Glossary · AI
BYOK (bring your own key)
Also called: bring your own API key, own AI key, BYO model
BYOK, or bring your own key, means a software product runs its AI features on an API key from your own AI provider account, so usage is billed to you directly by the provider instead of being resold through the product.
There are two ways an automation tool can give you AI. It can resell it: AI calls cost "credits" or extra tasks, priced by the vendor with a margin and the model choice made for you. Or you bring a key: the tool calls the provider with your credentials and the provider bills you at its published token prices.
Why teams choose BYOK
- Price transparency. You pay the provider's list price for exactly the tokens you use, visible on the provider's own usage page.
- Model choice. Use the model that fits each step: a small one for classification, a frontier one for hard drafting.
- Data terms. Your agreement with the provider (retention, training opt-outs, regional processing) applies to your prompts.
- Spending limits. Set a hard monthly cap on the key at the provider.
The trade-offs
You manage another account and another bill, and a revoked or rate-limited key stops your AI steps. Treat keys like passwords: one per environment, stored encrypted, rotated when people leave, never pasted into prompts or logs.
How to compare tools
"Supports BYOK" varies: some vendors still charge a fee per AI call or a percentage on top when you bring a key. Read the pricing page for what's charged on own-key usage, not just whether it's allowed.
In Fluxo Flow
BYOK is the only way AI runs in Fluxo Flow: connect a key from any of 14 providers (OpenAI, Anthropic, Google Gemini, Mistral, Groq, xAI, DeepSeek, OpenRouter, Together AI, Fireworks AI, Azure OpenAI, AWS Bedrock, Google Vertex AI, any OpenAI-compatible endpoint). Your provider bills you at its price; we sell no AI credits and add no markup. Keys are encrypted at rest and never shown again in full. On the Partner plan, agencies can set one shared key or let each client bring its own.
Read next
Related terms
- OpenAI-compatible endpointAn OpenAI-compatible endpoint is an AI API that accepts requests and returns responses in the same format as OpenAI's API, so software written for OpenAI can call other providers, gateways or self-hosted models by changing the base URL and key.
- TokenA token is the unit of text a language model reads and writes, usually a word, part of a word or a punctuation mark, and the unit AI providers use to price usage and set context limits.
- LLMAn LLM, or large language model, is a neural network trained on large amounts of text that generates text by repeatedly predicting the next token, which lets it summarize, classify, extract and draft.
- Context windowA context window is the maximum number of tokens a language model can take into account in a single request, counting the instructions, the input data and the reply it writes.
- Audit logAn audit log is a chronological, tamper-resistant record of who did what in a system and when, kept so that changes, approvals and access can be traced afterwards.