Free Tier Coupon Book
53 models from 20 providers, sorted cheapest first. Freeloader exhausts the $0 ones before touching anything that costs money.
Free Tier
33 models — $0, just bring an API key
Cerebras
Llama 3.3 70B
$0
30 req/min 1K req/day
completely free within limits
128K ctx tools
Cerebras
Llama 3.1 8B
$0
30 req/min 1K req/day
completely free within limits
128K ctx tools
SambaNova
Llama 3.3 70B
$0
10 req/min 100 req/day
completely free within limits
128K ctx tools
SambaNova
Llama 3.1 8B
$0
10 req/min 100 req/day
completely free within limits
128K ctx tools
SambaNova
DeepSeek R1
$0
5 req/min 50 req/day
completely free within limits
66K ctx
OpenRouter
Llama 3.3 70B (Free)
$0
20 req/min 200 req/day
completely free within limits
131K ctx tools
OpenRouter
Gemini 2.0 Flash (Free)
$0
20 req/min 200 req/day
completely free within limits
1M ctx tools vision
OpenRouter
DeepSeek R1 (Free)
$0
20 req/min 200 req/day
completely free within limits
164K ctx
OpenRouter
Qwen 2.5 72B (Free)
$0
20 req/min 200 req/day
completely free within limits
131K ctx
OpenRouter
Mistral 7B (Free)
$0
20 req/min 200 req/day
completely free within limits
33K ctx
OpenRouter
Phi-3 Mini (Free)
$0
20 req/min 200 req/day
completely free within limits
128K ctx
Ollama (Local)
Local Models (Ollama)
$0
unlimited (local inference)
completely free within limits
128K ctx tools
NVIDIA NIM
Llama 3.1 8B Instruct
$0
40 req/min
completely free within limits
128K ctx tools
NVIDIA NIM
Mistral 7B Instruct
$0
40 req/min
completely free within limits
33K ctx tools
GitHub Models
GPT-4o Mini
$0
15 req/min 150 req/day
completely free within limits
128K ctx tools vision
GitHub Models
Phi-3.5 Mini Instruct
$0
15 req/min 150 req/day
completely free within limits
128K ctx tools
Cloudflare Workers AI
Llama 3.1 8B Instruct
$0
completely free within limits
128K ctx tools
Cloudflare Workers AI
Mistral 7B Instruct
$0
completely free within limits
33K ctx
HuggingFace
Llama 3.1 8B Instruct
$0
60 req/min
completely free within limits
128K ctx
HuggingFace
Mistral 7B Instruct
$0
60 req/min
completely free within limits
33K ctx
Groq
Llama 3.1 8B Instant
$0
30 req/min 14K req/day
then $0.05/1M tokens after limits
128K ctx tools
Google
Gemini 2.0 Flash Lite
$0
30 req/min 2K req/day
then $0.07/1M tokens after limits
1M ctx tools vision
Google
Gemini 2.0 Flash
$0
15 req/min 2K req/day
then $0.10/1M tokens after limits
1M ctx tools vision
Mistral
Mistral NeMo
$0
1 req/min 500 req/day
then $0.10/1M tokens after limits
131K ctx tools
Google
Gemini 2.5 Flash
$0
15 req/min 2K req/day
then $0.15/1M tokens after limits
1M ctx tools vision
Cohere
Command R
$0
10 req/min 1K req/day
then $0.15/1M tokens after limits
128K ctx tools
Groq
Gemma 2 9B
$0
30 req/min 14K req/day
then $0.20/1M tokens after limits
8K ctx tools
Mistral
Mistral Small
$0
1 req/min 500 req/day
then $0.20/1M tokens after limits
131K ctx tools
Groq
Mixtral 8x7B
$0
30 req/min 14K req/day
then $0.24/1M tokens after limits
33K ctx tools
Groq
Llama 3.3 70B Versatile
$0
30 req/min 14K req/day 500K tok/day
then $0.59/1M tokens after limits
128K ctx tools
Google
Gemini 2.5 Pro
$0
5 req/min 25 req/day
then $1.25/1M tokens after limits
1M ctx tools vision
Mistral
Pixtral Large
$0
1 req/min 500 req/day
then $2.00/1M tokens after limits
131K ctx tools vision
Cohere
Command R+
$0
10 req/min 1K req/day
then $2.50/1M tokens after limits
128K ctx tools
Budget
15 models — fractions of a cent per request
OpenAI
GPT-4.1 Nano
$0.10 /1M input tokens
1M ctx tools vision
OpenAI
GPT-4o Mini
$0.15 /1M input tokens
128K ctx tools vision
Alibaba Cloud
Qwen-Turbo
$0.20 /1M input tokens
131K ctx tools
Inception Labs
Mercury 2
$0.25 /1M input tokens
128K ctx tools
Inception Labs
Mercury Coder
$0.25 /1M input tokens
128K ctx tools
DeepSeek
DeepSeek Chat (V3)
$0.27 /1M input tokens
66K ctx tools
Mistral
Codestral
$0.30 /1M input tokens
262K ctx tools
xAI
Grok 3 Mini Fast
$0.30 /1M input tokens
131K ctx tools
DeepSeek
DeepSeek Reasoner (R1)
$0.55 /1M input tokens
66K ctx
Alibaba Cloud
Qwen-Plus
$0.80 /1M input tokens
131K ctx tools vision
Together AI
Llama 3.3 70B Turbo
$0.88 /1M input tokens
131K ctx tools
Fireworks AI
Llama 3.3 70B
$0.90 /1M input tokens
131K ctx tools
Fireworks AI
Mixtral 8x22B MoE
$0.90 /1M input tokens
66K ctx tools
Together AI
Qwen 2.5 72B Turbo
$1.20 /1M input tokens
131K ctx tools
Alibaba Cloud
Qwen-Max
$2.40 /1M input tokens
131K ctx tools vision
Premium
5 models — the best, when you need the best
Anthropic
Claude Haiku 4.5
$0.80 /1M input tokens
200K ctx tools vision
Mistral
Mistral Large
$2.00 /1M input tokens
131K ctx tools vision
OpenAI
GPT-4o
$2.50 /1M input tokens
128K ctx tools vision
Anthropic
Claude Sonnet 4.6
$3.00 /1M input tokens
200K ctx tools vision
xAI
Grok 3 Fast
$5.00 /1M input tokens
131K ctx tools vision