evrocLlama 3.3 70B model ID, context window & pricing
llama
Quick facts
Model ID nvidia/Llama-3.3-70B-Instruct-FP8
Source evroc
Context Window 131072
Pricing $1.18 input / $1.18 output per 1M tokens
Capabilities open weights
Model overview
Llama 3.3 70B is an AI model from evroc with 131072 token context window and text input support.
Published pricing is $1.18 input and $1.18 output per 1M tokens.
- Workloads that use text inputs with text outputs.
Model ID nvidia/Llama-3.3-70B-Instruct-FP8
Provider evroc
Family llama
Status -
Knowledge Cutoff -
Release Date 2024-12-01
Input Modalities text
Output Modalities text
Context Window 131072
Input Limit -
Output Limit 32768
Tool Calling No
Reasoning No
Structured Output -
Temperature Control -
Open Weights Yes
Input Cost / 1M tokens $1.18
Output Cost / 1M tokens $1.18
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens -