Key facts
| API compatibility | OpenAI-compatible /v1/chat/completions (drop-in base URL change) |
| Models | 30+ models in one catalogue, from free tiers to frontier reasoning |
| Pricing | Flat monthly self-serve plans with unlimited fair-use usage; no per-token billing on self-serve |
| Free tier | plugsky-micro and plugsky-lite, no card required |
| Trial | 14-day full-access trial for stronger models |
| Deployment | Plugsky cloud, your VPC, on-prem and air-gapped |
| Migration effort | One line: change the base URL and model name |
TL;DR
- Keep your OpenAI SDK code; change the base URL and model name.
- Flat monthly pricing removes per-token surprises on self-serve plans.
- 30+ models behind one API, from free chat tiers to frontier reasoning.
- Residency options include region selection, VPC, on-prem and air-gapped.
- Start free, evaluate on your prompts, then cut over with a one-line rollback.
How it works, step by step
- Create a Plugsky account and generate an API key on the free plan.
- Change your base URL from api.openai.com to the Plugsky endpoint.
- Map your model names to Plugsky models and pin a default.
- Replay recorded requests and compare outputs, latency and error rates.
- Canary production traffic and monitor usage in the dashboard.
- Keep the reverse change documented so rollback takes seconds.
Original data
Try it yourself
Open the OpenAI API cost calculator →
Why teams replace the OpenAI API
Three drivers dominate. Cost predictability: usage-based billing makes forecasting hard for spiky products. Model breadth: teams want cheap classification models and frontier reasoning behind one endpoint. Data control: regulated buyers need to know where prompts are processed and want deployment options beyond a single managed cloud.
Adjacent capabilities matter too. OpenAI has audio, image and fine-tuning endpoints that Plugsky does not ship yet; those are coming soon. Migration decisions should therefore be scoped by endpoint, not by vendor loyalty.
What compatibility you actually need
Check the primitives your product uses: chat completions, streaming, JSON mode, function calling and embeddings. Plugsky supports those today through an OpenAI-compatible schema, so most SDK code, agents and RAG frameworks work unchanged.
- Inventory endpoints per service before migrating.
- Test streaming and tool calls, not just single completions.
- Version your prompts and evaluations so comparisons are fair.
- Keep a mapping table from current model names to Plugsky models.
- Confirm rate limits and fair-use terms match your traffic profile.
Cutover plan and rollback
Migrate in stages: staging first with recorded traffic, then a canary slice in production, then full cutover. Because the API is OpenAI-compatible, rollback is the same one-line change in reverse, which keeps risk low even for customer-facing services.
Residency and deployment deserve a separate check: Plugsky offers region selection plus VPC, on-prem and air-gapped options under enterprise agreements. Rehearse the rollback before you need it, so on-call engineers are not learning under pressure. Start on the free plan, use the 14-day full-access trial for hard prompts, and see the live pricing page for current plans.
Honest comparison
| Capability | Plugsky | OpenAI API | Self-hosting open models |
|---|---|---|---|
| API compatibility | Drop-in base URL change | Reference schema | Full rewrite |
| Pricing shape | Flat monthly self-serve | Usage-based | GPU plus ops cost |
| Model choice | 30+ models, one API | OpenAI catalogue | You host each model |
| Deployment | Cloud, VPC, on-prem, air-gapped | Managed cloud | You own the stack |
| Migration effort | One line plus model mapping | None | Months |
Frequently asked questions
Can I keep using the OpenAI SDK?
Yes. Plugsky exposes an OpenAI-compatible chat completions endpoint, so you change the base URL and model name and keep your existing SDK code.
Is there a free plan?
Yes. plugsky-micro and plugsky-lite are free with no credit card, and a 14-day full-access trial opens the full model catalogue.
How is pricing structured?
Self-serve plans are flat monthly with unlimited fair-use usage and no per-token billing. See the live pricing page for current plans.
Does Plugsky support streaming and function calling?
Yes, both are live, along with JSON mode and embeddings. Check the docs for per-model details.
What is not available yet?
Audio, images, moderation, files, batch, fine-tuning, assistants and responses are coming soon. Chat, tools, embeddings, RAG and agents are live.
Can I deploy in my own cloud?
Yes. VPC, on-prem and air-gapped deployments are available for enterprise customers.
What if I want to move back?
Your code stays OpenAI-compatible, so switching back is the same one-line change in reverse.