Qwen3-Next 80B Thinking (Free)
nvidia/qwen3-next-80b-a3b-thinking
nvidia
Qwen3-Next 80B MoE (3B active params) with thinking mode. Fastest top-tier reasoning on the free tier — 116 tok/s on our benchmark
Code Examples
from blockrun_llm import LLMClient
client = LLMClient() # Uses BLOCKRUN_WALLET_KEY (never sent to server)
response = client.chat("nvidia/qwen3-next-80b-a3b-thinking", "Hello!")Pricing
InputFree / 1M tokens
OutputFree / 1M tokens
Context131K tokens
Max Output16K tokens
Free model — no payment or wallet required.
Payment
Network
Base
Currency
USDC
Protocol
x402
Pay per request with USDC on Base. No subscription required.
Try It
Send a message to try Qwen3-Next 80B Thinking (Free)
Connect your wallet to enable payments