How to Get an Experimental Labs (Experiential Labs) API Key for Free
Updated 26 October 2026.
In short: Experiential Labs (often searched as "Experimental Labs") is an AI gateway with a $0 Free plan: one API key reaches its whole model catalog, and a set of models has no per-token charge. To use the free models, the account first needs a one-time $1 card verification. The $1 is not a fee: it comes back as credits in your balance. After that, the Free plan allows up to 1M tokens a day on its free models. The API follows OpenAI's format, so the key works in most apps made for OpenAI.
What you need
- A GitHub or Google account to sign in at platform.experientiallabs.ai.
- A debit or credit card for the $1 verification. Adding the card alone does not charge it; the verification is one settled $1 charge, credited back to your balance as 100 credits.
- A computer. Windows, Mac or Linux all work.
Step 1: Sign up for the Free plan
Open the pricing page. The Free plan costs $0 a month and lists DeepSeek V4.1 Flash, GPT-6 Luna and Jev with no per-token charge (box 1). Click Start free (box 2) and sign in with GitHub or Google.

Step 2: Complete the $1 card verification
Free models stay locked until the verification is done. In the platform, open Credits, add a card and complete the $1 verification. The $1 appears in your balance as credits, so you can spend it on any model.
Two things to know:
- If the bank declines the verification, the account goes under review and cannot use models, even after a later payment. Use the Appeal button on the banner at the top of the platform and add a short note about who you are.
- A request to a free model before verification fails with
402 free_tier_requires_payment.
Step 3: Create your API key
Open API Keys in the left menu and create a key. Copy it and keep it private:
- Anyone who has your key can use your allowance and your credits.
- Never paste it into a website, a public code repository or a screenshot.
- Each key can have its own daily spend cap, requests-per-minute and tokens-per-minute limits, set in the dashboard. A low daily spend cap stops the key from spending your credits by accident.
Step 4: Pick a free model
In October 2026 the model catalog marks these models as free:
| Model | Model ID | Label in the catalog |
|---|---|---|
| Clef Flash | clef-flash | Free |
| GPT-6 Luna Decisions | gpt-6-luna-decisions | Free |
| GLM-5.3 Uncensored | glm-5.3-uncensored:free | Free, with the :free ID |
| GPT-6 Luna | gpt-6-luna | Free with Pro; no per-token charge on every plan per the pricing page |
| DeepSeek V4.1 Flash | deepseek-v4.1-flash-1017 | Free with Pro; no per-token charge on every plan per the pricing page |
| Jev | jev-latest | Free with Pro; no per-token charge on every plan per the pricing page |
A model ID ending in :free is free only: past the free allowance it stops with
free_limit_reached and is never charged. Other models switch to your credits at list price.
Step 5: Know your free limits

| Limit on the Free plan | Amount |
|---|---|
| Requests | 10 a minute, shared across your free models |
| Tokens | 250,000 a minute and 1,000,000 a day, shared |
| Daily reset | 00:00 UTC (hourly allowances reset at the top of the hour) |
| General credits | None; your $1 verification credit is your only balance |
Cached input tokens do not count against the free allowances.
Step 6: Send your first request (no programming)
Open a command window. On Windows, press the Start key, type PowerShell and open it. On a Mac,
open Terminal. Put your key in place of YOUR_API_KEY.
Windows (PowerShell):
$env:EXPLABS_API_KEY = "YOUR_API_KEY"
$body = '{"model":"gpt-6-luna","messages":[{"role":"user","content":"Explain how AI works in a few words"}]}'
$r = Invoke-RestMethod -Method Post -Uri "https://api.experientiallabs.ai/v1/chat/completions" -Headers @{ Authorization = "Bearer $env:EXPLABS_API_KEY" } -ContentType "application/json" -Body $body
$r.choices[0].message.content
Mac or Linux (Terminal):
export EXPLABS_API_KEY="YOUR_API_KEY"
curl https://api.experientiallabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EXPLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6-luna",
"messages": [{"role": "user", "content": "Explain how AI works in a few words"}]
}'
You get a short answer back, counted against your free daily tokens.
Step 7: Use it in an app made for OpenAI
| Setting the app asks for | What to enter |
|---|---|
| API key | your Experiential Labs API key |
| Base URL (sometimes called API endpoint) | https://api.experientiallabs.ai/v1 |
| Model | a free model ID from Step 4, e.g. gpt-6-luna |
Your data on the Free plan
Zero data retention is a Pro feature. On the Free plan, requests pass through the gateway to the model's provider, and how that provider handles them depends on the model. Experiential Labs' terms do not allow using your prompts to train shared models. Do not send private information.
When something goes wrong
| What you see | What it means | What to do |
|---|---|---|
| Organization under review | The $1 card verification was declined | Click Appeal on the banner with a short note about who you are |
402 free_tier_requires_payment | The $1 verification is not done yet | Complete it on the Credits page |
429 free_limit_reached | You used the free allowance for today | Wait for the reset at 00:00 UTC, or change the model and continue |
429 insufficient_quota | Your credits, a key cap or a budget ran out | Add credits, raise the limit, or use a :free model |
Words to know
- API key: the password that identifies your program to the API. See what is an API key.
- Gateway: one API that passes your request to many model providers.
- Card verification: a one-time $1 charge that unlocks the free models; it is credited back.
- Credits: prepaid balance; one credit is $0.01 of usage.
:freemodel ID: a model's free-only version, which stops instead of charging.- Token: a piece of a word; the unit models read and write. See tokens and context windows.
More free AI API keys
Free APIs with no card at all: how to get AI API keys for free lists Gemini, Groq, OpenRouter, Cloudflare and Cohere with their daily limits.
Frequently asked questions
Is Experimental Labs (Experiential Labs) free?+
It has a $0 Free plan with models that have no per-token charge, up to 1M tokens a day. The free models unlock only after a one-time $1 card verification, which is credited back to your balance.
Why does Experiential Labs need $1?+
The $1 is a card verification, required to use free and promotional models. It is a single settled charge, and the amount comes back as credits you can spend.
Which Experiential Labs models are free?+
In October 2026 the catalog marks Clef Flash, GPT-6 Luna Decisions and GLM-5.3 Uncensored (glm-5.3-uncensored:free) as free, and GPT-6 Luna, DeepSeek V4.1 Flash and Jev as having no per-token charge.
What is the Experiential Labs free limit?+
10 requests a minute, 250,000 tokens a minute and 1,000,000 tokens a day, shared across the free models. The daily allowance resets at 00:00 UTC.
Why is my Experiential Labs account under review?+
The $1 card verification was declined. Models stay locked until the review is lifted; use the Appeal button on the platform banner with a short note about who you are.
More free API key tutorials
- How to get a Gemini API key for free
- How to get a Groq API key for free
- How to get an OpenRouter API key for free
- How to get a Cloudflare Workers AI API key for free
- How to get a Cohere API key for free
- Every free AI API and its daily limit
Want to use these APIs in a desktop app? OpenCode is a free, open-source AI coding app for Windows, Mac and Linux. How to add free API keys to OpenCode and pick a model.