BlockRun
Free · Qwen3 Thinking + Coder

Free Qwen3 API.
No key. No subscription.

Qwen3-Next 80B Thinking (3B active, 116 tok/s — the fastest free reasoning we ship) and Qwen3 Coder 480B (35B active, code-tuned). No key.

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 Qwen hosted free on NVIDIA, routed through BlockRun.

curl
curl https://blockrun.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/qwen3-next-80b-a3b-thinking",
    "messages": [{"role": "user", "content": "Refactor this loop into a list comprehension: result = []\nfor x in items:\n  if x > 0: result.append(x*2)"}]
  }'
See all 6 waysFull API reference →
Spotlight
Qwen3-Next 80B Thinking (Free)
nvidia/qwen3-next-80b-a3b-thinking
Context
131K
Price
free
Best for
reasoning · coding
Qwen3 Coder 480B (Free)
nvidia/qwen3-coder-480b
Context
131K
Price
free
Best for
coding
Six ways to call it

6 ways to use Qwen 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

    ClawRouter

    Drop ClawRouter into Cursor or Continue and get free Qwen3 Coder

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

# Then point any OpenAI-compatible client at the local proxy.
# ClawRouter routes to nvidia/qwen3-coder-480b (or the cheapest capable model)
# without changing your code.
  2. 02

    Claude Code MCP

    From Claude Code, call Qwen3 Coder for free as a second-opinion model

    Learn more →
    shell
    # Add the BlockRun MCP server (Claude Code, Cursor, or ChatGPT desktop)
claude mcp add blockrun --transport http https://mcp.blockrun.ai/mcp

# Then call from inside the editor:
#   blockrun_chat(model="nvidia/qwen3-coder-480b", messages=[{role:"user", 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/qwen3-next-80b-a3b-thinking",
    "messages": [{"role": "user", "content": "Refactor this loop into a list comprehension"}]
  }'
  4. 04

    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/qwen3-next-80b-a3b-thinking",
    messages=[{"role": "user", "content": "Refactor this loop into a list comprehension"}],
)
print(response.choices[0].message.content)
  5. 05

    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/qwen3-coder-480b",
  messages: [{ role: "user", content: "Refactor this loop into a list comprehension" }],
});
console.log(r.choices[0].message.content);
  6. 06

    Franklin

    the AI agent with a wallet — free OSS models for routine tasks, paid models on demand

    Learn more →
    shell
    # Install Franklin
curl -fsSL https://franklin.run/install | sh

# Run with this model
franklin chat --model nvidia/qwen3-next-80b-a3b-thinking "Summarize the README"
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 KYC
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.

Why two Qwen3 models?
Qwen3-Next 80B Thinking is the speed-tuned reasoning workhorse (116 tok/s, 3B active params). Qwen3 Coder 480B is code-specialised. Pick Thinking for general reasoning, Coder for IDE / refactor / code-gen tasks.
Is Qwen3 Coder good enough for Cursor / Continue / Claude Code?
Yes — 480B MoE with 35B active. It's competitive with closed-source code models on most refactoring and review tasks. Drop it in via ClawRouter or the BlockRun MCP server.
How does it compare to GPT-4 / Claude on code?
Frontier closed models are still ahead on the hardest novel problems, but Qwen3 Coder is dramatically cheaper (free, here) and matches them on most production refactor / explain / lint workflows.
Will my prompts be used to train Qwen?
NVIDIA's free tier (which hosts these models) reserves the right to use prompts for service improvement. Don't send proprietary code you wouldn't paste into a public Discord. For private inference, switch to paid models.
Does the Thinking model show its reasoning?
Yes — set reasoning_effort=high or use the OpenAI thinking_content extension. Reasoning tokens stream as they generate.