diff --git a/README.md b/README.md index 76825f1..5637792 100644 --- a/README.md +++ b/README.md @@ -74,15 +74,11 @@ This lists various services that provide free access or credits towards API-base 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). + 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
1,000,000 tokens/minute
25 requests/day
5 requests/minute - - Gemini 2.5 Flash (Preview) - - Gemini 2.0 Flash 1,000,000 tokens/minute
1,500 requests/day
15 requests/minute @@ -130,9 +126,14 @@ This lists various services that provide free access or credits towards API-base embedding-001 + NVIDIA NIM + Phone number verification required.
Models tend to be context window limited. + Various open models + 40 requests/minute + Mistral (La Plateforme) Free tier (Experiment plan) requires opting into data training, requires phone number verification. - Open and Proprietary Mistral models + Open and Proprietary Mistral models 1 request/second
500,000 tokens/minute
1,000,000,000 tokens/month Mistral (Codestral) @@ -145,15 +146,19 @@ This lists various services that provide free access or credits towards API-base Various open models Variable credits per month, currently $0.10 - Cerebras - Free tier restricted to 8K context + Cerebras + Free tier restricted to 8K context + Llama 4 Scout + 30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day + + Llama 3.1 8B 30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day Llama 3.3 70B 30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day - GroqAllam 2 7B7,000 requests/day
6,000 tokens/minute + GroqAllam 2 7B7,000 requests/day
6,000 tokens/minute DeepSeek R1 Distill Llama 70B1,000 requests/day
6,000 tokens/minute DeepSeek R1 Distill Qwen 32B1,000 requests/day
6,000 tokens/minute Distil Whisper Large v37,200 audio-seconds/minute
2,000 requests/day @@ -167,6 +172,7 @@ This lists various services that provide free access or credits towards API-base Llama 3.2 90B Vision3,500 requests/day
7,000 tokens/minute Llama 3.3 70B1,000 requests/day
6,000 tokens/minute Llama 3.3 70B (Speculative Decoding)1,000 requests/day
6,000 tokens/minute +Llama 4 Maverick 17B 128E Instruct1,000 requests/day
6,000 tokens/minute Llama 4 Scout Instruct1,000 requests/day
6,000 tokens/minute Llama Guard 3 8B14,400 requests/day
15,000 tokens/minute Mistral Saba 24B1,000 requests/day
6,000 tokens/minute @@ -200,17 +206,32 @@ This lists various services that provide free access or credits towards API-base DeepSeek R1 Distil Llama 70B - Cohere - 20 requests/min
1,000 requests/month + Cohere + 20 requests/minute
1,000 requests/month Command-R - Shared Limit + Shared Limit Command-R+ + + Command-R7B + Command-A - GitHub ModelsExtremely restrictive input/output token limits.
Rate limits dependent on Copilot subscription tier (Free/Pro/Business/Enterprise)AI21 Jamba 1.5 Large + + + Aya Expanse 8B + + + Aya Expanse 32B + + + Aya Vision 8B + + + 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 AI21 Jamba 1.5 Mini Codestral 25.01 Cohere Command R @@ -221,6 +242,7 @@ This lists various services that provide free access or credits towards API-base Cohere Embed v3 Multilingual DeepSeek-R1 DeepSeek-V3 +DeepSeek-V3-0324 JAIS 30b Chat Llama-3.2-11B-Vision-Instruct Llama-3.2-90B-Vision-Instruct @@ -257,7 +279,10 @@ This lists various services that provide free access or credits towards API-base Phi-4 Phi-4-mini-instruct Phi-4-multimodal-instruct -ChutesDistributed, decentralized crypto-based compute. Data is sent to individual hosts.DeepHermes 3 Llama 3 8B Preview +ChutesDistributed, decentralized crypto-based compute. Data is sent to individual hosts.DeepHermes 3 Llama 3 8B Preview +DeepSeek R1 +DeepSeek R1-Zero +DeepSeek V3 DeepSeek V3 0324 DeepSeek V3 Base Dolphin 3.0 Mistral 24B @@ -349,11 +374,6 @@ This lists various services that provide free access or credits towards API-base Gemini 2.0 Pro Experimental - - NVIDIA NIM - Phone number verification required. - Various open models - 40 requests/minute ## Providers with trial credits @@ -372,13 +392,13 @@ This lists various services that provide free access or credits towards API-base Together $1 when you add a payment method - Various open models + Various open models Fireworks $1 - Various open models + Various open models Unify @@ -390,19 +410,19 @@ This lists various services that provide free access or credits towards API-base Baseten $30 - Any supported model - pay by compute time + Any supported model - pay by compute time - Nebius + Nebius $1 - Various open models + Various open models Novita $0.5 for 1 year
$20 for 3 months for DeepSeek models with referral code + GitHub account connection - Various open models + Various open models Hyperbolic$1DeepSeek V3 DeepSeek V3 0324 Hermes 3 Llama 3.1 70B @@ -421,7 +441,7 @@ 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 monthsE5-Mistral-7B-Instruct +SambaNova Cloud$5 for 3 monthsE5-Mistral-7B-Instruct Llama 3.1 405B Llama 3.1 70B Llama 3.1 8B @@ -430,6 +450,7 @@ This lists various services that provide free access or credits towards API-base Llama 3.2 3B Llama 3.2 90B Vision Llama 3.3 70B +Llama-4-Maverick-17B-128E-Instruct Llama-4-Scout-17B-16E-Instruct Llama-Guard-3-8B Qwen/QwQ-32B @@ -459,7 +480,7 @@ This lists various services that provide free access or credits towards API-base AI21 $10 for 3 months - Jamba/Jurrasic-2 + Jamba family of models Upstage @@ -477,7 +498,7 @@ This lists various services that provide free access or credits towards API-base Alibaba Cloud (International) Model Studio Token/time-limited trials on a per-model basis - Various open and proprietary Qwen models + Various open and proprietary Qwen models Modal diff --git a/src/README_template.md b/src/README_template.md index 3454fad..c6a558b 100644 --- a/src/README_template.md +++ b/src/README_template.md @@ -28,13 +28,13 @@ This lists various services that provide free access or credits towards API-base Together $1 when you add a payment method - Various open models + Various open models Fireworks $1 - Various open models + Various open models Unify @@ -46,24 +46,24 @@ This lists various services that provide free access or credits towards API-base Baseten $30 - Any supported model - pay by compute time + Any supported model - pay by compute time - Nebius + Nebius $1 - Various open models + Various open models Novita $0.5 for 1 year
$20 for 3 months for DeepSeek models with referral code + GitHub account connection - Various open models + Various open models {{TRIAL_MODEL_LIST}} AI21 $10 for 3 months - Jamba/Jurrasic-2 + Jamba family of models Upstage @@ -81,7 +81,7 @@ This lists various services that provide free access or credits towards API-base Alibaba Cloud (International) Model Studio Token/time-limited trials on a per-model basis - Various open and proprietary Qwen models + Various open and proprietary Qwen models Modal diff --git a/src/pull_available_models.py b/src/pull_available_models.py index e981386..9951fee 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -269,6 +269,7 @@ MODEL_TO_NAME_MAPPING = { "gemma-3-27b-it": "Gemma 3 27B Instruct", "nvidia/llama-3.3-nemotron-super-49b-v1:free": "Llama 3.3 Nemotron Super 49B v1", "nvidia/llama-3.1-nemotron-nano-8b-v1:free": "Llama 3.1 Nemotron Nano 8B v1", + "meta-llama/llama-4-maverick-17b-128e-instruct": "Llama 4 Maverick 17B 128E Instruct", } @@ -950,15 +951,11 @@ def main(): table += "\n" table += f""" - 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 2.5 Pro (Experimental) {get_human_limits({"limits": gemini_models["gemini-2.0-pro-exp"]})} - - Gemini 2.5 Flash (Preview) - {get_human_limits({"limits": gemini_models["gemini-2.5-flash-preview"]})} - Gemini 2.0 Flash {get_human_limits({"limits": gemini_models["gemini-2.0-flash"]})} @@ -1006,11 +1003,18 @@ def main(): embedding-001 """ + + table += """ + NVIDIA NIM + Phone number verification required.
Models tend to be context window limited. + Various open models + 40 requests/minute + """ table += """ Mistral (La Plateforme) Free tier (Experiment plan) requires opting into data training, requires phone number verification. - Open and Proprietary Mistral models + Open and Proprietary Mistral models 1 request/second
500,000 tokens/minute
1,000,000,000 tokens/month """ @@ -1029,8 +1033,12 @@ def main(): """ table += """ - Cerebras - Free tier restricted to 8K context + Cerebras + Free tier restricted to 8K context + Llama 4 Scout + 30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day + + Llama 3.1 8B 30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day @@ -1079,16 +1087,31 @@ def main(): """ table += """ - Cohere - 20 requests/min
1,000 requests/month + Cohere + 20 requests/minute
1,000 requests/month Command-R - Shared Limit + Shared Limit Command-R+ + + Command-R7B + Command-A + + + Aya Expanse 8B + + + Aya Expanse 32B + + + Aya Vision 8B + + + Aya Vision 32B """ for idx, model in enumerate(github_models): @@ -1163,13 +1186,6 @@ def main(): Gemini 2.0 Pro Experimental """ - table += """ - NVIDIA NIM - Phone number verification required. - Various open models - 40 requests/minute - """ - table += "" trial_table = ""