Terminology
This page summarizes key terms used across the docs for consistent understanding.
Core Concepts
- BYOK (Bring Your Own Key): A model where users manage their own upstream AI provider API Keys. The system acts only as a secure proxy and does not provide paid key pools.
- Provider Key / Upstream Key (δΈζΈΈε―ι₯): The original API Key obtained by users from official platforms like OpenAI, Anthropic, DeepSeek, etc., which is added to the XAI system and stored encrypted.
- XAI API Key / Virtual Key (θζε―ι₯): The exclusive key assigned by the XAI system to users (format:
sk-Xvs...), used to call the XAI unified API endpoint. - Zero Markup Pricing: API call charges are deducted directly from the user's official account, with XAI charging no markup or service fees.
- End-to-End Encryption: Provider Keys are encrypted using user-specific keys via the ChaCha20-Poly1305 algorithm, with no super-admin access in the system.
Account System
- Owner (主账ζ·): Top-level account that manages descendants and keys.
- Descendants (ε代η¨ζ·): Any users in the owner's subtree; see "User Hierarchy".
- DNA: Lineage path (e.g.,
.1.42.) used to filter user groups. - Gear (ζ‘£δ½): User attribute that impacts routing/drift strategies.
- Tier (ε±ηΊ§): User attribute for pricing/permissions.
Routing & Key Management
- Level (ηηΊ§): Abstraction for key pools and model routing. Users can assign different Provider Keys to different Levels.
- Key Pool (ε―ι₯ζ± ): A collection of multiple Provider Keys under the same Level, automatically rotated by the system to distribute request pressure.
- Model Mapper (樑εζ ε°): Aliasing models to targets (e.g.,
gpt-4=gpt-4-turbo), configurable at user-level or owner-level. - Level Mapper (Level ζ ε°): Map model patterns to a Level (e.g.,
claude*=2), routing to the corresponding key pool. - Sleep (δΌη ): After errors (e.g., 429, 5xx), the key is temporarily removed from rotation and rejoins after a waiting period.
- Switch Over (ζ ιεζ’): Move from one Level to another when the current Level is unavailable.
Security & Permissions
- Resources (θ΅ζΊη½εε): Allowed API paths (e.g.,
/v1/chat/completions). - AllowModels (樑εη½εε): List of models a sub-account is allowed to call.
- AllowIPs (IP η½εε): IP addresses or CIDR ranges allowed to call the API.
- Encryption Key (ε ε―ε―ι₯): Each user's unique 32-character key used to encrypt that user's Provider Keys.
Billing & Rate Limiting
- Factor (ε ε): Coefficient used in pricing.
- Rates (θ΄Ήηεη): Multiplier applied to model pricing.
- Model Limits (樑ειι): Per-model limits (RPM/RPH/RPD, TPM/TPH/TPD).
- RPM/RPH/RPD: Requests per minute/hour/day.
- TPM/TPH/TPD: Tokens per minute/hour/day.
- Credit Balance (δΏ‘η¨ι’εΊ¦): User's prepaid card balance, used for internal billing statistics (independent of upstream official billing).
See also:
- βAccess Controlβ
- βUser Hierarchyβ
- βBilling & Creditsβ