evroc
Llama 3.3 70B
Canonical ID:
evroc/nvidia/Llama-3.3-70B-Instruct-FP8
Popular open Llama workhorse for multilingual chat, coding, and self-hosting
Overview
- Provider
-
evroc
- Family
- llama-3.3-70b-instruct-fp8
- Release date
- 2024-12-01
- Last updated
- 2024-12-01
- Input modalities
- text
- Output modalities
- text
Pricing and Limits
Token pricing
- Input
- $1.18/1M
- Output
- $1.18/1M
- Cached input
- N/A
Context and output
- Context window
- 131,072
- Max output tokens
- 32,768
- Qualified ID
- evroc/nvidia/Llama-3.3-70B-Instruct-FP8
Model Summary
Llama 3.3 70B is a model listing in the evroc provider catalog. It is categorized under the llama-3.3-70b-instruct-fp8 family.
The model supports text modalities across input/output paths. Reported context capacity is 131,072. Pricing is listed at $1.18/1M input and $1.18/1M output.
More From evroc
Related models from the same provider catalog.
evroc
Devstral Small 2 24B Instruct 2512
evroc/mistralai/devstral-small-2-24b-instruct-2512
evroc
E5 Multi-Lingual Large Embeddings 0.6B
evroc/intfloat/multilingual-e5-large-instruct
evroc
Gemma 4 26B A4B IT
evroc/google/gemma-4-26B-A4B-it
evroc
GLM-5.2
evroc/zai-org/GLM-5.2
evroc
GPT OSS 120B
evroc/openai/gpt-oss-120b
evroc
KB Whisper
evroc/KBLab/kb-whisper-large
evroc
Kimi K2.5
evroc/moonshotai/Kimi-K2.5
evroc
Kimi K2.6
evroc/moonshotai/Kimi-K2.6