diff --git a/README.md b/README.md index 52b3334..3d7789b 100644 --- a/README.md +++ b/README.md @@ -23,7 +23,7 @@ This lists various services that provide free access or credits towards API-base -GroqDistil Whisper Large v37,200 audio-seconds/minute
2,000 requests/day +GroqDistil Whisper Large v37,200 audio-seconds/minute
2,000 requests/day Gemma 2 9B Instruct14,400 requests/day
15,000 tokens/minute Gemma 7B Instruct14,400 requests/day
15,000 tokens/minute Llama 3 70B14,400 requests/day
6,000 tokens/minute @@ -36,11 +36,15 @@ This lists various services that provide free access or credits towards API-base Llama 3.2 1B7,000 requests/day
7,000 tokens/minute Llama 3.2 3B7,000 requests/day
7,000 tokens/minute Llama 3.2 90B Vision3,500 requests/day
7,000 tokens/minute +Llama 3.3 70B14,400 requests/day
6,000 tokens/minute +Llama 3.3 70B (Speculative Decoding)1,000 requests/day
6,000 tokens/minute Llama Guard 3 8B14,400 requests/day
15,000 tokens/minute Mixtral 8x7B14,400 requests/day
5,000 tokens/minute Whisper Large v37,200 audio-seconds/minute
2,000 requests/day Whisper Large v3 Turbo7,200 audio-seconds/minute
2,000 requests/day -OpenRouter20 requests/minute
200 requests/dayGemma 2 9B Instruct +OpenRouter20 requests/minute
200 requests/dayGemini Experimental 1114 +Gemini Experimental 1206 +Gemma 2 9B Instruct Llama 3 8B Instruct Llama 3.1 405B Instruct Llama 3.1 70B Instruct @@ -58,8 +62,8 @@ This lists various services that provide free access or credits towards API-base Toppy M 7B Zephyr 7B Beta - Google AI Studio - Data is used for training (when used outside of the UK/CH/EEA/EU). + Google AI Studio + Data is used for training (when used outside of the UK/CH/EEA/EU). Gemini 1.5 Flash 1,000,000 tokens/minute
1,500 requests/day
15 requests/minute @@ -81,7 +85,11 @@ This lists various services that provide free access or credits towards API-base Gemini 1.5 Pro (Experimental) - 1,000,000 tokens/minute
50 requests/day
2 requests/minute + 1,000,000 tokens/minute
100 requests/day
5 requests/minute + + + LearnLM 1.5 Pro (Experimental) + 1,500 requests/day
15 requests/minute Gemini 1.0 Pro @@ -257,9 +265,9 @@ This lists various services that provide free access or credits towards API-base Gemini Pro Experimental glhf.chat (Free Beta) - Email for API access - Any model on Hugging Face runnable on vLLM and fits on a A100 node (~640GB VRAM), including Llama 3.1 405B at FP8 + Any model on Hugging Face runnable on vLLM and fits on a A100 node (~640GB VRAM), including Llama 3.1 405B at FP8 + 480 requests/8 hours ## Providers with trial credits @@ -334,7 +342,7 @@ This lists various services that provide free access or credits towards API-base Grok - Hyperbolic$10DeepSeek V2.5 + Hyperbolic$10DeepSeek V2.5 Hermes 3 Llama 3.1 70B Llama 3 70B Instruct Llama 3.1 405B Base @@ -343,6 +351,7 @@ This lists various services that provide free access or credits towards API-base Llama 3.1 70B Instruct Llama 3.1 8B Instruct Llama 3.2 3B Instruct +Llama 3.3 70B Instruct Pixtral 12B (2409) Qwen QwQ 32B Preview Qwen2-VL 72B Instruct diff --git a/src/pull_available_models.py b/src/pull_available_models.py index 25ebcbb..b3b5092 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -15,7 +15,7 @@ MODEL_TO_NAME_MAPPING = { "@cf/deepseek-ai/deepseek-math-7b-instruct": "Deepseek Math 7B Instruct", "@cf/defog/sqlcoder-7b-2": "SQLCoder 7B 2", "@cf/fblgit/una-cybertron-7b-v2-bf16": "Una Cybertron 7B v2 (BF16)", - "@cf/google/gemma-2b-it-lora": "Gemma 2B Instruct (LoRA)", + "@cf/google/gemma-2b-it-lora": "Gemma 2B Instruct (LoRA)", "@cf/google/gemma-7b-it-lora": "Gemma 7B Instruct (LoRA)", "@cf/meta-llama/llama-2-7b-chat-hf-lora": "Llama 2 7B Chat (LoRA)", "@cf/meta/llama-2-7b-chat-fp16": "Llama 2 7B Chat (FP16)", @@ -149,7 +149,12 @@ MODEL_TO_NAME_MAPPING = { "google/learnlm-1.5-pro-experimental:free": "LearnLM 1.5 Pro Experimental", "google/gemini-exp-1114:free": "Gemini Experimental 1114", "qwen25-coder-32b-instruct": "Qwen2.5 Coder 32B Instruct", - "qwen/qwq-32b-preview": "Qwen QwQ 32B Preview" + "qwen/qwq-32b-preview": "Qwen QwQ 32B Preview", + "meta-llama/llama-3.3-70b-instruct": "Llama 3.3 70B Instruct", + "llama-3.3-70b-versatile": "Llama 3.3 70B", + "google/gemini-exp-1206:free": "Gemini Experimental 1206", + "llama3.1-nemotron-70b-instruct-fp8": "Llama 3.1 Nemotron 70B Instruct (FP8)", + "llama-3.3-70b-specdec": "Llama 3.3 70B (Speculative Decoding)" } @@ -182,6 +187,7 @@ OPENROUTER_IGNORED_MODELS = { 'google/gemini-exp-1121:free', 'google/learnlm-1.5-pro-experimental:free', 'google/gemini-exp-1114:free' + 'google/gemini-exp-1206:free' } # Ignore gemini experimental free models because rate limits mean they are unusable.