qwen/qwen3-next-80b-a3b-thinking
131K context$0.10/M input$0.78/M output
nvidia/qwen/qwen3-next-80b-a3b-thinkingDescription
Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...
Quick Start
curl https://router.tangle.tools/v1/chat/completions \
-H "Authorization: Bearer $TANGLE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/qwen/qwen3-next-80b-a3b-thinking",
"messages": [{"role": "user", "content": "Hello!"}]
}'Modalities
Input: TextOutput: Text
Pricing
Input$0.10/M
Output$0.78/M
Context131K tokens
Model Info
Providernvidia
IDnvidia/qwen/qwen3-next-80b-a3b-thinking