AI Gateway

API Key Management for LLM Apps: How to Manage Client Access

API Key Management for LLM Apps: How to Manage Client Access

API key management for LLM applications means issuing every app, service, and environment its own revocable credential instead of sharing raw provider keys. This guide shows how to do it with Bifrost virtual keys, covering scoping, rate limits, rotation, revocation, and log attribution.

Claude Agent SDK Through a Gateway: Routing, Budgets, MCP

Claude Agent SDK Through a Gateway: Routing, Budgets, MCP

The Claude Agent SDK packages Claude Code's agent loop, tools, and context management as a Python and TypeScript library. This guide shows how to route Claude Agent SDK traffic through Bifrost for provider routing and failover, per-tenant budgets, and governed MCP tool access.

How to Enforce AI Budgets Per Team, Project and Key

How to Enforce AI Budgets Per Team, Project and Key

An AI budget is a hard spending ceiling enforced in the LLM request path, not a monthly report. This guide covers budget hierarchies, project mapping, reset windows, rate limits, exhausted-budget behavior, and a worked $10,000 example in Bifrost.

OpenAI Responses API vs Chat Completions vs Anthropic Messages

OpenAI Responses API vs Chat Completions vs Anthropic Messages

The OpenAI Responses API is OpenAI's stateful, item-based interface for agentic apps, while Chat Completions and Anthropic Messages remain stateless message APIs. This guide compares the three on state, tools, reasoning, and retention, and shows how Bifrost serves all three formats.

FinOps for AI: Showback and Chargeback for LLM Spend

FinOps for AI: Showback and Chargeback for LLM Spend

FinOps for AI is the practice of making LLM and agent spend visible, attributable, and accountable to the teams that create it. This guide explains showback vs chargeback for AI, the attribution model AI spend needs, and how to build both from request-level data at the AI gateway.

AI Access Control: How to Restrict Model Access by Role and Team

AI Access Control: How to Restrict Model Access by Role and Team

AI access control decides which models, providers, and tools each team, role, or user may call. This guide shows how to build per-team model allowlists in Bifrost, with a worked example, the exact config fields, and what a denied request returns.

Enterprise SSO for LLMs: SAML vs OIDC Setup Guide

Enterprise SSO for LLMs: SAML vs OIDC Setup Guide

Enterprise SSO for LLMs lets employees reach the AI gateway with their corporate identity, so roles, teams, and offboarding follow the directory. This guide compares SAML and OIDC, then walks through OIDC setup, claim mapping, SCIM provisioning, and audit logs in Bifrost.