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 that excels in text-based tasks such as coding, multilingual support, and instruction following. It offers improved performance in reasoning, mathematics, and tool calling compared to its predecessors.

Some other noteworthy features of Llama 3.3 70B Instruct include its ability to generate JSON outputs for function calling and provide step-by-step reasoning with accurate responses.

MetricValue
Parameter Count70 billion
Mixture of ExpertsNo
Context Length128,000 tokens
MultilingualYes
Quantized*No

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.

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