What is the context window of Llama 3.3 70B by evroc?

Llama 3.3 70B by evroc has a context window of 131K tokens. It supports up to 131K input tokens and can generate up to 33K output tokens.

What input and output types does Llama 3.3 70B support?

Llama 3.3 70B by evroc accepts text as input and can generate text as output.

Is Llama 3.3 70B by evroc open source?

Yes, Llama 3.3 70B by evroc has open weights, meaning the model weights are publicly available for download and self-hosting.

Back to Models

Llama 3.3 70B API

evroc

About

Process massive datasets with Llama 3.3 70B, featuring an expansive 131K context window for long-document analysis. This model delivers cost-effective pricing at $1.18/1M input and $1.18/1M output tokens, open weights architecture. Access Llama 3.3 70B via the evroc API with up to 33K output tokens.

Capabilities

Input Modalities

text

Output Modalities

text

Reasoning

Structured Output

Tool Use

WeightsOpen

Temperature

Fixed

Attachment

Not Supported

Limits

Context Window

131K

Tokens

Input Limit

131K

Tokens

Max Output

33K

Tokens

Pricing

Standard (per 1M tokens)

Input

$1.18

Output

$1.18

Frequently Asked Questions

Llama 3.3 70B by evroc costs $1.18 per 1M input tokens and $1.18 per 1M output tokens.

Model Details

nvidia/Llama-3.3-70B-Instruct-FP8

Provider

evroc

Family

llama

Release Date

Dec 1, 2024

Knowledge Cutoff

N/A

API Integration

NPM Package

@ai-sdk/openai-compatible

Environment Variables

EVROC_API_KEY

API Base URL

https://models.think.evroc.com/v1

Documentation