Imejis.io
Give your agent a design studio to automate your marketing - social images, e-commerce banners and…
Free+Paid
- Web app
What is Hopscotch AI?
One API for 500+ AI models, with spend limits and failover built in. Hopscotch AI: one API, every model, no markup Hopscotch is an LLM gateway: a single OpenAI-compatible API that fronts more than 500 models from Anthropic, OpenAI, Google, DeepSeek, Moonshot, Qwen and others.
Our verdict
Hopscotch is a genuinely transparent LLM gateway: 500+ models on one OpenAI-compatible API, list-price tokens with no markup, a free bring-your-own-keys mode, and spend limits that refuse requests before they cost money - plus failover that keeps agents running through provider outages without code changes.
Full review
Hopscotch AI: one API, every model, no markup
Hopscotch is an LLM gateway: a single OpenAI-compatible API that fronts more than 500 models from Anthropic, OpenAI, Google, DeepSeek, Moonshot, Qwen and others. You point your existing OpenAI SDK at its base URL, drop in one key, and every model in the catalog becomes a one-line model-name change away. The pitch that separates it from a crowded gateway market is pricing: buy credit from USD 5 and pay each provider’s list price per token – no markup, no fees, no subscription.
Spend limits that refuse, not alert
The cost-control story is stronger than most. Every API key gets a credit limit that resets daily, weekly or monthly, with monthly caps per teammate and workspace. A request that would cross a limit is refused before it reaches the provider – exactly what you want standing between an agent loop and your balance.
Hopscotch AI: one API, every model, no markup
Hopscotch is an LLM gateway: a single OpenAI-compatible API that fronts more than 500 models from Anthropic, OpenAI, Google, DeepSeek, Moonshot, Qwen and others. You point your existing OpenAI SDK at its base URL, drop in one key, and every model in the catalog becomes a one-line model-name change away. The pitch that separates it from a crowded gateway market is pricing: buy credit from USD 5 and pay each provider’s list price per token – no markup, no fees, no subscription.
Spend limits that refuse, not alert
The cost-control story is stronger than most. Every API key gets a credit limit that resets daily, weekly or monthly, with monthly caps per teammate and workspace. A request that would cross a limit is refused before it reaches the provider – exactly what you want standing between an agent loop and your balance. The Activity log lists every request with model, serving provider, outcome, tokens, cost and latency, and exports to CSV; a Usage view breaks spend down by model, provider, key and teammate.
Named models and honest failover
Hopscotch commits to running the model you name – no silent swaps to cheaper models – and says which provider actually served each request. If a provider 429s or goes down, the request moves to another key or to the next model in your own routing profile, and your code still sees one request, one response. A playground runs one prompt on up to three models side by side, billed through your key, so you can compare answers and cost before changing code. These are vendor-described behaviors; we did not send requests through the gateway.
The catch: an opaque operator
For a service that proxies your prompts, the company behind it is unusually quiet. The site announces a USD 7.5m raise but publishes no legal entity, founders, headquarters or founding year, and we found no terms of service or privacy policy pages. There is a genuine free option – bring your own provider keys and the gateway layer costs nothing with no monthly cap – but teams with compliance requirements will need those legal gaps closed first.
Ashley Richmond’s editorial view
The pricing model is the most honest I have seen in this category, and the pre-request spend limits solve a real fear for anyone running agents. Start with the free BYOK mode and a tight key limit, and watch the Activity log. The provisional desk-research score is 4.1/5.
Desk-research disclosure: Official pages reviewed September 30, 2026. No account, API key, credit purchase or gateway requests. Company identity fields remain blank; no terms or privacy pages found. All prices and the 500+ model count are vendor-published.
Who it's for
Best for
- Developers and teams running multi-model AI workloads who want one API
- one bill and hard spend limits instead of juggling provider accounts.
Not ideal for
- Organizations that require published legal terms and a named legal entity before routing prompts through a third party
- and teams needing fixed monthly pricing.
How we tested
Ashley Richmond desk research September 30, 2026. Official site pages reviewed: home, pricing, llms.txt, index.md, docs site. No API key, account, credit purchase or request through the gateway. Identity: no legal entity, founders, headquarters or founding year published; company fields left blank. The site announces a USD 7.5m raise without naming the entity. No terms of service or privacy policy pages found (URLs return 404) and left blank. Support: pricing page advertises email and chat support; llms.txt publishes hello@hopscotchlabs.ai (labeled Sales) and a Discord invite. Pricing facts (USD 5 minimum credit, no markup/fees/subscription, free BYOK with no monthly cap) from the official pricing page. The 500+ model count and failover behavior are vendor claims. Media: official brand-kit mark plus genuine product UI captured from hopscotchlabs.ai (request activity log, model catalog, playground). Integrations chips claude and chatgpt checked because Anthropic and OpenAI models are vendor-documented named chips. Listing titled Hopscotch AI per source CSV; vendor branding is simply Hopscotch. Sources: https://hopscotchlabs.ai/ ; https://hopscotchlabs.ai/pricing ; https://docs.hopscotchlabs.ai ; https://hopscotchlabs.ai/llms.txt ; https://www.producthunt.com/products/hopscotch-7
At a glance
| Pricing | Usage-based |
|---|---|
| Free plan | No |
| Free trial | No |
| Pricing page | View pricing |
| Platforms | Web app, API / SDK |
| API | No |
| Apps Insight Score | 42/100 |
| Implementation | Easy |
| Learning curve | Beginner |
Why this app scored 42/100
Editorial Review 25/30
- Product quality 8/10 8/10
- Ease of use 4/5 4/5
- Feature depth 4/5 4/5
- Innovation 4/5 4/5
- Value for money 3/3 3/3
- Recommendation confidence 2/2 2/2
Trust & Verification 4/25
- AppsInsight badge installed Badge not installed 0/15
- HTTPS website HTTPS 1/1
- Business support email Provided 1/1
- Privacy policy published Missing 0/2
- Terms of service published Missing 0/1
- Security certifications None listed 0/2
- Knowledge base / help center Provided 2/2
- Social profiles linked 0 profiles linked 0/1
Community 0/20
- Verified reviews & rating 0 reviews (5 needed) 0/15
- Recent reviews No reviews yet 0/5
Product Profile 10/20
- Detailed description 441 words 3/3
- Screenshots 2 screenshots 1/3
- Demo video No demo video 0/2
- FAQ 6 items 1/2
- Feature list 8 items 1/2
- Pricing published Plan tiers published 3/3
- Pros & cons Pros & cons listed 1/1
- Integrations 2 integrations 0/2
- API available No 0/1
- Company details 0 of 3 details filled 0/1
Freshness 3/5
- Listing recently updated Updated 2 days ago 3/3
- Recent changelog entry No changelog entries 0/2
Editorial points are assigned by AppsInsight editors and cannot be purchased or influenced.
Integrations
Built for
Industry
SaaS & technology
How Hopscotch AI compares
| Feature | Hopscotch AI | Imejis.io | Bucketree |
|---|---|---|---|
| Rating | 4.1 / 5 | 4.1 / 5 | 3.9 / 5 |
| Pricing | Usage-based | Free+Paid | Free+Paid |
| Starting price | — | — | $25/year for 3 Macs |
| Free plan | Included | Included | Included |
| Free trial | No | No | Yes |
| Platforms | Web app, API / SDK | Web app | macOS |
| Best for | Developers and teams running multi-model AI workloads who want one API, one bill and hard spend limits instead of juggling provider accounts. | Marketing teams and developers who need campaign images generated at scale - social posts, e-commerce banners, personalized creative - via a one-POST API or directly from Claude, ChatGPT or Cursor over MCP. | Apple silicon Mac users with B2 buckets, B2 administrators, small studios managing files and version cleanup |
Key features
500+ models through one API
Call models from Anthropic, OpenAI, Google, DeepSeek, Moonshot, Qwen, Meta and more on one OpenAI-compatible base URL, billed to one balance - no separate integration, account or bill per provider.
OpenAI SDK compatible
Switch by changing three settings: base URL, API key and model name. The rest of existing OpenAI SDK code stays the same, per the vendor.
Named models, no silent swaps
The model you name is the model that runs; the Activity log shows which provider served each request. Hopscotch says it will never substitute a different model.
Routing profiles and fallbacks
Configure model order with automatic fallbacks - if a provider 429s or has an outage, the request moves to another key or the next model in your routing profile, and your code still sends one request and gets one response.
Spend limits everywhere
Credit limits per API key resetting daily, weekly or monthly, plus monthly limits per teammate and workspace. A request that would cross a limit is refused before it reaches the provider - protection against runaway agent loops.
Activity log and usage analytics
Every request listed with model, serving provider, outcome, tokens, cost and latency, exportable to CSV. Usage view breaks spend down by model, provider, key and teammate.
Model playground
Run one prompt on up to three models side by side, billed through your key like any other request, to compare answers and cost before changing code.
Transparent per-model pricing
Catalog lists each model with context window and price per million tokens; where several providers serve the same open-weight model, each upstream and its price is shown.
Key benefits
- One integration replaces a dozen provider accounts, keys and bills.
- Token spend stays under control with limits that refuse requests before they cost money.
- Failover keeps agent workloads running through provider outages without code changes.
- Compare models on your own prompts and pay list price - no markup, no fees, no subscription.
Pricing
Usage-based
Pay as you go
- Buy credit (from USD 5)
- then pay each provider list price per token with no markup
- no fees and no subscription. Bring-your-own-provider-keys mode is free with no monthly cap. Includes routing
- fallbacks
- usage analytics
- request logs
- spend limits per key/teammate/workspace
- and email and chat support. Model prices are per-million-token and listed per model in the catalog.
Pros & Cons
Pros
- No markup, fees or subscription: you pay each provider's list price for tokens used, credit from USD 5.
- Bring-your-own-keys mode is free with no monthly cap, so the gateway layer can cost nothing.
- Spend limits at key, teammate and workspace level with pre-request refusal - rare among LLM gateways.
- Genuine product UI on the official site (activity log, model catalog, playground) and public docs.
Cons
- Young company with an opaque identity: no legal entity, founders, headquarters or founding year published on the site.
- No terms of service or privacy policy pages found (URLs 404) - a governance gap for a service that proxies prompts.
- Pay-as-you-go credit model means spend is variable by design; heavy users must manage limits actively.
- 500+ model claim and failover behavior are vendor-described; we did not run requests through the gateway.
Screenshots & media
Hopscotch AI alternatives
View all alternatives
Bucketree
Native Mac management for Backblaze B2 buckets, keys and file operations.
Free planPaid from $25/year for 3 MacsFree trial
- macOS
More API Tools apps
User reviews
No reviews yet. Be the first to review this app.
Write a review
Already have an account? Log in to track your reviews.
Frequently asked questions
How much does Hopscotch cost?
There is no subscription. You buy credit from USD 5 and pay each provider's list price per token - the vendor advertises no markup, no fees. Bringing your own provider keys is free with no monthly cap. Per-model prices are listed in the catalog.
Do I have to change my code?
Three settings, per the vendor: set the base URL to api.hopscotchlabs.ai/v1, use your Hopscotch API key, and name the model with its provider prefix (for example anthropic/claude-sonnet-5). Existing OpenAI SDK code otherwise stays the same.
Will Hopscotch swap my model for a cheaper one?
No. The vendor states the model you name is the model that runs, and the Activity log shows which provider served it. Fallbacks only fire on errors like a provider 429 or outage, and only to models in your own routing profile.
What stops an agent in a loop from draining my balance?
Spend limits. Each API key can have a credit limit that resets daily, weekly or monthly, with monthly limits per teammate and workspace. A request that would cross a limit is refused before it reaches the provider.
Is there a free option?
Yes: bring your own provider keys and the gateway layer is free with no monthly cap - you still pay your providers directly for tokens. Using Hopscotch's keys and balance is pay-as-you-go from a USD 5 minimum credit purchase.
Who makes Hopscotch?
The site brands the product Hopscotch (hopscotchlabs.ai) and announces a USD 7.5m raise, but publishes no legal entity, founders, headquarters or founding year, and no terms or privacy pages were found. Contact is hello@hopscotchlabs.ai plus a Discord community.