # markdown_table += "|[Google AI Studio](https://aistudio.google.com)|Free tier Gemini API access not available within UK/CH/EEA/EU.
Data is used for training.|Gemini 1.5 Flash|15 requests/min
1500 requests/day
1 million tokens/min|\n" # markdown_table += "|^|^|Gemini 1.5 Pro|2 requests/min
50 requests/day
32000 tokens/min|\n" @@ -391,7 +391,7 @@ def main(): # "|^|^|embedding-001|1500 requests/min
100 contents/batch|\n" # ) table += """ - Google AI Studio + Google AI Studio Free tier Gemini API access not available within UK/CH/EEA/EU/
Data is used for training. Gemini 1.5 Flash 15 requests/min
1500 requests/day
1 million tokens/min @@ -419,7 +419,7 @@ def main(): """ table += """ - glhf.chat (Free Beta) + glhf.chat (Free Beta) Any model on Hugging Face runnable on vLLM and fits on a A100 node (~640GB VRAM), including Llama 3.1 405B at FP8 @@ -428,7 +428,7 @@ def main(): # markdown_table += "|[Cohere](https://cohere.com)|10 requests/min
1000 requests/month|Command-R||\n" # markdown_table += "|^|^|Command-R+||\n" table += """ - Cohere + Cohere 10 requests/min
1000 requests/month Command-R Shared Limit @@ -440,7 +440,7 @@ def main(): # markdown_table += "|[HuggingFace Serverless Inference](https://huggingface.co/docs/api-inference/en/index)|Dynamic Rate Limits.
Limited to models smaller than 10GB.
Some popular models are supported even if they exceed 10GB.|Various open models||\n" table += """ - HuggingFace Serverless Inference + HuggingFace Serverless Inference Dynamic Rate Limits.
Limited to models smaller than 10GB.
Some popular models are supported even if they exceed 10GB. Various open models @@ -449,17 +449,24 @@ def main(): hyperbolic_models = fetch_hyperbolic_models() for idx, model in enumerate(hyperbolic_models): # markdown_table += f"|{'[Hyperbolic](https://app.hyperbolic.xyz/)' if idx == 0 else '^'}|{ ' ' if idx == 0 else '^'}|{model['name']}| |\n" - table += f"{f'Hyperbolic (Free Testing Period)' if idx == 0 else ''}{ f'' if idx == 0 else ''}{model['name']}{get_human_limits(model)}\n" + table += f"{f'Hyperbolic (Free Testing Period)' if idx == 0 else ''}{ f'' if idx == 0 else ''}{model['name']}{get_human_limits(model)}\n" ovh_models = fetch_ovh_models() for idx, model in enumerate(ovh_models): # markdown_table += f"|{'[OVH AI Endpoints (Free Alpha)](https://endpoints.ai.cloud.ovh.net/)' if idx == 0 else '^'}|{ 'Token expires every 2 weeks.' if idx == 0 else '^'}|{model['name']}|{get_human_limits(model)}|\n" - table += f"{f'OVH AI Endpoints (Free Alpha)' if idx == 0 else ''}{ f'Token expires every 2 weeks.' if idx == 0 else ''}{model['name']}{get_human_limits(model)}\n" + table += f"{f'OVH AI Endpoints (Free Alpha)' if idx == 0 else ''}{ f'Token expires every 2 weeks.' if idx == 0 else ''}{model['name']}{get_human_limits(model)}\n" cloudflare_models = fetch_cloudflare_models() for idx, model in enumerate(cloudflare_models): # markdown_table += f"|{'[Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai)' if idx == 0 else '^'}|{ '10000 neurons/day
Beta models have unlimited usage.
Typically 300 requests/min for text models.' if idx == 0 else '^'}|{model['name']}| |\n" - table += f"{f'Cloudflare Workers AI' if idx == 0 else ''}{ f'10000 neurons/day
Beta models have unlimited usage.
Typically 300 requests/min for text models.' if idx == 0 else ''}{model['name']}\n" + table += f"{f'Cloudflare Workers AI' if idx == 0 else ''}{ f'10000 neurons/day
Beta models have unlimited usage.
Typically 300 requests/min for text models.' if idx == 0 else ''}{model['name']}\n" + + table += """ + Lambda Labs (Free Preview) + Free for a limited time + Nous Hermes 3 Llama 3.1 405B (FP8) + + """ table += ""