BlockRun
Get started
Free · Llama 3.2 11B Vision

Free Llama API.
No key. No subscription.

Meta's Llama 3.2 11B Vision — 128K context, takes images as well as text. No key, no wallet, no subscription. Just call it.

Try in 10 secondsSee all 6 waysWant Claude / GPT-5? Pay-per-call →
Quickstart · 10 seconds

Try it now.

No API key. No wallet. No signup. Paste this into any terminal — the response streams back from Llama 3.2 11B Vision, routed through BlockRun.

curl
curl https://blockrun.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/llama-3.2-11b-vision",
    "messages": [{"role": "user", "content": "Write a haiku about open-source models"}]
  }'
See all 6 waysFull API reference →
Spotlight
Llama 3.2 11B Vision (Free)
nvidia/llama-3.2-11b-vision
Context
128K
Price
free
Modalities
text · image · video · audio
Best for
vision
Six ways to call it

6 ways to use Llama free.

BlockRun is the access layer. Pick the surface that matches how you build — terminal, notebook, IDE, agent runtime — and the same free models work everywhere.

  1. 01

    Python SDK

    pip install blockrun-llm — or any OpenAI-compatible client

    Learn more →
    python
    # Works with the OpenAI SDK — no key required for free models
from openai import OpenAI

client = OpenAI(
    base_url="https://blockrun.ai/api/v1",
    api_key="not-needed-for-free-models",
)

response = client.chat.completions.create(
    model="nvidia/llama-3.2-11b-vision",
    messages=[{"role": "user", "content": "Write a haiku about open-source models"}],
)
print(response.choices[0].message.content)
  2. 02

    Franklin Agent

    Llama-family models are great for agent loops — Franklin Agent runs it on your terminal

    Learn more →
    shell
    # Install Franklin Agent
npm i -g @blockrun/franklin

# Run with this model
franklin start --model nvidia/llama-3.2-11b-vision -p "Summarize the README"
  3. 03

    cURL

    no key, no wallet, paste in any terminal

    Learn more →
    shell
    curl https://blockrun.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/llama-3.2-11b-vision",
    "messages": [{"role": "user", "content": "Write a haiku about open-source models"}]
  }'
  4. 04

    ClawRouter

    smart router for OpenClaw / Claude Code — auto-picks free models when possible

    Learn more →
    shell
    # Install once
npm install -g @blockrun/clawrouter

# Then point any OpenAI-compatible client at the local proxy.
# ClawRouter routes to nvidia/llama-3.2-11b-vision (or the cheapest capable model)
# without changing your code.
  5. 05

    Claude Code MCP

    19 tools for Claude Code, Cursor & ChatGPT — call any free model from inside your editor

    Learn more →
    shell
    # Add the BlockRun MCP server (Claude Code, Cursor, or ChatGPT desktop)
claude mcp add blockrun -s user -- npx -y @blockrun/mcp@latest

# Then call from inside the editor:
#   blockrun_chat(model="nvidia/llama-3.2-11b-vision", messages=[{role:"user", content:"…"}])
  6. 06

    TypeScript SDK

    npm install @blockrun/llm — or any OpenAI-compatible client

    Learn more →
    typescript
    // Works with the OpenAI SDK — no key required for free models
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://blockrun.ai/api/v1",
  apiKey: "not-needed-for-free-models",
});

const r = await client.chat.completions.create({
  model: "nvidia/llama-3.2-11b-vision",
  messages: [{ role: "user", content: "Write a haiku about open-source models" }],
});
console.log(r.choices[0].message.content);
Trust / Defaults

We don't share
your data.

Your prompt goes to the AI provider you picked. Nothing else, nowhere else. No training, no retention beyond the request, no profile linking.

Read the privacy policyTerms →
We don't share your data
No training, no retention beyond the request. Your prompt is forwarded only to the AI provider you select.
No accounts, no sign-up
Wallet in, prompt out. Pseudonymous by default — no email, no phone number, no identity documents.
Open-source SDKs, MIT
Read the code, audit the wire format, run it yourself. @blockrun/llm and blockrun-llm on npm and PyPI.
When free isn't enough

Want Claude, GPT-5,
or Gemini too?

No subscription. No monthly minimum. Pay per call in USDC via x402 — works the same endpoint, same SDK, same model IDs. Connect a wallet, top up $5, call any frontier model. No credit card.

See pay-per-call pricingGet started
FAQ

Everything you might
be wondering.

Is the Llama API really free?
Yes. Meta's Llama 3.2 11B Vision is hosted free on NVIDIA's build.nvidia.com tier and exposed through BlockRun without payment, signup, or wallet. We pass NVIDIA's quota straight through.
What happened to Llama 4 Maverick and Nemotron Super 49B?
Both are gone from our free upstream — Maverick hangs and NVIDIA published an end-of-life for the 49B on 2026-08-30. Calls pinned to either ID auto-redirect to a live free model, so they still return 200, and this page will switch back if a newer free Llama appears.
Do I need an API key?
No. The endpoint accepts unauthenticated requests when the model is free. For paid models (Claude, GPT-5, Gemini), you connect a wallet and pay per call via x402.
What's the catch?
NVIDIA's free tier may use prompts for service improvement — don't send PII or proprietary data. For private inference, route to paid models or run Llama yourself.
What's the request size limit?
128 KB per request body for free models (vs 5 MB for paid). Plenty for most chat workloads but not for long context dumps.
Can I use the OpenAI SDK?
Yes. BlockRun is OpenAI-compatible — set base_url to https://blockrun.ai/api/v1 and any OpenAI client just works.