Meta Llama Models
haimaker.ai provides API access to all 8 Meta Llama models, with context windows up to 1M tokens, priced from $0.03 to $0.40 per 1M input tokens. OpenAI-compatible endpoint, instant access.
Models
8
Max context
1M
From
$0.03
/1M input
Modes
chat
Llama Guard 4 12B
Meta Llama
meta-llama/llama-guard-4-12b
12.0B params164K ctxIn: $0.18/1MOut: $0.18/1M
vision
Llama 4 Scout 17B 16E Instruct
Meta Llama
meta-llama/llama-4-scout
108.6B params1M ctxIn: $0.10/1MOut: $0.30/1M
function callingvision
Llama 4 Maverick 17B 128E Instruct
Meta Llama
meta-llama/llama-4-maverick
401.6B params1M ctxIn: $0.20/1MOut: $0.70/1M
function callingvision
Llama 3.3 70B Instruct
Meta Llama
meta-llama/llama-3.3-70b-instruct
70.6B params131K ctxIn: $0.10/1MOut: $0.32/1M
function calling
Llama 3.2 3B Instruct
Meta Llama
meta-llama/llama-3.2-3b-instruct
3.2B params131K ctxIn: $0.05/1MOut: $0.33/1M
Llama 3.2 1B Instruct
Meta Llama
meta-llama/llama-3.2-1b-instruct
1.2B params60K ctxIn: $0.03/1MOut: $0.20/1M
Llama 3.1 8B Instruct
Meta Llama
meta-llama/llama-3.1-8b-instruct
8.0B params131K ctxIn: $0.05/1MOut: $0.08/1M
function calling
Llama 3.1 70B Instruct
Meta Llama
meta-llama/llama-3.1-70b-instruct
70.6B params131K ctxIn: $0.40/1MOut: $0.40/1M
function calling