Qwen3.8 Flash Next FP8

Overview

Qwen3.8 Flash Next FP8 is a efficient model from Hugging Face with a 0 context window, supporting function calling. Priced at $0.000150/1K input, $0.000470/1K output.

ANT Routing Intelligence

Limited routing data available for Qwen3.8 Flash Next FP8. Intelligence insights will appear as more requests are routed through ANT.

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="huggingface/Qwen/Qwen3.8-Flash-Next-FP8",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Try it or ask an AI