BlockRun
Get started
Free · open-weights alternatives

Free Mistral API.
No key. No subscription.

Our free Mistral upstream is down — calls to nvidia/mistral-* still return 200, answered by a healthy free model. Meanwhile, two free open-weights coding models with no key and the same OpenAI-compatible endpoint.

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 Cohere North Mini Code, routed through BlockRun.

curl
curl https://blockrun.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cohere/north-mini-code",
    "messages": [{"role": "user", "content": "Write a one-paragraph bio for an open-source maintainer"}]
  }'
See all 6 waysFull API reference →
Spotlight
Cohere North Mini Code (Free)
cohere/north-mini-code
Context
256K
Price
free
Best for
coding
Poolside Laguna XS 2.1 (Free)
poolside/laguna-xs-2.1
Context
131K
Price
free
Best for
coding
Six ways to call it

6 ways to use the open-weights alternatives 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

    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": "cohere/north-mini-code",
    "messages": [{"role": "user", "content": "Write a one-paragraph bio for an open-source maintainer"}]
  }'
  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="cohere/north-mini-code",
    messages=[{"role": "user", "content": "Write a one-paragraph bio for an open-source maintainer"}],
)
print(response.choices[0].message.content)
  3. 03

    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 cohere/north-mini-code (or the cheapest capable model)
# without changing your code.
  4. 04

    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: "poolside/laguna-xs-2.1",
  messages: [{ role: "user", content: "Write a one-paragraph bio for an open-source maintainer" }],
});
console.log(r.choices[0].message.content);
  5. 05

    Franklin Agent

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

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

# Run with this model
franklin start --model cohere/north-mini-code -p "Summarize the README"
  6. 06

    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="cohere/north-mini-code", messages=[{role:"user", 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.

Which Mistral should I pick?
None are available free right now — NVIDIA retired Mistral Large 3, Mistral Small 4 and, on 2026-08-30, Mistral Nemotron. Calls to any nvidia/mistral-* ID still return 200: BlockRun's health gate answers them with a healthy free model. BlockRun has no paid Mistral SKU either, so for a real Mistral you need Mistral's own API.
Why coding models as the alternative?
Mistral's free-tier draw was its coding line — Codestral, Devstral. Cohere North Mini Code and Poolside Laguna XS 2.1 are the free coding models in the catalog today: compact, fast, and callable with no key on the same endpoint.
Is the API free for production use?
BlockRun routes free requests through the free upstream pools with no per-call billing. Throughput is subject to each pool's quota — for guaranteed capacity, switch to paid models with a wallet.
Do these support function calling?
Yes — they emit OpenAI-compatible tool_calls. Same wire format as paid models, just route through the free endpoint.
What happened to Mistral Small 4 / Devstral 2 / Mistral Large 3 675B?
NVIDIA retired Mistral Small 4 119B from its free tier (2026-08-03), Devstral 2 was pulled earlier (404), and Mistral Large 3 675B stopped responding as of 2026-07-20. Calls to any of them auto-reroute to a healthy free model via BlockRun's health gate, so requests still return 200. They come back automatically if NVIDIA restores them.