BlockRun
Back to Pricing

Llama 4 Maverick (Free)

nvidia/llama-4-maverick

nvidia

Meta's Llama 4 Maverick MoE (17B x 128 experts) hosted free by NVIDIA

Code Examples

from blockrun_llm import LLMClient

client = LLMClient()  # Uses BLOCKRUN_WALLET_KEY (never sent to server)
response = client.chat("nvidia/llama-4-maverick", "Hello!")

Pricing

InputFree / 1M tokens
OutputFree / 1M tokens
Context131K tokens
Max Output16K tokens

Free model — no payment or wallet required.

Payment

Network
Circle Gateway (mainnet)
Currency
USDC
Protocol
x402

Pay per request with USDC on Base. No subscription required.

Try It

Send a message to try Llama 4 Maverick (Free)

Connect your wallet to enable payments