Models/Llama 3.3 70B Instruct
MetaMeta / Llama 3.3 70B Instruct
Released: 12/6/2024
texttext
Input: $0.90 / Output: $0.90

Llama 3.3 70B Instruct is an LLM optimized for dialogue use cases, excelling in reasoning, math, instruction following, and multilingual support. It is particularly effective for tasks requiring strong understanding and generation capabilities across multiple languages.

MetricValue
Parameter Count70 billion
Mixture of ExpertsNo
Context Length128,000 tokens
MultilingualYes
Quantized*Unknown

*Quantization is specific to the inference provider and may vary by provider.

Meta models available on Oxen.ai
ModalityPrice (1M tokens)
ModelInference providerInputOutputInputOutput
Fireworks AI
texttext$3.00$3.00
Together.ai
texttext$3.50$3.50
Fireworks AI
texttext$0.90$0.90
Together.ai
texttext$0.88$0.88
Groq
texttext$0.05$0.08
Fireworks AI
texttext$0.20$0.20
Together.ai
texttext$0.18$0.18
Together.ai
texttext$0.90$0.90
Groq
imagetext$0.18$0.18
Groq
texttext$0.04$0.04
Groq
texttext$0.06$0.06
Together.ai
texttext$0.06$0.06
Groq
imagetext$0.90$0.90
Fireworks AI
texttext$0.90$0.90
Together.ai
texttext$0.88$0.88
Groq
texttext$0.59$0.59
Groq
texttext$0.59$0.79
See all models available on Oxen.ai