Using Qwen3-Next-80B-A3B-Thinking on Fireworks AI
Implementation guide · Qwen3 · Alibaba
Fireworks AI exposes Qwen3-Next-80B-A3B-Thinking through model ID accounts/fireworks/models/qwen3-next-80b-a3b-thinking. Use the setup steps, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-10-19. Next refresh: weekly.
Quick Start
- 1
- 2Use the Fireworks AI SDK or REST API to call
accounts/fireworks/models/qwen3-next-80b-a3b-thinking— see the documentation for request format.
Code Examples
pip install openaiFIREWORKS_API_KEYaccounts/fireworks/models/qwen3-next-80b-a3b-thinkingFireworks model IDs use "accounts/fireworks/models/{model-name}" format, e.g. "accounts/fireworks/models/llama4-scout-instruct-basic" or "accounts/fireworks/models/deepseek-r1".
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["FIREWORKS_API_KEY"],
base_url="https://api.fireworks.ai/inference/v1"
)
response = client.chat.completions.create(
model="accounts/fireworks/models/qwen3-next-80b-a3b-thinking",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Capabilities
About Qwen3-Next-80B-A3B-Thinking
Qwen3-Next-80B-A3B-Thinking is the thinking-mode variant of Alibaba Qwen's Qwen3-Next-80B-A3B, an 80B-parameter mixture-of-experts model with 3B active parameters per token and a hybrid Gated DeltaNet + Gated Attention architecture. It was announced on 2025-09-11 alongside the Instruct variant, with Apache-2.0 open weights on Hugging Face.