diff --git a/README.md b/README.md index 2681a5f..74df65a 100644 --- a/README.md +++ b/README.md @@ -13,70 +13,72 @@ This lists various services that provide free access or credits towards API-base ## Free Providers - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +### [OpenRouter](https://openrouter.ai) + +[20 requests/minute
50 requests/day
1000 requests/day with $10 credit balance](https://openrouter.ai/docs/api-reference/limits) + +Models share a common quota. + +- [Bytedance UI Tars 72B](https://openrouter.ai/bytedance-research/ui-tars-72b:free) +- [DeepCoder 14B Preview](https://openrouter.ai/agentica-org/deepcoder-14b-preview:free) +- [DeepHermes 3 Llama 3 8B Preview](https://openrouter.ai/nousresearch/deephermes-3-llama-3-8b-preview:free) +- [DeepSeek R1](https://openrouter.ai/deepseek/deepseek-r1:free) +- [DeepSeek R1 Distill Llama 70B](https://openrouter.ai/deepseek/deepseek-r1-distill-llama-70b:free) +- [DeepSeek R1 Distill Qwen 14B](https://openrouter.ai/deepseek/deepseek-r1-distill-qwen-14b:free) +- [DeepSeek R1 Distill Qwen 32B](https://openrouter.ai/deepseek/deepseek-r1-distill-qwen-32b:free) +- [DeepSeek R1 Zero](https://openrouter.ai/deepseek/deepseek-r1-zero:free) +- [DeepSeek V3](https://openrouter.ai/deepseek/deepseek-chat:free) +- [DeepSeek V3 0324](https://openrouter.ai/deepseek/deepseek-chat-v3-0324:free) +- [DeepSeek V3 Base](https://openrouter.ai/deepseek/deepseek-v3-base:free) +- [Dolphin 3.0 Mistral 24B](https://openrouter.ai/cognitivecomputations/dolphin3.0-mistral-24b:free) +- [Dolphin 3.0 R1 Mistral 24B](https://openrouter.ai/cognitivecomputations/dolphin3.0-r1-mistral-24b:free) +- [Featherless Qwerky 72B](https://openrouter.ai/featherless/qwerky-72b:free) +- [Gemini 2.5 Pro Experimental 03-25](https://openrouter.ai/google/gemini-2.5-pro-exp-03-25:free) +- [Gemma 2 9B Instruct](https://openrouter.ai/google/gemma-2-9b-it:free) +- [Gemma 3 12B Instruct](https://openrouter.ai/google/gemma-3-12b-it:free) +- [Gemma 3 1B Instruct](https://openrouter.ai/google/gemma-3-1b-it:free) +- [Gemma 3 27B Instruct](https://openrouter.ai/google/gemma-3-27b-it:free) +- [Gemma 3 4B Instruct](https://openrouter.ai/google/gemma-3-4b-it:free) +- [Kimi VL A3B Thinking](https://openrouter.ai/moonshotai/kimi-vl-a3b-thinking:free) +- [Llama 3.1 8B Instruct](https://openrouter.ai/meta-llama/llama-3.1-8b-instruct:free) +- [Llama 3.1 Nemotron 70B Instruct](https://openrouter.ai/nvidia/llama-3.1-nemotron-70b-instruct:free) +- [Llama 3.1 Nemotron Nano 8B v1](https://openrouter.ai/nvidia/llama-3.1-nemotron-nano-8b-v1:free) +- [Llama 3.1 Nemotron Ultra 253B v1](https://openrouter.ai/nvidia/llama-3.1-nemotron-ultra-253b-v1:free) +- [Llama 3.2 11B Vision Instruct](https://openrouter.ai/meta-llama/llama-3.2-11b-vision-instruct:free) +- [Llama 3.2 1B Instruct](https://openrouter.ai/meta-llama/llama-3.2-1b-instruct:free) +- [Llama 3.2 3B Instruct](https://openrouter.ai/meta-llama/llama-3.2-3b-instruct:free) +- [Llama 3.3 70B Instruct](https://openrouter.ai/meta-llama/llama-3.3-70b-instruct:free) +- [Llama 3.3 Nemotron Super 49B v1](https://openrouter.ai/nvidia/llama-3.3-nemotron-super-49b-v1:free) +- [Llama 4 Maverick](https://openrouter.ai/meta-llama/llama-4-maverick:free) +- [Llama 4 Scout](https://openrouter.ai/meta-llama/llama-4-scout:free) +- [Mistral 7B Instruct](https://openrouter.ai/mistralai/mistral-7b-instruct:free) +- [Mistral Nemo](https://openrouter.ai/mistralai/mistral-nemo:free) +- [Mistral Small 24B Instruct 2501](https://openrouter.ai/mistralai/mistral-small-24b-instruct-2501:free) +- [Mistral Small 3.1 24B Instruct](https://openrouter.ai/mistralai/mistral-small-3.1-24b-instruct:free) +- [Molmo 7B D](https://openrouter.ai/allenai/molmo-7b-d:free) +- [Moonlight-16B-A3B-Instruct](https://openrouter.ai/moonshotai/moonlight-16b-a3b-instruct:free) +- [OlympicCoder 32B](https://openrouter.ai/open-r1/olympiccoder-32b:free) +- [OlympicCoder 7B](https://openrouter.ai/open-r1/olympiccoder-7b:free) +- [QwQ 32B ArliAI RpR v1](https://openrouter.ai/arliai/qwq-32b-arliai-rpr-v1:free) +- [Qwen 2.5 72B Instruct](https://openrouter.ai/qwen/qwen-2.5-72b-instruct:free) +- [Qwen 2.5 7B Instruct](https://openrouter.ai/qwen/qwen-2.5-7b-instruct:free) +- [Qwen 2.5 VL 32B Instruct](https://openrouter.ai/qwen/qwen2.5-vl-32b-instruct:free) +- [Qwen 2.5 VL 3B Instruct](https://openrouter.ai/qwen/qwen2.5-vl-3b-instruct:free) +- [Qwen 2.5 VL 7B Instruct](https://openrouter.ai/qwen/qwen-2.5-vl-7b-instruct:free) +- [Qwen QwQ 32B](https://openrouter.ai/qwen/qwq-32b:free) +- [Qwen QwQ 32B Preview](https://openrouter.ai/qwen/qwq-32b-preview:free) +- [Qwen2.5 Coder 32B Instruct](https://openrouter.ai/qwen/qwen-2.5-coder-32b-instruct:free) +- [Qwen2.5 VL 72B Instruct](https://openrouter.ai/qwen/qwen2.5-vl-72b-instruct:free) +- [Reka Flash 3](https://openrouter.ai/rekaai/reka-flash-3:free) +- [Rogue Rose 103B v0.2](https://openrouter.ai/sophosympatheia/rogue-rose-103b-v0.2:free) +- [Zephyr 7B Beta](https://openrouter.ai/huggingfaceh4/zephyr-7b-beta:free) + +### [Google AI Studio](https://aistudio.google.com) + +Data is used for training when used outside of the UK/CH/EEA/EU. + +
ProviderProvider Limits/NotesModel NameModel Limits
OpenRouter20 requests/minute
50 requests/day
1000 requests/day with $10 credit balance		Bytedance UI Tars 72BShared Quota
DeepCoder 14B Preview
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
QwQ 32B ArliAI RpR v1
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 StudioData 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
+ @@ -90,63 +92,66 @@ This lists various services that provide free access or credits towards API-base - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +
Model NameModel Limits
Gemini 2.5 Pro (Experimental)5,000,000 tokens/day
1,000,000 tokens/minute
25 requests/day
5 requests/minute
Gemini 2.0 Flash1,000,000 tokens/minute
1,500 requests/day
15 requests/minute
Gemini 2.0 Flash-Lite1,000,000 tokens/minute
1,500 requests/day
30 requests/minute
Gemini 2.0 Flash (Experimental)4,000,000 tokens/minute
1,500 requests/day
10 requests/minute
Gemma 3 1B Instruct15,000 tokens/minute
14,400 requests/day
30 requests/minute
text-embedding-004150 batch requests/minute
1,500 requests/minute
100 content/batch
Shared Quota
embedding-001
NVIDIA NIMPhone number verification required.
Models tend to be context window limited.		Various open models40 requests/minute
Mistral (La Plateforme)Free tier (Experiment plan) requires opting into data training, requires phone number verification.Open and Proprietary Mistral models1 request/second
500,000 tokens/minute
1,000,000,000 tokens/month
Mistral (Codestral)Currently free to use, monthly subscription based, requires phone number verification.Codestral30 requests/minute
2,000 requests/day
HuggingFace Serverless InferenceLimited to models smaller than 10GB.
Some popular models are supported even if they exceed 10GB.		Various open modelsVariable credits per month, currently $0.10
CerebrasFree tier restricted to 8K contextLlama 4 Scout30 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 8B30 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 70B30 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
+ +### [NVIDIA NIM](https://build.nvidia.com/explore/discover) + +Phone number verification required. Models tend to be context window limited. + +- [Various open models](https://build.nvidia.com/models) (40 requests/minute) + +### [Mistral (La Plateforme)](https://console.mistral.ai/) + +Free tier (Experiment plan) requires opting into data training, requires phone number verification. + +- [Open and Proprietary Mistral models](https://docs.mistral.ai/getting-started/models/models_overview/) (1 request/second, 500,000 tokens/minute, 1,000,000,000 tokens/month) + +### [Mistral (Codestral)](https://codestral.mistral.ai/) + +Currently free to use, monthly subscription based, requires phone number verification. + +- Codestral (30 requests/minute, 2,000 requests/day) + +### [HuggingFace Serverless Inference](https://huggingface.co/docs/api-inference/en/index) + +Limited to models smaller than 10GB. Some popular models are supported even if they exceed 10GB. + +- Various open models ([Variable credits per month, currently $0.10](https://huggingface.co/docs/api-inference/pricing)) + +### [Cerebras](https://cloud.cerebras.ai/) + +Free tier restricted to 8K context. + + + + + +
Model NameModel Limits
Llama 4 Scout30 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 8B30 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 70B30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day
+ +### [Groq](https://console.groq.com) + + + - - - - - - - - - +
Model NameModel Limits
Allam 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
Gemma 2 9B Instruct14,400 requests/day
15,000 tokens/minute
Llama 3 70B14,400 requests/day
6,000 tokens/minute
Llama 3 8B14,400 requests/day
6,000 tokens/minute
Llama 3.1 8B14,400 requests/day
6,000 tokens/minute
Llama 3.2 11B Vision7,000 requests/day
7,000 tokens/minute
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 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
Qwen 2.5 32B1,000 requests/day
6,000 tokens/minute
Qwen 2.5 Coder 32B1,000 requests/day
6,000 tokens/minute
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)DeepSeek R1 Distill Llama 70B12 requests/minute
+ +### [OVH AI Endpoints (Free Beta)](https://endpoints.ai.cloud.ovh.net/) + + + @@ -157,278 +162,320 @@ This lists various services that provide free access or credits towards API-base - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +
Model NameModel Limits
DeepSeek R1 Distill Llama 70B12 requests/minute
Llama 3.1 70B Instruct12 requests/minute
Llama 3.1 8B Instruct12 requests/minute
Llama 3.3 70B Instruct12 requests/minute
Mixtral 8x7B Instruct v0.112 requests/minute
Qwen 2.5 VL 72B Instruct12 requests/minute
Qwen2.5 Coder 32B Instruct12 requests/minute
TogetherUp to 60 requests/minuteLlama 3.2 11B Vision Instruct
Llama 3.3 70B Instruct
DeepSeek R1 Distil Llama 70B
Cohere20 requests/minute
1,000 requests/month		Command-AShared Limit
Command-R7B
Command-R+
Command-R
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
Cohere Command R 08-2024
Cohere Command R+
Cohere Command R+ 08-2024
Cohere Embed v3 English
Cohere Embed v3 Multilingual
DeepSeek-R1
DeepSeek-V3-0324
JAIS 30b Chat
Llama 4 Maverick 17B 128E Instruct FP8
Llama 4 Scout 17B 16E Instruct
Llama-3.2-11B-Vision-Instruct
Llama-3.2-90B-Vision-Instruct
Llama-3.3-70B-Instruct
Meta-Llama-3-70B-Instruct
Meta-Llama-3-8B-Instruct
Meta-Llama-3.1-405B-Instruct
Meta-Llama-3.1-70B-Instruct
Meta-Llama-3.1-8B-Instruct
Ministral 3B
Mistral Large
Mistral Large (2407)
Mistral Large 24.11
Mistral Nemo
Mistral Small
Mistral Small 3.1
OpenAI GPT-4o
OpenAI GPT-4o mini
OpenAI Text Embedding 3 (large)
OpenAI Text Embedding 3 (small)
OpenAI o1
OpenAI o1-mini
OpenAI o1-preview
OpenAI o3-mini
Phi-3-medium instruct (128k)
Phi-3-medium instruct (4k)
Phi-3-mini instruct (128k)
Phi-3-mini instruct (4k)
Phi-3-small instruct (128k)
Phi-3-small instruct (8k)
Phi-3.5-MoE instruct (128k)
Phi-3.5-mini instruct (128k)
Phi-3.5-vision instruct (128k)
Phi-4
Phi-4-mini-instruct
Phi-4-multimodal-instruct
ChutesDistributed, decentralized crypto-based compute. Data is sent to individual hosts.DeepCoder 14B Preview
DeepHermes 3 Llama 3 8B Preview
DeepSeek R1
DeepSeek R1-Zero
DeepSeek V3
DeepSeek V3 0324
DeepSeek V3 Base
Dolphin 3.0 Mistral 24B
Dolphin 3.0 R1 Mistral 24B
Gemma 3 12B Instruct
Gemma 3 1B Instruct
Gemma 3 4B Instruct
Kimi VL A3B Thinking
Llama 3.1 Nemotron Nano 8B v1
Llama 3.1 Nemotron Ultra 253B v1
Llama 3.3 Nemotron Super 49B v1
Llama 4 Maverick 17B 128E Instruct FP8
Llama 4 Scout 17B 16E Instruct
Mistral Small 3.1 24B Instruct 2503
OlympicCoder 32B
OlympicCoder 7B
QwQ 32B ArliAI RpR v1
Qwen 2.5 VL 32B Instruct
Reka Flash 3
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
Llama 2 13B Chat (AWQ)
Llama 2 7B Chat (FP16)
Llama 2 7B Chat (INT8)
Llama 2 7B Chat (LoRA)
Llama 3 8B Instruct
Llama 3 8B Instruct
Llama 3 8B Instruct (AWQ)
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct (AWQ)
Llama 3.1 8B Instruct (FP8)
Llama 3.2 11B Vision Instruct
Llama 3.2 1B Instruct
Llama 3.2 3B Instruct
Llama 3.3 70B Instruct (FP8)
Llama 4 Scout Instruct
Llama Guard 3 8B
LlamaGuard 7B (AWQ)
Mistral 7B Instruct v0.1
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)
Phi-2
Qwen 1.5 0.5B Chat
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 AIVery stringent payment verification for Google Cloud.Gemini 2.5 Pro (Experimental)10 requests/minute
Shared Quota
+ +### [Together](https://together.ai) + +Up to 60 requests/minute. + +- [Llama 3.2 11B Vision Instruct](https://together.ai/llama-3-2-11b-free) +- [Llama 3.3 70B Instruct](https://together.ai/llama-3-3-70b-free) +- [DeepSeek R1 Distil Llama 70B](https://together.ai/deepseek-r1-distilled-llama-70b-free) + +### [Cohere](https://cohere.com) + +[20 requests/minute
1,000 requests/month](https://docs.cohere.com/docs/rate-limits) + +Models share a common quota. + +- Command-A +- Command-R7B +- Command-R+ +- Command-R +- Aya Expanse 8B +- Aya Expanse 32B +- Aya Vision 8B +- Aya Vision 32B + +### [GitHub Models](https://github.com/marketplace/models) + +Extremely restrictive input/output token limits. [Rate limits dependent on Copilot subscription tier (Free/Pro/Business/Enterprise)](https://docs.github.com/en/github-models/prototyping-with-ai-models#rate-limits) + +- AI21 Jamba 1.5 Large +- AI21 Jamba 1.5 Mini +- Codestral 25.01 +- Cohere Command R +- Cohere Command R 08-2024 +- Cohere Command R+ +- Cohere Command R+ 08-2024 +- Cohere Embed v3 English +- Cohere Embed v3 Multilingual +- DeepSeek-R1 +- DeepSeek-V3-0324 +- JAIS 30b Chat +- Llama 4 Maverick 17B 128E Instruct FP8 +- Llama 4 Scout 17B 16E Instruct +- Llama-3.2-11B-Vision-Instruct +- Llama-3.2-90B-Vision-Instruct +- Llama-3.3-70B-Instruct +- Meta-Llama-3-70B-Instruct +- Meta-Llama-3-8B-Instruct +- Meta-Llama-3.1-405B-Instruct +- Meta-Llama-3.1-70B-Instruct +- Meta-Llama-3.1-8B-Instruct +- Ministral 3B +- Mistral Large +- Mistral Large (2407) +- Mistral Large 24.11 +- Mistral Nemo +- Mistral Small +- Mistral Small 3.1 +- OpenAI GPT-4.1 +- OpenAI GPT-4o +- OpenAI GPT-4o mini +- OpenAI Text Embedding 3 (large) +- OpenAI Text Embedding 3 (small) +- OpenAI o1 +- OpenAI o1-mini +- OpenAI o1-preview +- OpenAI o3-mini +- Phi-3-medium instruct (128k) +- Phi-3-medium instruct (4k) +- Phi-3-mini instruct (128k) +- Phi-3-mini instruct (4k) +- Phi-3-small instruct (128k) +- Phi-3-small instruct (8k) +- Phi-3.5-MoE instruct (128k) +- Phi-3.5-mini instruct (128k) +- Phi-3.5-vision instruct (128k) +- Phi-4 +- Phi-4-mini-instruct +- Phi-4-multimodal-instruct + +### [Chutes](https://chutes.ai/) + +Distributed, decentralized crypto-based compute. Data is sent to individual hosts. + +- DeepCoder 14B Preview +- DeepHermes 3 Llama 3 8B Preview +- DeepSeek R1 +- DeepSeek R1-Zero +- DeepSeek V3 +- DeepSeek V3 0324 +- DeepSeek V3 Base +- Dolphin 3.0 Mistral 24B +- Dolphin 3.0 R1 Mistral 24B +- Gemma 3 12B Instruct +- Gemma 3 1B Instruct +- Gemma 3 4B Instruct +- Kimi VL A3B Thinking +- Llama 3.1 Nemotron Nano 8B v1 +- Llama 3.1 Nemotron Ultra 253B v1 +- Llama 3.3 Nemotron Super 49B v1 +- Llama 4 Maverick 17B 128E Instruct FP8 +- Llama 4 Scout 17B 16E Instruct +- Mistral Small 3.1 24B Instruct 2503 +- OlympicCoder 32B +- OlympicCoder 7B +- QwQ 32B ArliAI RpR v1 +- Qwen 2.5 VL 32B Instruct +- Reka Flash 3 + +### [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai) + +[10,000 neurons/day](https://developers.cloudflare.com/workers-ai/platform/pricing/#free-allocation) + +- DeepSeek 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 +- Llama 2 13B Chat (AWQ) +- Llama 2 7B Chat (FP16) +- Llama 2 7B Chat (INT8) +- Llama 2 7B Chat (LoRA) +- Llama 3 8B Instruct +- Llama 3 8B Instruct +- Llama 3 8B Instruct (AWQ) +- Llama 3.1 8B Instruct +- Llama 3.1 8B Instruct (AWQ) +- Llama 3.1 8B Instruct (FP8) +- Llama 3.2 11B Vision Instruct +- Llama 3.2 1B Instruct +- Llama 3.2 3B Instruct +- Llama 3.3 70B Instruct (FP8) +- Llama 4 Scout Instruct +- Llama Guard 3 8B +- LlamaGuard 7B (AWQ) +- Mistral 7B Instruct v0.1 +- 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) +- Phi-2 +- Qwen 1.5 0.5B Chat +- 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](https://console.cloud.google.com/vertex-ai/model-garden) + +Very stringent payment verification for Google Cloud. + + + - - - - - - + + + + + +
Model NameModel Limits
Gemini 2.5 Pro (Experimental)10 requests/minute
Shared Quota
Gemini 2.0 Flash (Experimental)
Gemini 2.0 Flash Thinking (Experimental)
Gemini 2.0 Pro (Experimental)
Llama 4 Maverick Instruct60 requests/minute
Free during preview
Llama 4 Scout Instruct60 requests/minute
Free during preview
Llama 3.3 70B Instruct30 requests/minute
Free during preview
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
Llama 4 Maverick Instruct60 requests/minute
Free during preview
Llama 4 Scout Instruct60 requests/minute
Free during preview
Llama 3.3 70B Instruct30 requests/minute
Free during preview
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
+ + ## Providers with trial credits - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
ProviderCreditsRequirementsModels
Together$1 when you add a payment methodVarious open models
Fireworks$1Various open models
Unify$5 when you add a payment methodRoutes to other providers, various open models and proprietary models (OpenAI, Gemini, Anthropic, Mistral, Perplexity, etc)
Baseten$30Any supported model - pay by compute time
Nebius$1Various open models
Novita$0.5 for 1 year
$20 for 3 months for DeepSeek models with referral code + GitHub account connection		Various open models
Hyperbolic$1DeepSeek V3
DeepSeek V3 0324
Hermes 3 Llama 3.1 70B
Llama 3 70B Instruct
Llama 3.1 405B Base
Llama 3.1 405B Base (FP8)
Llama 3.1 405B Instruct
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
Qwen QwQ 32B Preview
Qwen2.5 72B Instruct
Qwen2.5 Coder 32B Instruct
Qwen2.5 VL 72B Instruct
Qwen2.5 VL 7B Instruct
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
Llama 3.2 1B
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
Qwen/QwQ-32B-Preview
Qwen/Qwen2-Audio-7B-Instruct
Qwen/Qwen2.5-72B-Instruct
Qwen/Qwen2.5-Coder-32B-Instruct
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
DeepSeek R1 Distill Llama 70B
DeepSeek R1 Distill Llama 8B
Gemma 3 27B Instruct
Llama 3.1 70B Instruct
Llama 3.1 8B Instruct
Llama 3.3 70B Instruct
Mistral Nemo 2407
Mistral Small 3.1 24B Instruct 2503
Pixtral 12B (2409)
Qwen2.5 Coder 32B Instruct
sentence-t5-xxl
AI21$10 for 3 monthsJamba family of models
Upstage$10 for 3 monthsSolar Pro/Mini
NLP Cloud$15Phone number verificationVarious open models
Alibaba Cloud (International) Model StudioToken/time-limited trials on a per-model basisVarious open and proprietary Qwen models
Modal$30/monthAny supported model - pay by compute time
+### [Together](https://together.ai) + +**Credits:** $1 when you add a payment method + +**Models:** [Various open models](https://together.ai/models) + +### [Fireworks](https://fireworks.ai/) + +**Credits:** $1 + +**Models:** [Various open models](https://fireworks.ai/models) + +### [Unify](https://unify.ai/) + +**Credits:** $5 when you add a payment method + +**Models:** Routes to other providers, various open models and proprietary models (OpenAI, Gemini, Anthropic, Mistral, Perplexity, etc) + +### [Baseten](https://app.baseten.co/) + +**Credits:** $30 + +**Models:** [Any supported model - pay by compute time](https://www.baseten.co/library/) + +### [Nebius](https://studio.nebius.com/) + +**Credits:** $1 + +**Models:** [Various open models](https://studio.nebius.ai/models) + +### [Novita](https://novita.ai/referral?invited_code=E5R0CA&ref=ytblmjc&utm_source=affiliate) + +**Credits:** $0.5 for 1 year, $20 for 3 months for DeepSeek models with [referral code](https://novita.ai/referral?invited_code=E5R0CA&ref=ytblmjc&utm_source=affiliate) + GitHub account connection + +**Models:** [Various open models](https://novita.ai/models) + +### [AI21](https://studio.ai21.com/) + +**Credits:** $10 for 3 months + +**Models:** Jamba family of models + +### [Upstage](https://console.upstage.ai/) + +**Credits:** $10 for 3 months + +**Models:** Solar Pro/Mini + +### [NLP Cloud](https://nlpcloud.com/home) + +**Credits:** $15 + +**Requirements:** Phone number verification + +**Models:** Various open models + +### [Alibaba Cloud (International) Model Studio](https://bailian.console.alibabacloud.com/) + +**Credits:** Token/time-limited trials on a per-model basis + +**Models:** [Various open and proprietary Qwen models](https://www.alibabacloud.com/en/product/modelstudio) + +### [Modal](https://modal.com) + +**Credits:** $30/month + +**Models:** Any supported model - pay by compute time + +### [Hyperbolic](https://app.hyperbolic.xyz/) + +**Credits:** $1 + +**Models:** +- DeepSeek V3 +- DeepSeek V3 0324 +- Hermes 3 Llama 3.1 70B +- Llama 3 70B Instruct +- Llama 3.1 405B Base +- Llama 3.1 405B Base (FP8) +- Llama 3.1 405B Instruct +- 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 +- Qwen QwQ 32B Preview +- Qwen2.5 72B Instruct +- Qwen2.5 Coder 32B Instruct +- Qwen2.5 VL 72B Instruct +- Qwen2.5 VL 7B Instruct + +### [SambaNova Cloud](https://cloud.sambanova.ai/) + +**Credits:** $5 for 3 months + +**Models:** +- E5-Mistral-7B-Instruct +- Llama 3.1 405B +- Llama 3.1 8B +- Llama 3.2 11B Vision +- Llama 3.2 1B +- 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 +- Qwen/QwQ-32B-Preview +- Qwen/Qwen2-Audio-7B-Instruct +- deepseek-ai/DeepSeek-R1 +- deepseek-ai/DeepSeek-R1-Distill-Llama-70B +- deepseek-ai/DeepSeek-V3-0324 + +### [Scaleway Generative APIs](https://console.scaleway.com/generative-api/models) + +**Credits:** 1,000,000 free tokens + +**Models:** +- BGE-Multilingual-Gemma2 +- DeepSeek R1 Distill Llama 70B +- DeepSeek R1 Distill Llama 8B +- Gemma 3 27B Instruct +- Llama 3.1 70B Instruct +- Llama 3.1 8B Instruct +- Llama 3.3 70B Instruct +- Mistral Nemo 2407 +- Mistral Small 3.1 24B Instruct 2503 +- Pixtral 12B (2409) +- Qwen2.5 Coder 32B Instruct +- sentence-t5-xxl + + diff --git a/src/README_template.md b/src/README_template.md index c6a558b..17b7dcb 100644 --- a/src/README_template.md +++ b/src/README_template.md @@ -14,79 +14,4 @@ This lists various services that provide free access or credits towards API-base ## Providers with trial credits - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - {{TRIAL_MODEL_LIST}} - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
ProviderCreditsRequirementsModels
Together$1 when you add a payment methodVarious open models
Fireworks$1Various open models
Unify$5 when you add a payment methodRoutes to other providers, various open models and proprietary models (OpenAI, Gemini, Anthropic, Mistral, Perplexity, etc)
Baseten$30Any supported model - pay by compute time
Nebius$1Various open models
Novita$0.5 for 1 year
$20 for 3 months for DeepSeek models with referral code + GitHub account connection		Various open models
AI21$10 for 3 monthsJamba family of models
Upstage$10 for 3 monthsSolar Pro/Mini
NLP Cloud$15Phone number verificationVarious open models
Alibaba Cloud (International) Model StudioToken/time-limited trials on a per-model basisVarious open and proprietary Qwen models
Modal$30/monthAny supported model - pay by compute time
+{{TRIAL_LIST_MARKDOWN}} diff --git a/src/pull_available_models.py b/src/pull_available_models.py index d794a2a..0e7c92f 100644 --- a/src/pull_available_models.py +++ b/src/pull_available_models.py @@ -559,192 +559,176 @@ def main(): chutes_models = fetch_chutes_models(chutes_logger) groq_models = fetch_groq_models(groq_logger) - table = """ - - - - - - - - - -""" + # Initialize markdown string for free providers + model_list_markdown = "" - for idx, model in enumerate(openrouter_models): - table += "" + # --- OpenRouter --- + model_list_markdown += "### [OpenRouter](https://openrouter.ai)\n\n" + if openrouter_models: + provider_limits = get_human_limits(openrouter_models[0]) # Limits are the same for all free models here + model_list_markdown += f"[{provider_limits}
1000 requests/day with $10 credit balance](https://openrouter.ai/docs/api-reference/limits)\n\n" + model_list_markdown += "Models share a common quota.\n\n" + for model in openrouter_models: + model_list_markdown += f"- [{model['name']}](https://openrouter.ai/{model['id']})\n" + model_list_markdown += "\n" - if idx == 0: - table += f'" - table += f'' - table += f"" - if idx == 0: - table += f'' - table += "\n" + # --- Google AI Studio --- + model_list_markdown += "### [Google AI Studio](https://aistudio.google.com)\n\n" + model_list_markdown += "Data is used for training when used outside of the UK/CH/EEA/EU.\n\n" + model_list_markdown += "
ProviderProvider Limits/NotesModel NameModel Limits
' - table += 'OpenRouter' - table += "{get_human_limits(model)}
1000 requests/day with $10 credit balance		{model['name']}Shared Quota
\n" gemini_text_models = [ { "id": "gemini-2.5-pro-exp-03-25", "name": "Gemini 2.5 Pro (Experimental)", - "limits": gemini_models["gemini-2.0-pro-exp"], + "limits": gemini_models.get("gemini-2.0-pro-exp", {}), }, { "id": "gemini-2.0-flash", "name": "Gemini 2.0 Flash", - "limits": gemini_models["gemini-2.0-flash"], + "limits": gemini_models.get("gemini-2.0-flash", {}), }, { "id": "gemini-2.0-flash-lite", "name": "Gemini 2.0 Flash-Lite", - "limits": gemini_models["gemini-2.0-flash-lite"], + "limits": gemini_models.get("gemini-2.0-flash-lite", {}), }, { "id": "gemini-2.0-flash-exp", "name": "Gemini 2.0 Flash (Experimental)", - "limits": gemini_models["gemini-2.0-flash-exp"], + "limits": gemini_models.get("gemini-2.0-flash-exp", {}), }, { "id": "gemini-1.5-flash", "name": "Gemini 1.5 Flash", - "limits": gemini_models["gemini-1.5-flash"], + "limits": gemini_models.get("gemini-1.5-flash", {}), }, { "id": "gemini-1.5-flash-8b", "name": "Gemini 1.5 Flash-8B", - "limits": gemini_models["gemini-1.5-flash-8b"], + "limits": gemini_models.get("gemini-1.5-flash-8b", {}), }, { "id": "gemini-1.5-pro", "name": "Gemini 1.5 Pro", - "limits": gemini_models["gemini-1.5-pro"], + "limits": gemini_models.get("gemini-1.5-pro", {}), }, { "id": "learnlm-1.5-pro-experimental", "name": "LearnLM 1.5 Pro (Experimental)", - "limits": gemini_models["learnlm-1.5-pro-experimental"], + "limits": gemini_models.get("learnlm-1.5-pro-experimental", {}), }, { "id": "gemma-3-27b-it", "name": "Gemma 3 27B Instruct", - "limits": gemini_models["gemma-3-27b"], + "limits": gemini_models.get("gemma-3-27b", {}), }, { "id": "gemma-3-12b-it", "name": "Gemma 3 12B Instruct", - "limits": gemini_models["gemma-3-12b"], + "limits": gemini_models.get("gemma-3-12b", {}), }, { "id": "gemma-3-4b-it", "name": "Gemma 3 4B Instruct", - "limits": gemini_models["gemma-3-4b"], + "limits": gemini_models.get("gemma-3-4b", {}), }, { "id": "gemma-3-1b-it", "name": "Gemma 3 1B Instruct", - "limits": gemini_models["gemma-3-1b"], + "limits": gemini_models.get("gemma-3-1b", {}), }, ] gemini_embedding_models = [ { "id": "text-embedding-004", "name": "text-embedding-004", - "limits": gemini_models["project-embedding"], + "limits": gemini_models.get("project-embedding", {}), }, { "id": "embedding-001", "name": "embedding-001", - "limits": gemini_models["project-embedding"], + "limits": gemini_models.get("project-embedding", {}), }, ] - for idx, model in enumerate(gemini_text_models): - table += "" - if idx == 0: - table += f'" - table += f'' - table += f"" - table += f"" - table += "\n" + # Write text models to table + for model in gemini_text_models: + limits_str = get_human_limits(model) + model_list_markdown += f"\n" - for idx, model in enumerate(gemini_embedding_models): - table += "" - table += f"" - if idx == 0: - table += f'' - table += "\n" + # Write embedding models to table + first_embedding = True + for model in gemini_embedding_models: + limits_str = get_human_limits(model) + model_list_markdown += f"" + if first_embedding: + model_list_markdown += f'' + first_embedding = False + model_list_markdown += "\n" - table += """ - - - - - """ + model_list_markdown += "
Model NameModel Limits
' - table += 'Google AI Studio' - table += "Data is used for training (when used outside of the UK/CH/EEA/EU).{model['name']}{get_human_limits(model)}
{model['name']}{limits_str}
{model['name']}{get_human_limits(model)}
100 content/batch
Shared Quota
{model['name']}{limits_str}
100 content/batch
Shared Quota
NVIDIA NIMPhone number verification required.
Models tend to be context window limited.		Various open models40 requests/minute
\n\n" - table += """ - Mistral (La Plateforme) - Free tier (Experiment plan) requires opting into data training, requires phone number verification. - Open and Proprietary Mistral models - 1 request/second
500,000 tokens/minute
1,000,000,000 tokens/month - """ + # --- NVIDIA NIM --- + model_list_markdown += "### [NVIDIA NIM](https://build.nvidia.com/explore/discover)\n\n" + model_list_markdown += "Phone number verification required. Models tend to be context window limited.\n\n" + model_list_markdown += "- [Various open models](https://build.nvidia.com/models) (40 requests/minute)\n" + model_list_markdown += "\n" - table += """ - Mistral (Codestral) - Currently free to use, monthly subscription based, requires phone number verification. - Codestral - 30 requests/minute
2,000 requests/day - """ + # --- Mistral (La Plateforme) --- + model_list_markdown += "### [Mistral (La Plateforme)](https://console.mistral.ai/)\n\n" + model_list_markdown += "Free tier (Experiment plan) requires opting into data training, requires phone number verification.\n\n" + model_list_markdown += "- [Open and Proprietary Mistral models](https://docs.mistral.ai/getting-started/models/models_overview/) (1 request/second, 500,000 tokens/minute, 1,000,000,000 tokens/month)\n" + model_list_markdown += "\n" - table += """ - HuggingFace Serverless Inference - Limited to models smaller than 10GB.
Some popular models are supported even if they exceed 10GB. - Various open models - Variable credits per month, currently $0.10 - """ + # --- Mistral (Codestral) --- + model_list_markdown += "### [Mistral (Codestral)](https://codestral.mistral.ai/)\n\n" + model_list_markdown += "Currently free to use, monthly subscription based, requires phone number verification.\n\n" + model_list_markdown += "- Codestral (30 requests/minute, 2,000 requests/day)\n" + model_list_markdown += "\n" - table += """ - 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 - """ + # --- HuggingFace Serverless Inference --- + model_list_markdown += "### [HuggingFace Serverless Inference](https://huggingface.co/docs/api-inference/en/index)\n\n" + model_list_markdown += "Limited to models smaller than 10GB. Some popular models are supported even if they exceed 10GB.\n\n" + model_list_markdown += "- Various open models ([Variable credits per month, currently $0.10](https://huggingface.co/docs/api-inference/pricing))\n" + model_list_markdown += "\n" - for idx, model in enumerate(groq_models): - table += "" + # --- Cerebras --- + model_list_markdown += "### [Cerebras](https://cloud.cerebras.ai/)\n\n" + model_list_markdown += "Free tier restricted to 8K context.\n\n" + model_list_markdown += "\n" + cerebras_limit_text = "30 requests/minute
60,000 tokens/minute
900 requests/hour
1,000,000 tokens/hour
14,400 requests/day
1,000,000 tokens/day" + cerebras_models = [ + {"name": "Llama 4 Scout", "limits_text": cerebras_limit_text}, + {"name": "Llama 3.1 8B", "limits_text": cerebras_limit_text}, + {"name": "Llama 3.3 70B", "limits_text": cerebras_limit_text}, + ] + for model in cerebras_models: + model_list_markdown += f"\n" + model_list_markdown += "
Model NameModel Limits
{model['name']}{model['limits_text']}
\n\n" - if idx == 0: - table += f'' - table += 'Groq' - table += "" - table += f'' + # --- Groq --- + model_list_markdown += "### [Groq](https://console.groq.com)\n\n" + if groq_models: + model_list_markdown += "\n" + for model in groq_models: + limits_str = get_human_limits(model) + model_list_markdown += f"\n" + model_list_markdown += "
Model NameModel Limits
{model['name']}{limits_str}
\n" + model_list_markdown += "\n" - table += f"{model['name']}" - table += f"{get_human_limits(model)}" - table += "\n" - - for idx, model in enumerate(ovh_models): - table += "" - if idx == 0: - table += '' - table += 'OVH AI Endpoints (Free Beta)' - table += "" - table += '' - table += f"{model['name']}" - table += f"{get_human_limits(model)}" - table += "\n" + # --- OVH AI Endpoints --- + model_list_markdown += "### [OVH AI Endpoints (Free Beta)](https://endpoints.ai.cloud.ovh.net/)\n\n" + if ovh_models: + model_list_markdown += "\n" + for model in ovh_models: + limits_str = get_human_limits(model) + model_list_markdown += f"\n" + model_list_markdown += "
Model NameModel Limits
{model['name']}{limits_str}
\n" + model_list_markdown += "\n" + # --- Together --- together_models = [ { "id": "meta-llama/Llama-Vision-Free", @@ -762,20 +746,15 @@ def main(): "urlId": "deepseek-r1-distilled-llama-70b-free", }, ] + model_list_markdown += "### [Together](https://together.ai)\n\n" + model_list_markdown += "Up to 60 requests/minute.\n\n" + if together_models: + for model in together_models: + model_list_markdown += f"- [{model['name']}](https://together.ai/{model['urlId']})\n" + model_list_markdown += "\n" - for idx, model in enumerate(together_models): - table += "" - if idx == 0: - table += f'' - table += 'Together' - table += "" - table += ( - f'Up to 60 requests/minute' - ) - table += f"{model['name']}" - table += f"{get_human_limits(model)}" - table += "\n" + # --- Cohere --- cohere_models = [ {"id": "command-a-03-2025", "name": "Command-A"}, {"id": "command-r7b-12-2024", "name": "Command-R7B"}, @@ -786,63 +765,40 @@ def main(): {"id": "c4ai-aya-vision-8b", "name": "Aya Vision 8B"}, {"id": "c4ai-aya-vision-32b", "name": "Aya Vision 32B"}, ] + model_list_markdown += "### [Cohere](https://cohere.com)\n\n" + model_list_markdown += "[20 requests/minute
1,000 requests/month](https://docs.cohere.com/docs/rate-limits)\n\n" + model_list_markdown += "Models share a common quota.\n\n" + if cohere_models: + for model in cohere_models: + model_list_markdown += f"- {model['name']}\n" + model_list_markdown += "\n" - for idx, model in enumerate(cohere_models): - table += "" - if idx == 0: - table += f'' - table += 'Cohere' - table += "" - table += f'20 requests/minute
1,000 requests/month' - table += f"{model['name']}" - if idx == 0: - table += f'Shared Limit' - table += "\n" + # --- GitHub Models --- + model_list_markdown += "### [GitHub Models](https://github.com/marketplace/models)\n\n" + model_list_markdown += "Extremely restrictive input/output token limits. [Rate limits dependent on Copilot subscription tier (Free/Pro/Business/Enterprise)](https://docs.github.com/en/github-models/prototyping-with-ai-models#rate-limits)\n\n" + if github_models: + for model in github_models: + model_list_markdown += f"- {model['name']}\n" + model_list_markdown += "\n" - for idx, model in enumerate(github_models): - table += "" - table += ( - f'GitHub Models' - if idx == 0 - else "" - ) - table += ( - f'Extremely restrictive input/output token limits.
Rate limits dependent on Copilot subscription tier (Free/Pro/Business/Enterprise)' - if idx == 0 - else "" - ) - table += f"{model['name']}" - table += "" - table += "\n" + # --- Chutes --- + model_list_markdown += "### [Chutes](https://chutes.ai/)\n\n" + model_list_markdown += "Distributed, decentralized crypto-based compute. Data is sent to individual hosts.\n\n" + if chutes_models: + for model in chutes_models: + model_list_markdown += f"- {model['name']}\n" + model_list_markdown += "\n" - for idx, model in enumerate(chutes_models): - table += "" - if idx == 0: - table += '' - table += 'Chutes' - table += "" - table += ( - 'Distributed, decentralized crypto-based compute. Data is sent to individual hosts.' - ) - table += f"{model['name']}" - table += "" - table += "\n" + # --- Cloudflare Workers AI --- + model_list_markdown += "### [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai)\n\n" + model_list_markdown += "[10,000 neurons/day](https://developers.cloudflare.com/workers-ai/platform/pricing/#free-allocation)\n\n" + if cloudflare_models: + for model in cloudflare_models: + model_list_markdown += f"- {model['name']}\n" + model_list_markdown += "\n" - for idx, model in enumerate(cloudflare_models): - table += "" - if idx == 0: - table += '' - table += 'Cloudflare Workers AI' - table += "" - table += '' - table += '10,000 neurons/day' - table += "" - table += f"{model['name']}" - table += "" - table += "\n" + # --- Google Cloud Vertex AI --- vertex_llama_models = [ { "id": "llama-4-maverick-17b-128e-instruct-maas", @@ -903,70 +859,148 @@ def main(): "limits": {"requests/minute": 10}, }, ] + model_list_markdown += "### [Google Cloud Vertex AI](https://console.cloud.google.com/vertex-ai/model-garden)\n\n" + model_list_markdown += "Very stringent payment verification for Google Cloud.\n\n" + model_list_markdown += "\n" - for idx, model in enumerate(vertex_gemini_models): - table += "" - if idx == 0: - table += ( - f'" - table += f'' - table += f'' - if idx == 0: - table += f"" - table += "\n" + # Write Gemini models to table + first_gemini = True + if vertex_gemini_models: + for model in vertex_gemini_models: + limits_str = get_human_limits(model) + model_list_markdown += f'' + if first_gemini: + model_list_markdown += f'' + first_gemini = False + model_list_markdown += "\n" - for idx, model in enumerate(vertex_llama_models): - table += "" - table += f"" - table += f"" - table += "\n" + # Write Llama models to table + if vertex_llama_models: + for model in vertex_llama_models: + limits_str = get_human_limits(model) + model_list_markdown += f'\n' - table += "
Model NameModel Limits
' - ) - table += 'Google Cloud Vertex AI' - table += "Very stringent payment verification for Google Cloud.{model['name']}{get_human_limits(model)}
Shared Quota
{model['name']}{limits_str}
Shared Quota
{model['name']}{get_human_limits(model)}
Free during preview
{model['name']}{limits_str}
Free during preview
" + model_list_markdown += "\n\n" - trial_table = "" - for idx, model in enumerate(hyperbolic_models): - trial_table += "" - if idx == 0: - trial_table += f'' - trial_table += ( - 'Hyperbolic' - ) - trial_table += "" - trial_table += f'$1' - trial_table += f'' - trial_table += f"{model['name']}" - trial_table += "\n" - for idx, model in enumerate(samba_models): - trial_table += "" + # --- Trial Providers Section Generation --- + trial_list_markdown = "" - if idx == 0: - trial_table += f'' - trial_table += 'SambaNova Cloud' - trial_table += "" - trial_table += f'$5 for 3 months' + # --- Static Trial Providers (Markdown List/Simple Entry) --- + trial_providers_static = [ + { + "name": "Together", + "url": "https://together.ai", + "credits": "$1 when you add a payment method", + "requirements": "", + "models_desc": "[Various open models](https://together.ai/models)", + }, + { + "name": "Fireworks", + "url": "https://fireworks.ai/", + "credits": "$1", + "requirements": "", + "models_desc": "[Various open models](https://fireworks.ai/models)", + }, + { + "name": "Unify", + "url": "https://unify.ai/", + "credits": "$5 when you add a payment method", + "requirements": "", + "models_desc": "Routes to other providers, various open models and proprietary models (OpenAI, Gemini, Anthropic, Mistral, Perplexity, etc)", + }, + { + "name": "Baseten", + "url": "https://app.baseten.co/", + "credits": "$30", + "requirements": "", + "models_desc": "[Any supported model - pay by compute time](https://www.baseten.co/library/)", + }, + { + "name": "Nebius", + "url": "https://studio.nebius.com/", + "credits": "$1", + "requirements": "", + "models_desc": "[Various open models](https://studio.nebius.ai/models)", + }, + { + "name": "Novita", + "url": "https://novita.ai/referral?invited_code=E5R0CA&ref=ytblmjc&utm_source=affiliate", + "credits": "$0.5 for 1 year, $20 for 3 months for DeepSeek models with [referral code](https://novita.ai/referral?invited_code=E5R0CA&ref=ytblmjc&utm_source=affiliate) + GitHub account connection", + "requirements": "", + "models_desc": "[Various open models](https://novita.ai/models)", + }, + { + "name": "AI21", + "url": "https://studio.ai21.com/", + "credits": "$10 for 3 months", + "requirements": "", + "models_desc": "Jamba family of models", + }, + { + "name": "Upstage", + "url": "https://console.upstage.ai/", + "credits": "$10 for 3 months", + "requirements": "", + "models_desc": "Solar Pro/Mini", + }, + { + "name": "NLP Cloud", + "url": "https://nlpcloud.com/home", + "credits": "$15", + "requirements": "Phone number verification", + "models_desc": "Various open models", + }, + { + "name": "Alibaba Cloud (International) Model Studio", + "url": "https://bailian.console.alibabacloud.com/", + "credits": "Token/time-limited trials on a per-model basis", + "requirements": "", + "models_desc": "[Various open and proprietary Qwen models](https://www.alibabacloud.com/en/product/modelstudio)", + }, + { + "name": "Modal", + "url": "https://modal.com", + "credits": "$30/month", + "requirements": "", + "models_desc": "Any supported model - pay by compute time", + }, + ] - trial_table += f"" - trial_table += f"{model['name']}" - trial_table += "\n" + for provider in trial_providers_static: + trial_list_markdown += f"### [{provider['name']}]({provider['url']})\n\n" + trial_list_markdown += f"**Credits:** {provider['credits']}\n\n" + if provider["requirements"]: + trial_list_markdown += f"**Requirements:** {provider['requirements']}\n\n" + trial_list_markdown += f"**Models:** {provider['models_desc']}\n\n" + + # --- Hyperbolic (Trial - Table) --- + if hyperbolic_models: + trial_list_markdown += "### [Hyperbolic](https://app.hyperbolic.xyz/)\n\n" + trial_list_markdown += "**Credits:** $1\n\n" + trial_list_markdown += "**Models:**\n" + for model in hyperbolic_models: + trial_list_markdown += f"- {model['name']}\n" + trial_list_markdown += "\n" + + # --- SambaNova Cloud (Trial - Table) --- + if samba_models: + trial_list_markdown += "### [SambaNova Cloud](https://cloud.sambanova.ai/)\n\n" + 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 += "\n" + + # --- Scaleway Generative APIs (Trial - Table) --- + if scaleway_models: + trial_list_markdown += "### [Scaleway Generative APIs](https://console.scaleway.com/generative-api/models)\n\n" + trial_list_markdown += "**Credits:** 1,000,000 free tokens\n\n" + trial_list_markdown += "**Models:**\n" + for model in scaleway_models: + trial_list_markdown += f"- {model['name']}\n" + trial_list_markdown += "\n" - for idx, model in enumerate(scaleway_models): - trial_table += "" - if idx == 0: - trial_table += '' - trial_table += 'Scaleway Generative APIs' - trial_table += "" - trial_table += ( - '1,000,000 free tokens' - ) - trial_table += f"" - trial_table += f"{model['name']}" - trial_table += "\n" if MISSING_MODELS: logger.warning("Missing models:") @@ -984,8 +1018,8 @@ WARNING: DO NOT EDIT THIS FILE DIRECTLY. IT IS GENERATED BY src/pull_available_m with open(os.path.join(script_dir, "..", "README.md"), "w") as f: f.write( (warning + readme) - .replace("{{MODEL_LIST}}", table) - .replace("{{TRIAL_MODEL_LIST}}", trial_table) + .replace("{{MODEL_LIST}}", model_list_markdown) + .replace("{{TRIAL_LIST_MARKDOWN}}", trial_list_markdown) ) logger.info("Wrote models to README.md")