Local benchmark
Free
FSL-1.1-ALv2; provider API spend separate
- Included scope
- Local proxy; events; versioned receipts; coverage reporting
Inferock Bench
● Identity checkedLocal LLM usage and billing diagnostics · Official-source review 2026-10-09
Inferock Bench is a local diagnostic proxy that records metered LLM calls and generates usage, timing and billing-integrity receipts. It separates observed spend, calculated bill-bounded loss, time loss and invoice-check exposure, with explicit coverage states.
- Category
- Local LLM usage and billing diagnostics
- Free access
- Local benchmark use is free under FSL-1.1-ALv2 restrictions; proxied requests and test batteries incur actual provider API charges.
- API access
- Local proxy supports metered OpenAI, Anthropic, Gemini Developer API and a pinned OpenRouter endpoint set; subscriptions via OAuth are not measured.
Is Inferock Bench right for you?
A good fit for
Relevant to developers inspecting per-call usage and delivery evidence alongside an actual provider invoice.
Before you choose
Requires Node.js 22+. Bench 0.2.4 uses FSL with two-year Apache-2.0 conversion; the measure library is Apache-2.0 and standard CC-BY-4.0. Earlier packages have documented license defects; current files do not change old tarballs. Keys and receipts are local according to project documentation, with keys forwarded to providers; inspect the threat model. It cannot measure bypassing traffic or prove a refund, intent or widespread overbilling. Hero dollars are synthetic illustrations. Public run cards do not include underlying sanitized archives; benchmark findings were not independently reproduced. Reliability Index backend is pre-launch and opt-in is local-only today.
Workflow and handoff
Use a low-limit development API key and a few public prompts, compare receipt fields with provider records and preserve the matching invoice before raising billing questions.
Pricing and practical limits
Requires Node.js 22+. Bench 0.2.4 uses FSL with two-year Apache-2.0 conversion; the measure library is Apache-2.0 and standard CC-BY-4.0. Earlier packages have documented license defects; current files do not change old tarballs. Keys and receipts are local according to project documentation, with keys forwarded to providers; inspect the threat model. It cannot measure bypassing traffic or prove a refund, intent or widespread overbilling. Hero dollars are synthetic illustrations. Public run cards do not include underlying sanitized archives; benchmark findings were not independently reproduced. Reliability Index backend is pre-launch and opt-in is local-only today.
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 | Inferock Bench is a local diagnostic proxy that records metered LLM calls and generates usage, timing and billing-integrity receipts. It separates observed spend, calculated bill-bounded loss, time loss and invoice-check exposure, with explicit coverage states. | Facts sourced | 2026-10-09 |
| Pricing and restrictions | Requires Node.js 22+. Bench 0.2.4 uses FSL with two-year Apache-2.0 conversion; the measure library is Apache-2.0 and standard CC-BY-4.0. Earlier packages have documented license defects; current files do not change old tarballs. Keys and receipts are local according to project documentation, with keys forwarded to providers; inspect the threat model. It cannot measure bypassing traffic or prove a refund, intent or widespread overbilling. Hero dollars are synthetic illustrations. Public run cards do not include underlying sanitized archives; benchmark findings were not independently reproduced. Reliability Index backend is pre-launch and opt-in is local-only today. | Facts sourced | 2026-10-09 |
Understand the total cost
Inferock Bench pricing & plans
Alternatives to Inferock Bench
View all ↗
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 tool
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 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 Inferock Bench used for?
Inferock Bench is a local diagnostic proxy that records metered LLM calls and generates usage, timing and billing-integrity receipts. It separates observed spend, calculated bill-bounded loss, time loss and invoice-check exposure, with explicit coverage states.
Does Inferock Bench have a free plan?
Local benchmark use is free under FSL-1.1-ALv2 restrictions; proxied requests and test batteries incur actual provider API charges.. This record lists ongoing free access; check the plan limits before starting.
How much does Inferock Bench 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 Inferock Bench through an API?
Local proxy supports metered OpenAI, Anthropic, Gemini Developer API and a pinned OpenRouter endpoint set; subscriptions via OAuth are not measured.. API access and subscription access may have different terms; consult the linked sources.
What should I check before choosing it?
Requires Node.js 22+. Bench 0.2.4 uses FSL with two-year Apache-2.0 conversion; the measure library is Apache-2.0 and standard CC-BY-4.0. Earlier packages have documented license defects; current files do not change old tarballs. Keys and receipts are local according to project documentation, with keys forwarded to providers; inspect the threat model. It cannot measure bypassing traffic or prove a refund, intent or widespread overbilling. Hero dollars are synthetic illustrations. Public run cards do not include underlying sanitized archives; benchmark findings were not independently reproduced. Reliability Index backend is pre-launch and opt-in is local-only today.
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 product page reviewed for disclosed costs; unverified prices and allowances are identified in the listing.
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.