How should logistics companies use an AI API?

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	Exception summaries, status comms, customs docs, claims triage
Integration path	Connects to TMS, WMS and customer portals through 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
Live endpoints	Chat, streaming, JSON mode, function calling, embeddings, RAG and agents

TL;DR

• Turn exception data into verified, actionable summaries.
• Scope access per partner and keep customer data minimal.
• Use region selection for cross-border data obligations.
• Keep broker or coordinator review on customs and claims outputs.
• Start free with plugsky-micro and plugsky-lite, no card required.

How it works, step by step

1. Pick one lane and one workflow, such as exception summaries.
2. Ground facts in TMS event data rather than free-text memory.
3. Define partner-scoped access and key boundaries.
4. Build against the OpenAI-compatible endpoint with audit logging.
5. Configure residency for cross-border data obligations.
6. Measure handling time per exception, then expand to more lanes.

Try it yourself

Open the API latency tester →

Where an AI API fits in logistics

Logistics is an exception-handling business. The API helps most when it converts messy updates into clear, actionable text:

• Shipment exception summaries: condense tracking events and carrier notes into a status a coordinator can act on.
• Carrier and customer communications: draft delay notices and updates from verified milestones.
• Customs documentation assistance: check commercial invoices and declarations for missing fields for a broker to verify.
• Claims triage: summarise claim evidence and correspondence into a reviewable case file.
• Driver and partner support: answer process questions from current operating procedures.

Security, privacy and data handling

Logistics data crosses company boundaries constantly, so governance has to survive that reality:

• Scope access per partner so one relationship cannot see another's data.
• Keep customer personal data to the minimum needed in prompts.
• Use region selection for data that must remain in-country.
• Log prompts and outputs so disputes and audits can be reconstructed.

Deployment options and model choice

Cross-border flows make region selection the default, with private deployment for partners that demand 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

Multi-party operations expose weak controls quickly. Avoid:

• One key shared across carriers, customers and internal teams.
• Quoting customs or duty outcomes without broker verification.
• Sending full customer records when a shipment reference suffices.
• No retention decision for location and tracking data in logs.
• Automating delay notices without verifying the milestone data.

Pilot one lane and one workflow, integrate facts from the TMS rather than model memory, and structure partner access from the start. Measure handling time per exception before expanding lanes.

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	Exception summaries, status comms, customs docs, claims 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.

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.

Can it classify customs codes?

It can draft suggestions from documentation for a customs broker to verify; classification decisions remain with qualified staff.

How does pricing work?

Self-serve plans are flat monthly with unlimited fair-use usage; enterprise agreements cover residency and SLA terms. See the live pricing page for current plans.

Can partners access the API directly?

Prefer mediated access through your platform so partner scoping, logging and rate limits stay under your control.

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.

How do we keep data in-country?

Select a region-locked plane for the workloads that require it, and confirm the configuration with the enterprise team before go-live.