Llama 2 70b Hf

FeatherlessQuality: 50/100Degraded

Try in Playground

✗ Vision✗ Reasoning✗ Tool Use✓ Streaming✓ System Messages

Overview

Llama 2 70b Hf is a efficient model from Featherless with a 4K context window. Available through ANT's unified API.

ANT Routing Intelligence

Limited data

Total Requests

P50 Latency

15785ms

P95 Latency

15785ms

Selection Rate

0.0%

of eligible requests

Intelligence Score

15/100

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.antbase.ai/v1",
    api_key="YOUR_ANT_API_KEY",
)

response = client.chat.completions.create(
    model="featherless/NousResearch/Llama-2-70b-hf",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)