BYOK gateway
Free
No gateway fee; external provider bill separate
- Included scope
- Gateway and usage controls
Hopscotch AI
● Identity checkedAI model gateway with usage controls · Official-source review 2026-10-09
Hopscotch routes application requests through an OpenAI-compatible API to a catalog of model providers. It advertises configurable fallbacks, request logs and spending limits by key, teammate and workspace.
- Category
- AI model gateway with usage controls
- Free access
- Gateway requests using your own provider keys have no Hopscotch charge or monthly cap advertised. Underlying provider usage is billed separately; no free inference allowance confirmed.
- API access
- Chat Completions, Responses and models endpoints advertised; SDK base URL/key configuration and usage lookup supported.
Is Hopscotch AI right for you?
A good fit for
Relevant to developers comparing models and controlling spend who can validate endpoint feature compatibility.
Before you choose
Prepaid credit starts at $5, provider list token prices without markup/subscription. Own-key failures do not switch to paid vendor keys. Some provider-hosted web search/audio/tools are unsupported. Fallbacks follow configured profiles; default claimed same-model behavior has provider exceptions described in FAQ. Model catalog and example prices change and were not independently benchmarked. Default $50/minute spend cap is configurable, not total budget. No account/key, request, payment or routing test performed.
Workflow and handoff
Check the current model catalog and endpoint support, set narrow spend caps and compare correctness/cost on representative prompts before routing production traffic.
Pricing and practical limits
Prepaid credit starts at $5, provider list token prices without markup/subscription. Own-key failures do not switch to paid vendor keys. Some provider-hosted web search/audio/tools are unsupported. Fallbacks follow configured profiles; default claimed same-model behavior has provider exceptions described in FAQ. Model catalog and example prices change and were not independently benchmarked. Default $50/minute spend cap is configurable, not total budget. No account/key, request, payment or routing test performed.
Review method
Official product evidence reviewed on 2026-10-09; product artwork inspected visually. No hands-on vendor application test was performed. Application performance, security claims and plan enforcement were not independently tested.
What it can do
Features & capabilities
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Product workflow | Hopscotch routes application requests through an OpenAI-compatible API to a catalog of model providers. It advertises configurable fallbacks, request logs and spending limits by key, teammate and workspace. | Facts sourced | 2026-10-09 |
| Pricing and restrictions | Prepaid credit starts at $5, provider list token prices without markup/subscription. Own-key failures do not switch to paid vendor keys. Some provider-hosted web search/audio/tools are unsupported. Fallbacks follow configured profiles; default claimed same-model behavior has provider exceptions described in FAQ. Model catalog and example prices change and were not independently benchmarked. Default $50/minute spend cap is configurable, not total budget. No account/key, request, payment or routing test performed. | Facts sourced | 2026-10-09 |
Understand the total cost
Hopscotch AI pricing & plans
Prepaid provider usage
Not listed
From $5 prepaid; variable provider token rates
- Included scope
- Model requests and optional auto-top-up
Alternatives to Hopscotch AI
View all ↗
Token HarborToken Harbor exposes several model providers through one OpenAI-compatible API with free routes and paid usage passes. Users choose model IDs, review usage allowances and decide whether calls pause or continue from a paid balance at the pass limit.
Explore tool
AurikoAuriko provides an OpenAI-compatible model gateway with provider routing, fallback, key orchestration and cost analytics. It supports user-supplied or platform keys and configurable objectives such as cost, latency and data policy.
Explore tool
RunInfraRunInfra provides hosted open models through OpenAI- and Anthropic-compatible APIs. It offers prepaid token billing and workspace coding plans, with session-aware caching and separately reported cached-token usage.
Explore toolThe practical questions
Frequently asked questions
Was the application hands-on tested?
No. This listing is based on dated official-source evidence and a visual artwork check. Unconfirmed costs and restrictions are identified explicitly.
What is Hopscotch AI used for?
Hopscotch routes application requests through an OpenAI-compatible API to a catalog of model providers. It advertises configurable fallbacks, request logs and spending limits by key, teammate and workspace.
Does Hopscotch AI have a free plan?
Gateway requests using your own provider keys have no Hopscotch charge or monthly cap advertised. Underlying provider usage is billed separately; no free inference allowance confirmed.. This record lists ongoing free access; check the plan limits before starting.
How much does Hopscotch AI cost?
No paid monthly price is listed; this record treats the product as free to start. See the plan cards for entitlements, billing commitments and seat minimums.
Can I use Hopscotch AI through an API?
Chat Completions, Responses and models endpoints advertised; SDK base URL/key configuration and usage lookup supported.. API access and subscription access may have different terms; consult the linked sources.
What should I check before choosing it?
Prepaid credit starts at $5, provider list token prices without markup/subscription. Own-key failures do not switch to paid vendor keys. Some provider-hosted web search/audio/tools are unsupported. Fallbacks follow configured profiles; default claimed same-model behavior has provider exceptions described in FAQ. Model catalog and example prices change and were not independently benchmarked. Default $50/minute spend cap is configurable, not total budget. No account/key, request, payment or routing test performed.
Price history
No retained pricing changes yet. A current price alone does not establish a historical trend.
How this profile is supported
Official product information
Current official product source read individually; product artwork inspected visually.
Read original source ↗Pricing review
Official pricing and billing restrictions read individually.
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.