Free LLM resources

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

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

Free Providers

Provider	Provider Limits/Notes	Model	Model Limits
OpenRouter		Llama 3 8B Instruct	20 req/min, 200 req/day
		Gemma 2 9B	20 req/min, 200 req/day
		Gemma 7B	20 req/min, 200 req/day
		Mistral 7B Instruct	20 req/min, 200 req/day
		Phi-3 Mini 128K Instruct	10 req/day (shared among Phi-3 models)
		Phi-3 Medium 128K Instruct	10 req/day (shared among Phi-3 models)
		Zephyr 7B	20 req/min, 200 req/day
		Capybara 7B	20 req/min, 200 req/day
		OpenChat 3.5 7B	20 req/min, 200 req/day
		MythoMist 7B	20 req/min, 200 req/day
		Toppy M 7B	20 req/min, 200 req/day
GroqCloud
		Gemma 2 9B Instruct	30 req/min, 14,400 req/day, 15,000 tokens/min
		Gemma 7B Instruct	30 req/min, 14,400 req/day, 15,000 tokens/min
		Llama 3 70B	30 req/min, 14,400 req/day, 6,000 tokens/min
		Llama 3 8B	30 req/min, 14,400 req/day, 30,000 tokens/min
		Mixtral 8x7B	30 req/min, 14,400 req/day, 5,000 tokens/min
		Whisper Large V3	20 req/min, 2,000 req/day, 7,200 audio-seconds/hour, 28,800 audio-seconds/day
Google AI Studio	Free tier Gemini API access not available within UK/CH/EEA/EU Data is trained upon in the free tier.	Gemini 1.5 Flash	15 req/min, 1,500 req/day, 1 million tokens/min
		Gemini 1.5 Pro	2 req/min, 50 req/day, 32,000 tokens/min
		Gemini 1.0 Pro	15 req/min, 1,500 req/day, 32,000 tokens/min
	Embeddings are available in UK/CH/EEA/EU	text-embedding-004	1,500 req/min, 100 content/batch
		embedding-001	1,500 req/min, 100 content/batch
Cohere	10 req/min, 1,000 req/month	Command-R	Shared Limit
		Command-R+	Shared Limit
HuggingFace Serverless Inference	Dynamic Rate Limits. Limited to models smaller than 10GB. Some popular models are supported even if they exceed 10GB.	Various open models
OVH AI Endpoints (Free Alpha)	Token expires every 2 weeks	Llama 3 70B Instruct	12 req/min
		Llama 3 8B Instruct	12 req/min
		Mixtral 8x22B Instruct	12 req/min
		Mixtral 8x7B Instruct	12 req/min
		Mistral 7B Instruct	12 req/min
		Llama 2 13B Chat	12 req/min
		CodeLlama 13B Instruct	12 req/min
Cloudflare Workers AI	10,000 neurons/day. Beta models have unlimited usage. Typical 300 req/min for text models.	Llama 2 7B Chat
		Mistral 7B Instruct
		Deepseek Coder 6.7B Base AWQ
		Deepseek Coder 6.7B Instruct AWQ
		Deepseek Math 7B Base
		Deepseek Math 7B Instruct
		DiscoLM German 7B AWQ
		Falcon 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 LoRA
		Llama 3 8B Instruct
		Llama 3 8B Instruct AWQ
		Llama Guard 7B AWQ
		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
		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
		Starling LM 7B
		TinyLlama 1.1B Chat
		Una Cybertron 7B v2
		Zephyr 7B AWQ

Providers with trial credits

Provider	Credits	Models
Anthropic	$5 for 14 days	Claude 3
Mistral	$5 for 14 days	Mistral Open/Proprietary Models
Together	$5	Various open models
Fireworks	$1	Various open models
OctoAI	$10	Various open models
Unify	$10	Routes to other providers, various open models and proprietary models (OpenAI, Anthropic, Mistral, Perplexity)
DeepInfra	$1.80	Various open models
NVIDIA NIM	1000 API calls	Various open models