From f75f60bbcdf34b02018e889f008e61a3b422b358 Mon Sep 17 00:00:00 2001 From: Jun Siang Cheah Date: Fri, 27 Jun 2025 10:11:45 +0100 Subject: [PATCH] update --- README.md | 29 +++++++++++++++++++---------- src/pull_available_models.py | 33 ++++++++++++++------------------- 2 files changed, 33 insertions(+), 29 deletions(-) diff --git a/README.md b/README.md index 67f7e0e..142e78a 100644 --- a/README.md +++ b/README.md @@ -18,6 +18,7 @@ This lists various services that provide free access or credits towards API-base - [Mistral (La Plateforme)](#mistral-la-plateforme) - [Mistral (Codestral)](#mistral-codestral) - [HuggingFace Inference Providers](#huggingface-inference-providers) + - [Vercel AI Gateway](#vercel-ai-gateway) - [Cerebras](#cerebras) - [Groq](#groq) - [Together (Free)](#together-free) @@ -39,7 +40,6 @@ This lists various services that provide free access or credits towards API-base - [Alibaba Cloud (International) Model Studio](#alibaba-cloud-international-model-studio) - [Modal](#modal) - [Inference.net](#inferencenet) - - [CentML](#centml) - [nCompass](#ncompass) - [Kluster](#kluster) - [Hyperbolic](#hyperbolic) @@ -114,7 +114,7 @@ Models share a common quota. Data is used for training when used outside of the UK/CH/EEA/EU. - + @@ -165,6 +165,13 @@ HuggingFace Serverless Inference limited to models smaller than 10GB. Some popul - Various open models across supported providers +### [Vercel AI Gateway](https://vercel.com/docs/ai-gateway) + +Routes to various supported providers. + +**Limits:** [$5/month](https://vercel.com/docs/ai-gateway/pricing) + + ### [Cerebras](https://cloud.cerebras.ai/) Free tier restricted to 8K context. @@ -296,7 +303,9 @@ Extremely restrictive input/output token limits. Distributed, decentralized crypto-based compute. Data is sent to individual hosts. +**Limits:** [200 requests/day](https://chutes.ai/pricing) +- Various open models ### [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai) @@ -355,7 +364,6 @@ Data is sent to individual hosts. Very stringent payment verification for Google Cloud.
Model NameModel Limits
Gemini 2.5 Flash (Preview)250,000 tokens/minute
250 requests/day
10 requests/minute
Gemini 2.5 Flash250,000 tokens/minute
250 requests/day
10 requests/minute
Gemini 2.0 Flash1,000,000 tokens/minute
200 requests/day
15 requests/minute
Gemini 2.0 Flash-Lite1,000,000 tokens/minute
200 requests/day
30 requests/minute
Gemini 2.0 Flash (Experimental)250,000 tokens/minute
50 requests/day
10 requests/minute
- @@ -440,12 +448,6 @@ Very stringent payment verification for Google Cloud. **Models:** Various open models -### [CentML](https://centml.com) - -**Credits:** $1 - -**Models:** Various open models - ### [nCompass](https://ncompass.tech) **Credits:** $1 @@ -501,12 +503,19 @@ Very stringent payment verification for Google Cloud. **Credits:** $5 for 3 months **Models:** -- - E5-Mistral-7B-Instruct +- Llama 3.1 405B - Llama 3.1 8B +- Llama 3.2 1B +- Llama 3.2 3B - Llama 3.3 70B - Llama-4-Maverick-17B-128E-Instruct +- Llama-4-Scout-17B-16E-Instruct +- Llama-Guard-3-8B +- Qwen/QwQ-32B +- Qwen/Qwen2-Audio-7B-Instruct - Qwen/Qwen3-32B +- Whisper-Large-v3 - deepseek-ai/DeepSeek-R1-0528 - deepseek-ai/DeepSeek-R1-Distill-Llama-70B - deepseek-ai/DeepSeek-V3-0324 diff --git a/src/pull_available_models.py b/src/pull_available_models.py index 0a26187..f14cd85 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -517,7 +517,7 @@ def fetch_samba_models(logger): ret_models.append( { "id": model["model_id"], - "name": model["model_name"], + "name": model["model_name"] or model["model_id"], } ) ret_models = sorted(ret_models, key=lambda x: x["name"]) @@ -680,8 +680,8 @@ def main(): gemini_text_models = [ { - "id": "gemini-2.5-flash-preview-04-17", - "name": "Gemini 2.5 Flash (Preview)", + "id": "gemini-2.5-flash", + "name": "Gemini 2.5 Flash", "limits": gemini_models.get("gemini-2.5-flash", {}), }, { @@ -807,6 +807,12 @@ def main(): model_list_markdown += "- Various open models across supported providers\n" model_list_markdown += "\n" + # --- Vercel AI Gateway --- + model_list_markdown += "### [Vercel AI Gateway](https://vercel.com/docs/ai-gateway)\n\n" + model_list_markdown += "Routes to various supported providers.\n\n" + model_list_markdown += "**Limits:** [$5/month](https://vercel.com/docs/ai-gateway/pricing)\n\n" + model_list_markdown += "\n" + # --- Cerebras --- model_list_markdown += "### [Cerebras](https://cloud.cerebras.ai/)\n\n" model_list_markdown += "Free tier restricted to 8K context.\n\n" @@ -897,7 +903,9 @@ def main(): # --- Chutes --- model_list_markdown += "### [Chutes](https://chutes.ai/)\n\n" model_list_markdown += "Distributed, decentralized crypto-based compute.\n" - model_list_markdown += "Data is sent to individual hosts.\n\n" + model_list_markdown += "Data is sent to individual hosts.\n" + model_list_markdown += "**Limits:** [200 requests/day](https://chutes.ai/pricing)\n\n" + model_list_markdown += "- Various open models\n" if chutes_models: for model in chutes_models: model_list_markdown += f"- {model['name']}\n" @@ -934,13 +942,7 @@ def main(): "limits": {"requests/minute": 60}, }, ] - vertex_gemini_models = [ - { - "id": "gemini-2.5-pro-exp-03-25", - "name": "Gemini 2.5 Pro (Experimental)", - "limits": {"requests/minute": 10}, - } - ] + vertex_gemini_models = [] vertex_deepseek_models = [ { "id": "deepseek-r1-0528-maas", @@ -1067,13 +1069,6 @@ def main(): "requirements": "", "models_desc": "Various open models", }, - { - "name": "CentML", - "url": "https://centml.com", - "credits": "$1", - "requirements": "", - "models_desc": "Various open models", - }, { "name": "nCompass", "url": "https://ncompass.tech", @@ -1114,7 +1109,7 @@ def main(): trial_list_markdown += "**Credits:** $5 for 3 months\n\n" trial_list_markdown += "**Models:**\n" for model in samba_models: - trial_list_markdown += f"- {model['name']}\n" + trial_list_markdown += f"- {model['name']}\n" trial_list_markdown += "\n" # --- Scaleway Generative APIs (Trial - Table) ---
Model NameModel Limits
Gemini 2.5 Pro (Experimental)10 requests/minute
Shared Quota
Llama 3.2 90B Vision Instruct30 requests/minute
Free during preview
Llama 3.1 70B Instruct60 requests/minute
Free during preview
Llama 3.1 8B Instruct60 requests/minute
Free during preview