Try Bifrost Enterprise free for 14 days.
Request access
[ BIFROST BLOG ]

Latest Updates & Tutorials

Insights, integration guides, and updates from the Bifrost team.

Run guardrails on LLM and MCP traffic in the order you choose

Run guardrails on LLM and MCP traffic in the order you choose

Picture an enterprise organization that uses an AI agent to draft replies to support tickets. The tickets come straight from customers, so they contain whatever information customers share. Some customers may include full account numbers. Other customers may ask whether they should move their savings into a particular fund, which perhaps the compliance team does not want an AI answering. With Guardrails in Bifrost, the platform team can enforce multiple guardrail profiles with varying rules on

Oct 22, 2026•Madhu Shantan
A Closer Look at Bifrost Adaptive Routing: How It Works, and What You Can Now See

A Closer Look at Bifrost Adaptive Routing: How It Works, and What You Can Now See

Adaptive routing has kept LLM traffic on healthy providers and keys for over a year. Here's how it works, and what it now shows you: what it observed, what it did, and when you need to step in. Every team that puts an LLM in front of users learns the same lesson quickly: your product is only as reliable as the provider serving the model, and providers have bad days. They go down, slow to a crawl, rate limit you in the middle of a launch, run your account out of credit, retire the model you depe

Oct 22, 2026•Pratham Mishra
Say hello to the Home page: Your AI usage at a glance, with built-in budget approvals

Say hello to the Home page: Your AI usage at a glance, with built-in budget approvals

Bifrost already offers built-in observability. Yet for a user, to figure out “how much have I spent this week?” or "what models can I use?" involves navigating different sections of the Bifrost dashboard. Some admins even built their own custom applications using Bifrost APIs just to give their users/employees this view. With Bifrost Enterprise v2.3.0, this view comes out-of-the-box. Users now land on a Home page that displays their own usage, keys and access the moment they sign in. Meet th

Oct 21, 2026•Suresh Chaudhary
Introducing Agent Gateway in Bifrost: One gateway for models, tools and agents

Introducing Agent Gateway in Bifrost: One gateway for models, tools and agents

An agent hands work to another agent. That agent calls a model, uses a few tools, and sends back a result. Now you need to understand what happened - Who started the request? Should they have been able to call that agent? What did it send back? Which model and tool calls went into the answer? Each service might have its own logs. Following the work across all of them is where things get tedious. Agent Gateway brings A2A agent calls into Bifrost, alongside your model and MCP tool calls. You get

Oct 20, 2026•Dhwanil Pithva
Governance that follows your org structure: Access Profiles for teams, business units and customers

Governance that follows your org structure: Access Profiles for teams, business units and customers

AI budgets are now planned the same way the company plans traditional budgets: per team, per department, per customer account. Individual user limits alone aren't enough when you need to control spending and model access across the organization. With Bifrost Enterprise v2.3.0, Access Profiles can now be attached to entities - teams, business units, and customers - not just individual users. This lets you define policies at the entity level, enforce shared budgets, and keep access controls alig

Oct 19, 2026•Anuj Parihar
Cloudflare Workers AI Is Now a Built-In Provider in Bifrost

Cloudflare Workers AI Is Now a Built-In Provider in Bifrost

Cloudflare Workers AI is now available as a first class provider directly in Bifrost. Add your Cloudflare credentials, choose a Workers AI model, and send requests through the same payload you use for your other providers. Setup starts with selecting Cloudflare in the dashboard. Configure an account ID on each key, then use Workers AI for chat, embeddings, or native Clef decisions. The integration connects Bifrost to Workers AI, Cloudflare’s model inference service. What you can use today T

Oct 16, 2026•Madhu Shantan
Bifrost's /v1/decisions: one API for decision models across eight providers

Bifrost's /v1/decisions: one API for decision models across eight providers

Bifrost added /v1/decisions with TypeSafe's Jev in September. With v2.3.1, the same endpoint now serves decision models from eight providers, plus any self-hosted decision model you add as a custom provider. Decision models score defined outcomes and return probabilities directly, rather than generating free form text like language models. Following TypeSafe's release of Jev, enterprises are adopting them for content classification, request routing, and anomaly detection. Native decision model

Oct 16, 2026•Madhu Shantan
Meet Warp: An agent for your gateway's telemetry

Meet Warp: An agent for your gateway's telemetry

Warp is a new agent built into the Bifrost dashboard. You ask it a question about your gateway traffic in plain English. It answers by running queries against your log store, not by guessing. Getting answers out of your LLM logs Every request through Bifrost is logged with its provider, model, tokens, cost, latency, status, virtual key and full message content. That data already holds the answers to most questions about your LLM usage. But each question takes its own path through the dashboa

Oct 15, 2026•Vrinda Kohli
Benchmarking Bifrost's upgraded Complexity Router

Benchmarking Bifrost's upgraded Complexity Router

Bifrost’s Complexity Router sends each request to the model it needs, so your frontier model only handles the work that actually needs it. Since v2.0, you choose how incoming requests get classified into complexity tiers: a semantic classifier that matches requests against phrases you define, or a decision model such as Typesafe’s Jev (added in v2.3.0) that judges each request against tier definitions you can edit. We benchmarked both approaches against sending every request to Claude Opus 5.5.

Oct 14, 2026•Reehan
Security update: authentication bypass via encoded path traversal is fixed in Bifrost v2.2.5

Security update: authentication bypass via encoded path traversal is fixed in Bifrost v2.2.5

We fixed an authentication bypass in the Bifrost HTTP gateway. A request that used percent-encoded dot segments, such as ..%2F, could make a protected route look like a public one. The request then skipped authentication. The fix ships in transports/v2.2.5. This affects instances where the gateway can be reached by clients you do not trust. Instances on private networks have much lower exposure, because an attacker first needs access to that network. Because a compromised internal host could st

Oct 02, 2026•Akshay Deo
Jev: A Decision Model That Classifies Without Generating Text

Jev: A Decision Model That Classifies Without Generating Text

Jev is a decision model from TypeSafe that takes context and typed questions and returns probabilities over allowed answers instead of writing text. This post covers its Choice, Score, and Noul questions, speed and cost, confidence scores, known limits, and how it works with Bifrost.

Sep 29, 2026•Madhu Shantan
Security update: CVE-2026-90898 and CVE-2026-86242 are fixed in Bifrost v2.1.0

Security update: CVE-2026-90898 and CVE-2026-86242 are fixed in Bifrost v2.1.0

JFrog Security Research recently disclosed two vulnerabilities in Bifrost's management API. They can only be exploited when both of these are true: the instance is exposed to the internet, and dashboard authentication has not been set up. Both are fixed in transports/v2.1.0

Sep 26, 2026•Akshay Deo
Security
Typesafe system one models and new /v1/decisions endpoint

Typesafe system one models and new /v1/decisions endpoint

Bifrost now supports TypeSafe's jev judgment models behind a unified POST /v1/decisions endpoint and a 1:1 /typesafe drop-in for TypeSafe's official SDKs. This is available in v2.2.2 for both OSS and Enterprise. TypeSafe's jev family takes a piece of state - a support ticket, a model's answer, a review, any string or JSON blob - and returns calibrated judgments: a probability, a pick from your options, or a rubric score, each with confidence and a full probability distribution. That makes them

Sep 23, 2026•Akshay Deo
Engineering
MCP Guardrails in Bifrost

MCP Guardrails in Bifrost

Introduction MCP gives AI applications something more powerful than a prompt and a response. It gives them access to tools. An agent can search internal systems, create tickets, query databases, send messages, and work with third-party services. That is useful, but it also changes the security problem. The risk is not only that a model generates unsafe text. The risk is that unsafe or sensitive input becomes a real action in another system. This is where MCP guardrails matter. In Bifrost, MCP

Sep 16, 2026•Madhu Shantan
MCP Gateway
Bifrost v2.0 is here

Bifrost v2.0 is here

Today we are releasing Bifrost v2.0, the largest release we have shipped. A year ago we open sourced Bifrost with one belief: a gateway only earns the right to sit in front of every AI request if it is performant and resilient at scale. Bifrost now runs in production at Fortune 500 companies across financial services, healthcare, technology, pharma and defense, moving trillions of tokens a day. We also realized that most of an organization's AI traffic never reaches the gateway at all, because

Sep 15, 2026•Reehan
Release Notes
AI Governance and Observability in Bifrost

AI Governance and Observability in Bifrost

Most teams that run AI in production eventually get the same question from finance. Spending went up last month, and someone wants to know which team, feature, or model caused it. Often there is no clear answer. The numbers exist, but they sit in two systems that were never built to share data. This is a design problem, not a sign that anyone was careless. Often a team builds its metrics pipeline and its budgeting system at different times, owned by different people. One tracks requests and tok

Jul 09, 2026•Vrinda Kohli
AI Gateway
LLM Cost Optimization in Bifrost: Part 1

LLM Cost Optimization in Bifrost: Part 1

Introduction AI costs at enterprises can become expensive quickly. Recent examples show this clearly - Uber reportedly exhausted its annual AI budget only four months into 2026, while Pylon’s CEO said the company’s Anthropic bill was set to jump from $400K to $1.4M a year after crossing 150 seats. These are different companies at different scales, but the pattern is similar: once AI usage becomes normal across teams, cost control becomes an operational problem, not just a pricing problem. Most

Jul 03, 2026•Madhu Shantan
AI Gateway
Shadow AI Is the Insider Threat You Already Hired

Shadow AI: The Insider Threat You Never Noticed

The most damaging data leak in your organization this year probably won't come from an attacker. It'll come from an employee trying to hit a deadline. Right now, across nearly every company, people are pasting source code, customer records, contracts, and clinical notes into AI tools that security never approved, can't see, and can't audit, and most of it leaves no trace in the logs you actually watch. We called the last version of this problem shadow IT. This one is worse, and the gap between h

Jun 16, 2026•Vrinda Kohli
AI Gateway
Screening Text and Image LLM Traffic with AWS Bedrock Guardrails and Bifrost

Screening Text and Image LLM Traffic with AWS Bedrock Guardrails and Bifrost

LLM features started out as text in, text out. They have not been that for a while. A support tool ingests a screenshot of a customer's account dashboard with billing details visible on screen. A document agent reads a vendor PDF where the malicious instructions live inside an embedded image, not in the text the model sees. A receipt-processing assistant accepts a photo of an invoice that includes a full credit card number. A vision-enabled medical tool gets handed a chart image with a patient's

Jun 06, 2026•Marketing Access
Redacting Sensitive Data in LLM Traffic with Google Model Armor and Bifrost

Redacting Sensitive Data in LLM Traffic with Google Model Armor and Bifrost

Most AI security tooling is built around a binary: a prompt is either allowed through or rejected. That works for an obvious attack, but it is a blunt instrument for the situation enterprises actually hit most often, which is legitimate work that happens to carry sensitive data. A support agent pastes a customer's full record into a summarization tool because summarizing it is the job. A developer drops a stack trace with a live token into a debugging assistant. An analyst feeds a spreadsheet of

Jun 06, 2026•Kamya Shah
Guardrails
MCP Audit Logging: Requirements for Enterprise Governance and Compliance

MCP Audit Logging: Requirements for Enterprise Governance and Compliance

MCP adoption inside enterprise AI stacks moved from a single experimental server to fleets of tools wired into production agents in a remarkably short window. As that surface area expanded, three questions stopped being theoretical for platform teams: which tools is an agent allowed to call, who triggered any given call, and what arguments and results moved through it. Bifrost addresses those questions at the gateway layer with a first-class MCP audit log that captures every tool execution, the

Jun 02, 2026•Kamya Shah
MCP Gateway
Evaluating LLM Output for Quality, Safety, and Brand Voice with Patronus AI and Bifrost

Evaluating LLM Output for Quality, Safety, and Brand Voice with Patronus AI and Bifrost

LLM features in production fail in ways that classic guardrails are not looking for. A coding assistant returns JSON that looks valid and silently breaks the downstream pipeline that parses it. A customer support reply apologizes three times in five sentences and reads as defensive. A marketing draft names a competitor in a comparison the brand team never approved. An HR assistant writes advice in subtly gendered language. An internal tool answers a perfectly reasonable question with "As an AI a

Jun 02, 2026•Kamya Shah
Guardrails
Bringing Enterprise AI Security to LLMs with CrowdStrike AIDR Guardrails and Bifrost

Secure your AI workflows with CrowdStrike AIDR Guardrails and Bifrost

See how Bifrost and CrowdStrike AIDR secure enterprise LLM traffic: AIDR handles detection, Bifrost enforces policy inline before any prompt reaches a model. Enterprise AI deployments run into the same set of security issues within a few months of going live. A support rep pastes a full customer record into a summarization tool, and the prompt leaves your network for a third-party API with its own retention policy. A retrieval agent ingests a vendor PDF with instructions hidden in white-on-whit

Jun 01, 2026•Kamya Shah
Guardrails
MCP: The Protocol, the Plumbing, and the Gateway

MCP: The Protocol, the Plumbing, and the Gateway

If you've spent any time around AI tooling in the last year, you've probably heard the phrase "Model Context Protocol" thrown around, usually followed by the analogy "it's USB-C for AI." It's a useful starting point, but it's also where most explanations stop. This post starts there too, and then keeps going, all the way down to what's actually moving on the wire when your agent calls a tool. The problem MCP exists to solve LLMs, on their own, are isolated. They know what they were trained on

Jun 01, 2026•Vrinda Kohli
Guardrails at the Gateway: What Bifrost Ships and What It Integrates

Guardrails at the Gateway: What Bifrost Ships and What It Integrates

Introduction Every team running LLMs in production runs into the same surface area sooner or later. Prompt injection. PII leaking into a model provider's training pipeline. Credentials pasted into a chat by accident. Toxic or off-policy responses going back to a user. Hallucinated content quoted as fact. Most teams solve these problems the first time they hit them, usually inside the application itself, with a one-off regex, a hand-rolled OpenAI moderation call, or a wrapper around a vendor SDK

May 24, 2026•Madhu Shantan
Guardrails
Why MCP Tool Discovery Belongs in a Filesystem, Not the Context Window

Why MCP Tool Discovery Belongs in a Filesystem, Not the Context Window

Every MCP tool definition the model doesn't end up using is wasted context. That's the quiet bug in the way most teams run the Model Context Protocol today. Connect five MCP servers with thirty tools each, and the model receives 150 tool definitions before it ever sees the user's prompt, most of which it will never call. The token bill grows linearly with every server you add. Selection accuracy degrades. Latency creeps up. The framing this post wants to argue for is simple: tool discovery is n

May 22, 2026•Vrinda Kohli
MCP Gateway
Enterprise MCP Governance: Access, Audit, and Cost Controls for AI Agents

Enterprise MCP Governance: Access, Audit, and Cost Controls for AI Agents

Enterprise MCP governance comes down to three controls every production AI agent deployment needs: access, audit, and cost. Here is what each one looks like in practice. When a new engineer joins a team, they are not handed unrestricted access to every system the company runs. Their access is scoped to what they need, their actions are recorded, and the budget impact of what they do is tracked. The moment an AI agent is connected to a fleet of MCP servers without an equivalent layer in place, t

May 22, 2026•Kamya Shah
MCP Gateway
Code Mode and the Architecture of Token-Efficient MCP AgentsCode Mode

Code Mode and the Architecture of Token-Efficient MCP Agents

The Context Window Problem If you've built an agent that connects to more than a handful of MCP servers, you've already run into this. Every tool definition from every connected server gets loaded into the model's context window on every request. Five servers with 30 tools each means 150 tool definitions sitting in context before the model reads a single word of your prompt. This is more than a theoretical concern. Anthropic's engineering team documented a five-server setup where tool definiti

May 16, 2026•Vrinda Kohli
MCP Gateway
Beyond latency-based routing: Adaptive load balancing in Bifrost

Beyond latency-based routing: Adaptive load balancing in Bifrost

Most teams running multi-provider LLM stacks have moved past pure round-robin for traffic distribution across providers and API keys. They've adopted latency-based routing: measure response times, penalise slow backends, shift traffic toward the fast ones. The approach is reasonable, but it has a failure mode that's easy to miss until you're debugging a production incident. A 6-second response from your LLM provider can be either fast or slow, and a flat latency threshold has no way to tell whi

May 06, 2026•Madhu Shantan
AI Gateway
Your Semantic Cache Has a Grey Zone Problem

Your Semantic Cache Has a Grey Zone Problem

If you're running LLMs in production, you've probably built (or thought about building) a semantic cache. The pitch is simple: embed incoming prompts, find near-duplicates, serve the cached response, skip inference. It works. Except when it doesn't. A new paper from Apple introduces Krites, a caching policy that quietly fixes one of the most annoying problems in semantic caching, ie. the similarity grey zone, without adding a single millisecond to your serving latency. Let's break it down. Th

May 05, 2026•Vrinda Kohli
AI Gateway
Bifrost MCP Gateway: Access Control, Cost Governance, and 92% Lower Token Costs at Scale

Bifrost MCP Gateway: Access Control, Cost Governance, and 92% Lower Token Costs at Scale

Scaling cost per query — Tools vs Tokens Average input tokens consumed per query as tool count increases Code Mode OFF Code Mode ON Estimated cost - Code Mode OFF vs ON Absolute dollar cost per round, same queries Code Mode OFF Code Mode ON

Apr 08, 2026•Pratham Mishra
MCP Gateway
Integrating Gemini CLI with Bifrost Gateway

Integrating Gemini CLI with Bifrost Gateway

Gemini CLI is Google's command-line coding assistant that brings the power of Gemini models - including Gemini 2.0 Flash with its massive context window and multimodal capabilities - directly to your terminal. By routing Gemini CLI through Bifrost Gateway, you gain multi-model flexibility, comprehensive observability, MCP tool integration, and failover capabilities while preserving the familiar CLI experience. Architecture Overview Gemini CLI communicates with Google's Generative AI API for m

Dec 09, 2025•Akshay Deo
Integrations
Integrating Zed Editor with Bifrost Gateway

Integrating Zed Editor with Bifrost Gateway

Zed is a high-performance, collaborative code editor built for the modern development workflow. With native AI assistant integration, Zed can leverage language models directly within the editor for code generation, refactoring, and explanation. Integrating Zed with Bifrost Gateway unlocks multi-provider model access, MCP tools, and observability - transforming Zed's AI assistant into a flexible, enterprise-ready coding companion. Architecture Overview Zed's language model integration supports

Dec 02, 2025•Akshay Deo
Integrations
Integrating Qwen Code with Bifrost Gateway

Integrating Qwen Code with Bifrost Gateway

Qwen Code is Alibaba's advanced coding assistant, built on the Qwen large language model family with specialized reasoning capabilities for code generation, analysis, and refactoring. By routing Qwen Code through Bifrost Gateway, you unlock cross-provider flexibility, observability, and tool integration - allowing Qwen Code to work alongside or be substituted by other model providers while maintaining a consistent terminal experience. Architecture Overview Qwen Code communicates with APIs usi

Nov 24, 2025•Akshay Deo
Integrations
Integrating Codex CLI with Bifrost Gateway

Integrating Codex CLI with Bifrost Gateway

Codex CLI is OpenAI's command-line tool for code generation and completion, bringing AI-assisted coding directly to the terminal. By routing Codex CLI through Bifrost Gateway, you gain access to multiple model providers, enhanced observability, and MCP tool integration - transforming a single-provider CLI into a flexible, multi-model development assistant. Architecture Overview Codex CLI communicates with OpenAI's API using their standard HTTP endpoints. Bifrost intercepts these requests by a

Nov 17, 2025•Akshay Deo
Features
Integrating LibreChat with Bifrost Gateway

Integrating LibreChat with Bifrost Gateway

LibreChat is an open-source chat interface that provides a ChatGPT-like experience with support for multiple AI providers. Integrating it with Bifrost Gateway adds a layer of abstraction that enables unified model access, MCP tools, observability, and load balancing across different providers - all without modifying LibreChat's codebase. Architecture Overview LibreChat's custom endpoint feature allows integration with any OpenAI-compatible API. Bifrost leverages this by exposing an OpenAI-com

Nov 14, 2025•Akshay Deo
Integrations
Integrating Claude Code with Bifrost Gateway

Integrating Claude Code with Bifrost Gateway

Claude Code brings Anthropic's Claude Sonnet 4.5 directly to the terminal with agentic coding capabilities. While powerful on its own, integrating it with Bifrost Gateway unlocks additional capabilities like multi-model access, MCP tools, and observability without modifying the Claude Code client. Bifrost acts as an API gateway that provides compatible endpoints for Anthropic, OpenAI, and Gemini APIs. By routing Claude Code through Bifrost, you intercept API calls at the transport layer, enabli

Nov 12, 2025•Akshay Deo
Integrations
Access GPT, Gemini, Claude, Mistral etc. through 1 Gateway: Configure Providers in Bifrost

Access GPT, Gemini, Claude, Mistral etc. through 1 Gateway: Configure Providers in Bifrost

When building AI-powered applications, chances are you don’t want to rely on a single provider: * Claude for reasoning-heavy tasks * GPT-4o for multimodal inputs * Gemini for Google ecosystem integrations * Mistral for fast, cost-effective completions Each provider has different SDKs, auth methods, rate limits, and response formats. Maintaining them quickly becomes messy. Bifrost solves this by acting as a unified AI gateway: one API surface, multiple providers behind it. In this post, we

Oct 16, 2025•Akshay Deo
Features
Your Primary LLM Provider Failed? Enable Automatic Fallback with Bifrost

Your Primary LLM Provider Failed? Enable Automatic Fallback with Bifrost

When building applications that depend on external LLM APIs, provider failures are inevitable. Network timeouts, rate limits, model unavailability, and service outages all cause request failures that break application functionality. This post explains how to implement automatic fallback mechanisms using Bifrost to maintain service availability when primary providers fail. Failure Scenarios in LLM Applications LLM API calls can fail for several reasons: * Rate limiting: HTTP 429 responses wh

Oct 16, 2025•Akshay Deo
Features
From Text to Vision: Multimodal Support in Bifrost

From Text to Vision: Multimodal Support in Bifrost

Modern AI applications are rapidly moving beyond text-only interactions. Today's systems need to process images, generate speech, and transcribe audio, often within the same workflow. While individual providers offer these capabilities, building a robust multimodal system that spans multiple AI providers introduces significant complexity around API differences, error handling, and failover strategies. Bifrost, an open-source AI gateway, addresses these challenges by providing unified multimodal

Oct 16, 2025•Akshay Deo
Features