From f295023c896bf6eecdf04c3f93f6c510fba9e4a5 Mon Sep 17 00:00:00 2001 From: Jun Siang Cheah Date: Sat, 29 Mar 2025 12:07:50 +0000 Subject: [PATCH] update --- README.md | 30 +++++++++++++++++++++--------- src/pull_available_models.py | 22 ++++++++++++++++++---- 2 files changed, 39 insertions(+), 13 deletions(-) diff --git a/README.md b/README.md index b35cece..0769988 100644 --- a/README.md +++ b/README.md @@ -23,16 +23,20 @@ This lists various services that provide free access or credits towards API-base -OpenRouter20 requests/minute
200 requests/dayDeepHermes 3 Llama 3 8B Preview +OpenRouter20 requests/minute
200 requests/dayBytedance UI Tars 72B +DeepHermes 3 Llama 3 8B Preview DeepSeek R1 DeepSeek R1 Distill Llama 70B DeepSeek R1 Distill Qwen 14B DeepSeek R1 Distill Qwen 32B DeepSeek R1 Zero DeepSeek V3 +DeepSeek V3 0324 Dolphin 3.0 Mistral 24B Dolphin 3.0 R1 Mistral 24B +Featherless Qwerky 72B Gemini 2.0 Flash Lite Preview 02-05 +Gemini 2.5 Pro Experimental 03-25 Gemma 2 9B Instruct Gemma 3 12B Instruct Gemma 3 1B Instruct @@ -48,6 +52,8 @@ This lists various services that provide free access or credits towards API-base Mistral 7B Instruct Mistral Nemo Mistral Small 24B Instruct 2501 +Mistral Small 3.1 24B Instruct +Molmo 7B D Moonlight-16B-A3B-Instruct Mythomax L2 13B OlympicCoder 32B @@ -57,6 +63,9 @@ This lists various services that provide free access or credits towards API-base Phi-3 Mini 128k Instruct Qwen 2 7B Instruct Qwen 2.5 72B Instruct +Qwen 2.5 VL 32B Instruct +Qwen 2.5 VL 3B Instruct +Qwen 2.5 VL 7B Instruct Qwen QwQ 32B Qwen QwQ 32B Preview Qwen2.5 Coder 32B Instruct @@ -65,10 +74,13 @@ This lists various services that provide free access or credits towards API-base Rogue Rose 103B v0.2 Toppy M 7B Zephyr 7B Beta -mistralai/mistral-small-3.1-24b-instruct:free Google AI Studio Data is used for training (when used outside of the UK/CH/EEA/EU). + Gemini 2.5 Pro (Experimental) + 5,000,000 tokens/day
2,000,000 tokens/minute
50 requests/day
2 requests/minute + + Gemini 2.0 Flash 1,000,000 tokens/minute
1,500 requests/day
15 requests/minute @@ -80,10 +92,6 @@ This lists various services that provide free access or credits towards API-base Gemini 2.0 Flash (Experimental) 4,000,000 tokens/minute
1,500 requests/day
10 requests/minute - - Gemini 2.0 Pro (Experimental) - 5,000,000 tokens/day
2,000,000 tokens/minute
50 requests/day
2 requests/minute - Gemini 1.5 Flash 1,000,000 tokens/minute
1,500 requests/day
15 requests/minute @@ -155,7 +163,7 @@ This lists various services that provide free access or credits towards API-base Qwen QwQ 32B1,000 requests/day
6,000 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 -OVH AI Endpoints (Free Beta)Codestral Mamba 7B v0.112 requests/minute +OVH AI Endpoints (Free Beta)Codestral Mamba 7B v0.112 requests/minute DeepSeek R1 Distill Llama 70B12 requests/minute Llama 3.1 70B Instruct12 requests/minute Llama 3.1 8B Instruct12 requests/minute @@ -164,6 +172,7 @@ This lists various services that provide free access or credits towards API-base Mistral 7B Instruct v0.312 requests/minute Mistral Nemo 240712 requests/minute Mixtral 8x7B Instruct12 requests/minute +Qwen2.5 Coder 32B Instruct12 requests/minute Together @@ -365,7 +374,8 @@ This lists various services that provide free access or credits towards API-base $0.5 for 1 year
$20 for 3 months for DeepSeek models with referral code + GitHub account connection Various open models - Hyperbolic$1DeepSeek V3 + Hyperbolic$1DeepSeek V3 +DeepSeek V3 0324 Hermes 3 Llama 3.1 70B Llama 3 70B Instruct Llama 3.1 405B Base @@ -382,7 +392,8 @@ This lists various services that provide free access or credits towards API-base Qwen2.5 Coder 32B Instruct Qwen2.5 VL 72B Instruct Qwen2.5 VL 7B Instruct -SambaNova Cloud$5 for 3 monthsLlama 3.1 405B +SambaNova Cloud$5 for 3 monthsE5-Mistral-7B-Instruct +Llama 3.1 405B Llama 3.1 70B Llama 3.1 8B Llama 3.2 11B Vision @@ -399,6 +410,7 @@ This lists various services that provide free access or credits towards API-base allenai/Llama-3.1-Tulu-3-405B deepseek-ai/DeepSeek-R1 deepseek-ai/DeepSeek-R1-Distill-Llama-70B +deepseek-ai/DeepSeek-V3-0324 tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3 tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3 Scaleway Generative APIs1,000,000 free tokensBGE-Multilingual-Gemma2 diff --git a/src/pull_available_models.py b/src/pull_available_models.py index 331dd9d..77e0727 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -226,6 +226,16 @@ MODEL_TO_NAME_MAPPING = { "google/gemma-3-4b-it:free": "Gemma 3 4B Instruct", "open-r1/olympiccoder-32b:free": "OlympicCoder 32B", "open-r1/olympiccoder-7b:free": "OlympicCoder 7B", + "featherless/qwerky-72b:free": "Featherless Qwerky 72B", + "qwen/qwen2.5-vl-32b-instruct:free": "Qwen 2.5 VL 32B Instruct", + "deepseek/deepseek-chat-v3-0324:free": "DeepSeek V3 0324", + "qwen/qwen-2.5-vl-7b-instruct:free": "Qwen 2.5 VL 7B Instruct", + "deepseek-ai/deepseek-v3-0324": "DeepSeek V3 0324", + "allenai/molmo-7b-d:free": "Molmo 7B D", + "qwen/qwen2.5-vl-3b-instruct:free": "Qwen 2.5 VL 3B Instruct", + "google/gemini-2.5-pro-exp-03-25:free": "Gemini 2.5 Pro Experimental 03-25", + "mistralai/mistral-small-3.1-24b-instruct:free": "Mistral Small 3.1 24B Instruct", + "bytedance-research/ui-tars-72b:free": "Bytedance UI Tars 72B", } @@ -303,6 +313,8 @@ def get_groq_limits_for_stt_model(model_id, logger): def get_groq_limits_for_model(model_id, script_dir, logger): if "whisper" in model_id: return get_groq_limits_for_stt_model(model_id, logger) + if "tts" in model_id: + return None logger.info(f"Getting limits for chat model {model_id}...") r = requests.post( "https://api.groq.com/openai/v1/chat/completions", @@ -352,6 +364,8 @@ def fetch_groq_models(logger): for model, future in futures: limits = future.result() + if limits is None: + continue ret_models.append( { "id": model["id"], @@ -871,6 +885,10 @@ def main(): table += f""" Google AI Studio Data is used for training (when used outside of the UK/CH/EEA/EU). + Gemini 2.5 Pro (Experimental) + {get_human_limits({"limits": gemini_models["gemini-2.0-pro-exp"]})} + + Gemini 2.0 Flash {get_human_limits({"limits": gemini_models["gemini-2.0-flash"]})} @@ -882,10 +900,6 @@ def main(): Gemini 2.0 Flash (Experimental) {get_human_limits({"limits": gemini_models["gemini-2.0-flash-exp"]})} - - Gemini 2.0 Pro (Experimental) - {get_human_limits({"limits": gemini_models["gemini-2.0-pro-exp"]})} - Gemini 1.5 Flash {get_human_limits({"limits": gemini_models["gemini-1.5-flash"]})}