Free LLM API resources

This lists various services that provide free access or credits towards API-based LLM usage.

Note

Please don't abuse these services, else we might lose them.

Warning

This list explicitly excludes any services that are not legitimate (eg reverse engineers an existing chatbot)

Free Providers

Provider	Provider Limits/Notes	Model Name	Model Limits
Groq		Distil Whisper Large v3	7,200 audio-seconds/minute 2,000 requests/day
		Gemma 2 9B Instruct	14,400 requests/day 15,000 tokens/minute
		Llama 3 70B	14,400 requests/day 6,000 tokens/minute
		Llama 3 70B - Groq Tool Use Preview	14,400 requests/day 15,000 tokens/minute
		Llama 3 8B	14,400 requests/day 30,000 tokens/minute
		Llama 3 8B - Groq Tool Use Preview	14,400 requests/day 15,000 tokens/minute
		Llama 3.1 70B	14,400 requests/day 6,000 tokens/minute
		Llama 3.1 8B	14,400 requests/day 20,000 tokens/minute
		Llama 3.2 11B Vision	7,000 requests/day 7,000 tokens/minute
		Llama 3.2 1B	7,000 requests/day 7,000 tokens/minute
		Llama 3.2 3B	7,000 requests/day 7,000 tokens/minute
		Llama 3.2 90B Vision	3,500 requests/day 7,000 tokens/minute
		Llama 3.3 70B	1,000 requests/day 6,000 tokens/minute
		Llama 3.3 70B (Speculative Decoding)	1,000 requests/day 6,000 tokens/minute
		Llama Guard 3 8B	14,400 requests/day 15,000 tokens/minute
		Mixtral 8x7B	14,400 requests/day 5,000 tokens/minute
		Whisper Large v3	7,200 audio-seconds/minute 2,000 requests/day
		Whisper Large v3 Turbo	7,200 audio-seconds/minute 2,000 requests/day
OpenRouter	20 requests/minute 200 requests/day	Gemini 2.0 Flash Experimental
		Gemini Experimental 1114
		Gemini Experimental 1206
		Gemma 2 9B Instruct
		Llama 3 8B Instruct
		Llama 3.1 405B Instruct
		Llama 3.1 70B Instruct
		Llama 3.1 8B Instruct
		Llama 3.2 11B Vision Instruct
		Llama 3.2 1B Instruct
		Llama 3.2 3B Instruct
		Llama 3.2 90B Vision Instruct
		Mistral 7B Instruct
		Mythomax L2 13B
		OpenChat 7B
		Phi-3 Medium 128k Instruct
		Phi-3 Mini 128k Instruct
		Qwen 2 7B Instruct
		Toppy M 7B
		Zephyr 7B Beta
Google AI Studio	Data is used for training (when used outside of the UK/CH/EEA/EU).	Gemini 2.0 Flash	4,000,000 tokens/minute 10 requests/minute
		Gemini 1.5 Flash	1,000,000 tokens/minute 1,500 requests/day 15 requests/minute
		Gemini 1.5 Flash (Experimental)	1,000,000 tokens/minute 1,500 requests/day 5 requests/minute
		Gemini 1.5 Flash-8B	1,000,000 tokens/minute 1,500 requests/day 15 requests/minute
		Gemini 1.5 Flash-8B (Experimental)	1,000,000 tokens/minute 1,500 requests/day 15 requests/minute
		Gemini 1.5 Pro	32,000 tokens/minute 50 requests/day 2 requests/minute
		Gemini 1.5 Pro (Experimental)	1,000,000 tokens/minute 100 requests/day 5 requests/minute
		LearnLM 1.5 Pro (Experimental)	1,500 requests/day 15 requests/minute
		Gemini 1.0 Pro	32,000 tokens/minute 1,500 requests/day 15 requests/minute
		text-embedding-004	150 batch requests/minute 1,500 requests/minute 100 content/batch
		embedding-001
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
Mistral (Codestral)	Currently free to use, monthly subscription based, requires phone number verification.	Codestral	30 requests/minute 2,000 requests/day
HuggingFace Serverless Inference	Limited to models smaller than 10GB. Some popular models are supported even if they exceed 10GB.	Various open models	1,000 requests/day (with an account)
SambaNova Cloud		Llama 3.1 8B	30 requests/minute
		Llama 3.1 70B	20 requests/minute
		Llama 3.1 405B	10 requests/minute
		Llama 3.2 1B	30 requests/minute
		Llama 3.2 3B	30 requests/minute
		Llama 3.2 11B	10 requests/minute
		Llama 3.2 90B	1 requests/minute
		Llama 3.3 70B	20 requests/minute
		Llama Guard 3 8B	30 requests/minute
		Qwen 2.5 72B	20 requests/minute
		Qwen 2.5 Coder 32B	20 requests/minute
		QwQ 32B Preview	10 requests/minute
Cerebras	Waitlist Free tier restricted to 8K context	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 3.1 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
		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
GitHub Models	Waitlist Rate limits dependent on Copilot subscription tier	AI21-Jamba-Instruct
		Cohere Command R
		Cohere Command R+
		Cohere Embed v3 English
		Cohere Embed v3 Multilingual
		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
		Mistral Large
		Mistral Large (2407)
		Mistral Nemo
		Mistral Small
		OpenAI GPT-4o
		OpenAI GPT-4o mini
		OpenAI Text Embedding 3 (large)
		OpenAI Text Embedding 3 (small)
		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-mini instruct (128k)
OVH AI Endpoints (Free Beta)		CodeLlama 13B Instruct	12 requests/minute
		Codestral Mamba 7B v0.1	12 requests/minute
		Llama 2 13B Chat	12 requests/minute
		Llama 3 70B Instruct	12 requests/minute
		Llama 3 8B Instruct	12 requests/minute
		Llama 3.1 70B Instruct	12 requests/minute
		Mathstral 7B v0.1	12 requests/minute
		Mistral 7B Instruct	12 requests/minute
		Mistral Nemo 2407	12 requests/minute
		Mixtral 8x22B Instruct	12 requests/minute
		Mixtral 8x7B Instruct	12 requests/minute
Scaleway Generative APIs (Free Beta)		BGE-Multilingual-Gemma2	600 requests/minute 1,000,000 tokens/minute
		Llama 3.1 70B Instruct	300 requests/minute 100,000 tokens/minute
		Llama 3.1 8B Instruct	300 requests/minute 100,000 tokens/minute
		Mistral Nemo 2407	300 requests/minute 100,000 tokens/minute
		Pixtral 12B (2409)	300 requests/minute 100,000 tokens/minute
		Qwen2.5 Coder 32B Instruct
		sentence-t5-xxl	600 requests/minute 1,000,000 tokens/minute
Cloudflare Workers AI	10,000 tokens/day	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 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)
		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)
		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)
		SQLCoder 7B 2
		Starling LM 7B Beta
		TinyLlama 1.1B Chat v1.0
		Una Cybertron 7B v2 (BF16)
		Zephyr 7B Beta (AWQ)
Together		Llama 3.2 11B Vision Instruct	Free for 2024
Cohere	20 requests/min 1,000 requests/month	Command-R	Shared Limit
		Command-R+
Google Cloud Vertex AI	Very stringent payment verification for Google Cloud.	Llama 3.1 70B Instruct	Llama 3.1 API Service free during preview. 60 requests/minute
		Llama 3.1 8B Instruct	Llama 3.1 API Service free during preview. 60 requests/minute
		Llama 3.2 90B Vision Instruct	Llama 3.2 API Service free during preview. 30 requests/minute
		Gemini 2.0 Flash Experimental	Experimental Gemini model. 10 requests/minute
		Gemini Flash Experimental
		Gemini Pro Experimental
glhf.chat (Free Beta)		Any model on Hugging Face runnable on vLLM and fits on a A100 node (~640GB VRAM), including Llama 3.1 405B at FP8	480 requests/8 hours

Providers with trial credits

Provider	Credits	Requirements	Models
Together	$1		Various open models
Fireworks	$1		Various open models
Unify	$5 when you add a payment method		Routes to other providers, various open models and proprietary models (OpenAI, Gemini, Anthropic, Mistral, Perplexity, etc)
NVIDIA NIM	1,000 API calls for 1 month		Various open models
Baseten	$30		Any supported model - pay by compute time
xAI	$25/month until end of 2024		Grok
Nebius	$1		Various open models
Hyperbolic	$10		DeepSeek V2.5
			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 405B Instruct Virtuals
			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 Preview
			Qwen2-VL 72B Instruct
			Qwen2-VL 7B Instruct
			Qwen2.5 72B Instruct
			Qwen2.5 Coder 32B Instruct
AI21	$10 for 3 months		Jamba/Jurrasic-2
Upstage	$10 for 3 months		Solar Pro/Mini
NLP Cloud	$15	Phone number verification	Various open models