Last refreshed 2026-10-19. Next refresh: weekly.
Why use Qwen3-Next-80B-A3B-Thinking on Vercel AI Gateway?
Vercel AI Gateway offers Qwen3-Next-80B-A3B-Thinking with pay-as-you-go pricing at $0.15/1M input tokens. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.
Compare Qwen3-Next-80B-A3B-Thinking across 4 providers to find the best fit for your use caseSetup recipe
Python + curlpip install openaiexport AI_GATEWAY_API_KEY=...import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],alibaba/qwen3-next-80b-a3b-thinkingRequest example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
model="alibaba/qwen3-next-80b-a3b-thinking",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "alibaba/qwen3-next-80b-a3b-thinking", not the LLMReference slug "qwen3-next-80b-a3b-thinking".
- creator/model-name e.g. kwaipilot/kat-coder-pro-v2
- The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.
Compare Qwen3-Next-80B-A3B-Thinking Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| OpenRouter | $0.15 | $1.20 |
| Vercel AI Gateway | $0.15 | $1.20 |
| Together AI | — | — |
| Fireworks AI | — | — |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.15 |
| Output tokens | $1.20 |
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.