From 3869f1222b0e7b528bb93e2f6965ba83da4a41d7 Mon Sep 17 00:00:00 2001 From: Jun Siang Cheah Date: Fri, 11 Apr 2025 20:34:23 +0100 Subject: [PATCH] update --- README.md | 129 +++++++++++++++++++---------------- src/pull_available_models.py | 26 +++++-- 2 files changed, 89 insertions(+), 66 deletions(-) diff --git a/README.md b/README.md index c60ea8c..f853ed1 100644 --- a/README.md +++ b/README.md @@ -23,57 +23,57 @@ This lists various services that provide free access or credits towards API-base -OpenRouter20 requests/minute
50 requests/day
1000 requests/day with $10 credit balanceBytedance 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 -DeepSeek V3 Base -Dolphin 3.0 Mistral 24B -Dolphin 3.0 R1 Mistral 24B -Featherless Qwerky 72B -Gemini 2.5 Pro Experimental 03-25 -Gemma 2 9B Instruct -Gemma 3 12B Instruct -Gemma 3 1B Instruct -Gemma 3 27B Instruct -Gemma 3 4B Instruct -Kimi VL A3B Thinking -Llama 3.1 8B Instruct -Llama 3.1 Nemotron 70B Instruct -Llama 3.1 Nemotron Nano 8B v1 -Llama 3.1 Nemotron Ultra 253B v1 -Llama 3.2 11B Vision Instruct -Llama 3.2 1B Instruct -Llama 3.2 3B Instruct -Llama 3.3 70B Instruct -Llama 3.3 Nemotron Super 49B v1 -Llama 4 Maverick -Llama 4 Scout -Mistral 7B Instruct -Mistral Nemo -Mistral Small 24B Instruct 2501 -Mistral Small 3.1 24B Instruct -Molmo 7B D -Moonlight-16B-A3B-Instruct -OlympicCoder 32B -OlympicCoder 7B -Qwen 2.5 72B Instruct -Qwen 2.5 7B 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 -Qwen2.5 VL 72B Instruct -Reka Flash 3 -Rogue Rose 103B v0.2 -Zephyr 7B Beta +OpenRouter20 requests/minute
50 requests/day
1000 requests/day with $10 credit balanceBytedance 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 +DeepSeek V3 Base +Dolphin 3.0 Mistral 24B +Dolphin 3.0 R1 Mistral 24B +Featherless Qwerky 72B +Gemini 2.5 Pro Experimental 03-25 +Gemma 2 9B Instruct +Gemma 3 12B Instruct +Gemma 3 1B Instruct +Gemma 3 27B Instruct +Gemma 3 4B Instruct +Kimi VL A3B Thinking +Llama 3.1 8B Instruct +Llama 3.1 Nemotron 70B Instruct +Llama 3.1 Nemotron Nano 8B v1 +Llama 3.1 Nemotron Ultra 253B v1 +Llama 3.2 11B Vision Instruct +Llama 3.2 1B Instruct +Llama 3.2 3B Instruct +Llama 3.3 70B Instruct +Llama 3.3 Nemotron Super 49B v1 +Llama 4 Maverick +Llama 4 Scout +Mistral 7B Instruct +Mistral Nemo +Mistral Small 24B Instruct 2501 +Mistral Small 3.1 24B Instruct +Molmo 7B D +Moonlight-16B-A3B-Instruct +OlympicCoder 32B +OlympicCoder 7B +Qwen 2.5 72B Instruct +Qwen 2.5 7B 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 +Qwen2.5 VL 72B Instruct +Reka Flash 3 +Rogue Rose 103B v0.2 +Zephyr 7B Beta Google AI Studio Data is used for training (when used outside of the UK/CH/EEA/EU). @@ -196,15 +196,15 @@ This lists various services that provide free access or credits towards API-base Together - Llama 3.2 11B Vision Instruct + Llama 3.2 11B Vision Instruct - Llama 3.3 70B Instruct + Llama 3.3 70B Instruct - DeepSeek R1 Distil Llama 70B + DeepSeek R1 Distil Llama 70B Cohere @@ -232,7 +232,7 @@ This lists various services that provide free access or credits towards API-base Aya Vision 32B - GitHub ModelsExtremely restrictive input/output token limits.
Rate limits dependent on Copilot subscription tier (Free/Pro/Business/Enterprise)AI21 Jamba 1.5 Large + GitHub ModelsExtremely restrictive input/output token limits.
Rate limits dependent on Copilot subscription tier (Free/Pro/Business/Enterprise)AI21 Jamba 1.5 Large AI21 Jamba 1.5 Mini Codestral 25.01 Cohere Command R @@ -242,7 +242,6 @@ This lists various services that provide free access or credits towards API-base Cohere Embed v3 English Cohere Embed v3 Multilingual DeepSeek-R1 -DeepSeek-V3 DeepSeek-V3-0324 JAIS 30b Chat Llama-3.2-11B-Vision-Instruct @@ -302,13 +301,14 @@ This lists various services that provide free access or credits towards API-base OlympicCoder 7B Qwen 2.5 VL 32B Instruct Reka Flash 3 -Cloudflare Workers AI10,000 neurons/dayDeepSeek R1 Distill Qwen 32B +Cloudflare Workers AI10,000 neurons/dayDeepSeek R1 Distill Qwen 32B Deepseek Coder 6.7B Base (AWQ) Deepseek Coder 6.7B Instruct (AWQ) Deepseek Math 7B Instruct Discolm German 7B v1 (AWQ) Falcom 7B Instruct Gemma 2B Instruct (LoRA) +Gemma 3 12B Instruct Gemma 7B Instruct Gemma 7B Instruct (LoRA) Hermes 2 Pro Mistral 7B @@ -333,6 +333,7 @@ This lists various services that provide free access or credits towards API-base Mistral 7B Instruct v0.1 (AWQ) Mistral 7B Instruct v0.2 Mistral 7B Instruct v0.2 (LoRA) +Mistral Small 3.1 24B Instruct Neural Chat 7B v3.1 (AWQ) OpenChat 3.5 0106 OpenHermes 2.5 Mistral 7B (AWQ) @@ -341,14 +342,24 @@ This lists various services that provide free access or credits towards API-base Qwen 1.5 1.8B Chat Qwen 1.5 14B Chat (AWQ) Qwen 1.5 7B Chat (AWQ) +Qwen 2.5 Coder 32B Instruct +Qwen QwQ 32B SQLCoder 7B 2 Starling LM 7B Beta TinyLlama 1.1B Chat v1.0 Una Cybertron 7B v2 (BF16) Zephyr 7B Beta (AWQ) - Google Cloud Vertex AI - Very stringent payment verification for Google Cloud. + Google Cloud Vertex AI + Very stringent payment verification for Google Cloud. + Llama 4 Maverick Instruct + Llama 4 API Service free during preview.
60 requests/minute + + + Llama 4 Scout Instruct + Llama 4 API Service free during preview.
60 requests/minute + + Llama 3.1 70B Instruct Llama 3.1 API Service free during preview.
60 requests/minute diff --git a/src/pull_available_models.py b/src/pull_available_models.py index cba224a..ab14f7b 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -272,6 +272,10 @@ MODEL_TO_NAME_MAPPING = { "meta-llama/llama-4-maverick-17b-128e-instruct": "Llama 4 Maverick 17B 128E Instruct", "moonshotai/kimi-vl-a3b-thinking:free": "Kimi VL A3B Thinking", "moonshotai/kimi-vl-a3b-thinking": "Kimi VL A3B Thinking", + "@cf/mistralai/mistral-small-3.1-24b-instruct": "Mistral Small 3.1 24B Instruct", + "@cf/google/gemma-3-12b-it": "Gemma 3 12B Instruct", + "@cf/qwen/qwq-32b": "Qwen QwQ 32B", + "@cf/qwen/qwen2.5-coder-32b-instruct": "Qwen 2.5 Coder 32B Instruct", } @@ -852,10 +856,10 @@ def main(): table += 'OpenRouter' table += "" table += ( - f'{get_human_limits(model)}
1000 requests/day with $10 credit balance' + f'{get_human_limits(model)}
1000 requests/day with $10 credit balance' ) - table += f"{model['name']}" + table += f"{model['name']}" table += "" table += "\n" @@ -983,15 +987,15 @@ def main(): table += """ Together - Llama 3.2 11B Vision Instruct + Llama 3.2 11B Vision Instruct - Llama 3.3 70B Instruct + Llama 3.3 70B Instruct - DeepSeek R1 Distil Llama 70B + DeepSeek R1 Distil Llama 70B """ @@ -1064,8 +1068,16 @@ def main(): table += "\n" table += """ - Google Cloud Vertex AI - Very stringent payment verification for Google Cloud. + Google Cloud Vertex AI + Very stringent payment verification for Google Cloud. + Llama 4 Maverick Instruct + Llama 4 API Service free during preview.
60 requests/minute + + + Llama 4 Scout Instruct + Llama 4 API Service free during preview.
60 requests/minute + + Llama 3.1 70B Instruct Llama 3.1 API Service free during preview.
60 requests/minute