BlockRun
Get an API key
Free · Reasoning

Free Reasoning API.
No key. No subscription.

Nemotron 3.5 Lightning (131K context, thinking mode) and Nemotron 3 Ultra 550B — 550B total / 55B active, the largest free model in the catalog. No key, no signup.

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 Nemotron 3.5 Lightning, routed through BlockRun.

curl
curl https://blockrun.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3.5-lightning",
    "messages": [{"role": "user", "content": "Solve: 7 friends share 23 cookies equally; how many are left over?"}]
  }'
See all 6 waysFull API reference →
Spotlight
Nemotron 3.5 Lightning (Free)
nvidia/nemotron-3.5-lightning
Context
1M
Price
free
Best for
reasoning
Nemotron 3 Ultra 550B (Free)
nvidia/nemotron-3-ultra-550b
Context
1M
Price
free
Best for
reasoning
Six ways to call it

6 ways to use these reasoning models 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

    Franklin Agent

    Free reasoning model + Franklin Agent = strong terminal reasoning agent, free

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

# Run with this model
franklin start --model nvidia/nemotron-3.5-lightning -p "Summarize the README"
  2. 02

    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/nemotron-3.5-lightning",
    messages=[{"role": "user", "content": "Solve: 7 friends share 23 cookies equally; how many are left over?"}],
)
print(response.choices[0].message.content)
  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/nemotron-3.5-lightning",
    "messages": [{"role": "user", "content": "Solve: 7 friends share 23 cookies equally; how many are left over?"}]
  }'
  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/nemotron-3.5-lightning (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/nemotron-3.5-lightning", 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/nemotron-3.5-lightning",
  messages: [{ role: "user", content: "Solve: 7 friends share 23 cookies equally; how many are left over?" }],
});
console.log(r.choices[0].message.content);
Trust / Defaults

Free models,
free-tier terms.

Free models are served on free tiers whose terms may let the host use prompts to improve its service, so don't send sensitive data to a free model. Paid models run on paid tiers that don't train on API traffic. We never sell your data.

Read the privacy policyTerms →
Free-tier terms apply
Free models run on free tiers whose terms may let the host use prompts to improve its service. Don't send sensitive data to a free model.
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 an API key
FAQ

Everything you might
be wondering.

Which free reasoning model should I pick?
Default to Nemotron 3.5 Lightning — thinking-mode reasoning at ~35 tok/s with a 131K window. Pick Nemotron 3 Ultra 550B when you want the most capable free model: 550B total / 55B active, the largest on the tier. Both are free, no key.
Where's DeepSeek V4?
DeepSeek V4 Flash/Pro were retired from our free upstream (NVIDIA's on-demand tier stopped serving them). Calls to nvidia/deepseek-v4-* are auto-rerouted to a healthy free reasoning model so they still return 200. For dedicated DeepSeek, use the paid deepseek/* models with a wallet.
Is it really free?
Yes. Hosted free on NVIDIA's build.nvidia.com tier, passed straight through BlockRun. No signup, no wallet.
How much context can I use for free?
Up to the model's own window — each spotlight card above shows it — but the request body is capped at 128 KB on the free tier. For multi-megabyte context dumps, switch to paid models with a wallet (5 MB cap).
What if NVIDIA's upstream is down?
BlockRun's free-model health gate auto-routes around any dead free model in real time, so your call still returns 200 from a healthy model.