Pay only for what you use
Create an account and get 10,000 credits to run your first tests. Top up from $10 when you need more. Upgrade to PRO when you run enough tests to make the lower markup worth it.
Pay as you go
Most flexible$10min top-up
10,000 credits included on signup
Create an account and get a 10,000 credit signup gift. After that, top up when you need more tests: $10, $30 or $100. $10 buys about 33,000 credits. Credits roll over and never expire.
- Unlimited tests (credits deducted per run)
- Up to 10 models per test
- x3 markup on credit purchases
- Credits never expire
PRO
$20/monthly
50,000 credits included every month
50,000 credits added every month while you subscribe, a lower markup on every top-up ($10 buys about 66,000 credits) and more models per run.
- 50,000 credits included every month
- Unlimited tests (credits deducted per run)
- Up to 20 models per test
- x1.5 markup on credit purchases instead of x3
New accounts also get a 10,000 credit signup gift: 3,000 credits for confirming your email, 4,000 for your first test and 3,000 for a short survey. Credits are what you spend on a run. 10,000 credits equal $1 of real model usage, before the plan markup applied when you buy credits.
How markup works
Credits are priced by plan. The markup covers platform infrastructure and features, and it is applied once, when you buy credits. The cost estimate you see before a run has no markup in it.
Break-even: About $25 /month
Above it, PRO gives you more credits than pay as you go
Pay as you go
x3
$10 buys about 33,000 credits ($3.33 of model usage)
PRO
x1.5
$10 buys about 66,000 credits ($6.67 of model usage)
Common questions about model testing
Are these real API calls or cached results?
Real API calls, always. We send your prompt live to each model's API simultaneously. Results are never cached or pre-computed. This means costs, speeds, and token counts you see are exactly what you'd experience integrating the model directly in your app.
How accurate are cost figures and estimates?
What a run cost is calculated from the tokens each model really used and its current price, so it is exact for that run. The estimate you see before a run is a worst case, shown in credits with no markup, assuming the longest possible answer from every model, so the real charge is usually lower. A savings projection compares your current monthly bill with each alternative model's measured cost per call. It is a cost comparison only, never a verdict on quality.
What do I get when I create an account?
A 10,000 credit signup gift: 3,000 credits for confirming your email, 4,000 for running your first test and 3,000 for a short survey. 10,000 credits equal $1 of real model usage, enough for several small tests. After that you top up from $10 or subscribe to PRO. Credits you buy never expire.
How do workflows work?
A workflow is a chain of up to 10 prompts, each with its own models and settings. The app runs them one by one, in order, and shows clear results for every step. Each step runs on its own prompt, so one step's answer is not fed into the next. Every run is kept on the workflow's Runs tab, where you can compare runs and see what changed since the previous one in cost, speed and answers. You can put a spend cap on a run, schedule it as a workflow alert, or import the model-calling steps from an n8n file.
What happens to my prompts?
Your prompts are stored in your test history so you can revisit results. We don't sell your prompts or use them to train AI models. They are sent to the provider of each model you pick, and every provider has its own terms, which we don't control (our Privacy Policy links to them). We use anonymized task type and winner picks for Community Picks and our benchmarks, and you can turn that off in Settings. You can delete any test at any time.
Why not just use each provider's playground?
Setting up all providers individually requires creating 9 accounts, adding billing to each (minimum $90+ in API credits across providers), and spending 24+ hours on integration before seeing any results. We handle all of that - your first result in 30 seconds.
When does PRO pay for itself vs Pay as you go?
PRO is $20 a month. It adds 50,000 credits every month (they never expire, and you keep the unused ones if you cancel), and the credits you buy on top cost less because the markup is x1.5 instead of x3. If you spend more than about $25 a month in total, PRO gives you more credits than pay as you go. At $60 a month, PRO gives you about 58% more credits for the same money. Below about $25 a month, pay as you go is the better fit.
Are you affiliated with any model providers?
No. We have no financial relationship with OpenAI, Anthropic, Google, or any other model provider. We don't receive payments for featuring any model or influencing results. Our independence is intentional - a comparison tool that favors one provider is useless. We pay market rates for API access like everyone else.
Start cutting cost per inference
- 50+ models
- No API keys
- Results in 30 seconds