Key facts
| API compatibility | OpenAI-compatible /v1/chat/completions; drop-in base URL change |
| Models | 30+ models behind one API; open-weight options for private deployment |
| Typical patterns | Onboarding summaries, support Q&A, transaction enrichment, fraud triage |
| Integration path | Connects to KYC, ledger, helpdesk and case-management systems via middleware |
| Pricing model | Flat monthly self-serve plans with unlimited fair-use usage; no per-token billing — see the live pricing page |
| Free tier | plugsky-micro and plugsky-lite on the free plan, no card required |
| Deployment | Plugsky cloud, your VPC, on-prem and air-gapped options |
| Compliance posture | SOC 2 Type II and ISO 27001 readiness in progress (not yet certified); validate evidence during diligence |
TL;DR
- Automate summaries and support; keep risk decisions human.
- Keep card data out of prompts and inside PCI scope.
- Use per-service keys and export audit logs from day one.
- Attach residency and DPA evidence to your compliance record.
- Start free with plugsky-micro and plugsky-lite, no card required.
How it works, step by step
- Pick one workflow, such as onboarding summaries or support answers.
- Define the human review point and the evidence you must retain.
- Classify data and exclude card data and identifiers you do not need.
- Build against the OpenAI-compatible endpoint with per-service keys.
- Configure region selection and audit export before production traffic.
- Measure quality and handling time, then expand workflow by workflow.
Original data
Try it yourself
Open the AI API pricing tracker →
Where an AI API fits in fintech
Fintechs ship fast, but regulated workflows still need evidence. Good first use cases sit between automation and review:
- Onboarding summaries: condense KYC packs and application forms into structured summaries for analysts to verify.
- Support automation: answer common questions from approved policy content and route the rest to humans.
- Transaction enrichment: classify and clean merchant descriptors for reporting and reconciliation.
- Fraud-ops triage notes: summarise case evidence into a narrative an investigator confirms.
- Internal knowledge search: answer staff questions from procedures and product documentation.
Security, privacy and data handling
Payments and financial data attract both regulators and attackers, so controls should be visible from day one:
- Keep card data inside PCI-scoped systems and out of prompts entirely.
- Keep risk and fraud decisions with human investigators; models draft, people decide.
- Use scoped keys per service and rotate them on a schedule.
- Export audit logs and align retention with your regulatory obligations.
Deployment options and model choice
Most fintechs start cloud-native in a pinned region and adopt VPC or on-prem when a partner or licence requires it. Deployment is a choice among four tiers on the same OpenAI-compatible API: shared cloud, a private endpoint in your VPC, on-prem and air-gapped, with region selection for residency. The catalogue holds 30+ models behind one key, with open-weight models for disconnected sites, and switching provider is a base URL change. Live today: chat, streaming, JSON mode, function calling, embeddings, RAG and agents. Still coming soon: audio, images, moderation, files, batch, fine-tuning, assistants and the responses API. Start on the free plan with plugsky-micro and plugsky-lite, no card, or use the 14-day full-access trial for paid tiers; the live pricing page has current plans.
From pilot to production
Growth-stage shortcuts become audit findings. Avoid:
- Scaling support automation without a fallback to a human agent.
- Using a shared key across support, risk and engineering.
- Sending full transaction histories when a scoped extract suffices.
- Treating enrichment output as correct without reconciliation checks.
- Deferring the DPA and residency decisions until after launch.
Start with internal and support workflows, define the human decision points, and attach evidence (residency configuration, audit export, DPA) to your compliance record. Measure accuracy per workflow before it touches a customer.
Honest comparison
| Capability | Plugsky | Typical per-token API | Building in-house |
|---|---|---|---|
| API compatibility | OpenAI-compatible chat, embeddings and tools | Usually compatible | Full rewrite |
| Deployment | Cloud, VPC, on-prem and air-gapped | Mostly cloud-only | You operate GPUs and serving |
| Data residency | Region selection and sovereign options | Limited regions | You control fully |
| Pricing | Flat monthly self-serve, fair-use usage | Per-token, harder to forecast | GPU plus operations cost |
| Model choice | 30+ models behind one API | Varies by provider | You host every model |
| Industry fit | Onboarding summaries, support Q&A, transaction enrichment, fraud triage | Generic API, you adapt it | You build every workflow |
Frequently asked questions
Can we keep our existing OpenAI SDK code?
Yes. Plugsky exposes an OpenAI-compatible API, so you change the base URL and model name and keep your integration and prompts.
Is there a free plan?
Yes. The free plan includes two free models, plugsky-micro and plugsky-lite, and does not require a credit card.
How does pricing work?
Self-serve plans are flat monthly with unlimited fair-use usage; enterprise agreements cover residency, capacity and SLA terms. See the live pricing page for current plans.
Is Plugsky PCI certified?
No such claim should be assumed. Keep card data in your PCI-scoped systems and validate vendor controls directly with the enterprise team during diligence.
Can we keep data in our region?
Yes. Region-locked planes let you choose where prompts, storage and logs are processed; enterprise options add VPC, on-prem and air-gapped deployment.
Which endpoints are live today?
Chat completions, streaming, JSON mode, function calling, embeddings, RAG and agents are live. Audio, images, moderation, files, batch, fine-tuning, assistants and the responses API are coming soon.
Would our data be used for training?
Plugsky processes customer data to provide the service; training exclusion belongs in your DPA. Confirm current terms with the enterprise team before sending customer data.