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

Latest Updates & Tutorials

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

MiniMax and BytePlus ModelArk are now built-in providers in Bifrost

MiniMax and BytePlus ModelArk are now built-in providers in Bifrost

Bifrost already routes OpenAI, Anthropic, Gemini and 20+ other providers through one OpenAI-compatible API. With Bifrost v2.4.0, MiniMax and BytePlus ModelArk join built-in providers list in open source and Enterprise, so your teams can call MiniMax-M3, Seedream, Seedance and MiniMax speech models on the same endpoints, under the same virtual keys, budgets and logs. Platform teams use Bifrost to give application teams one API for model providers, with access, budgets and logs set once in the Ga

Nov 18, 2026•Suresh Chaudhary
GPT-6.2 Astra and GPT-6.2 Sol are now available on Bifrost

GPT-6.2 Astra and GPT-6.2 Sol are now available on Bifrost

OpenAI shipped GPT-6.2 Astra and GPT-6.2 Sol today, and Bifrost supports both from day 0. Astra is OpenAI's frontier model for the hardest work, now 20% cheaper than GPT-6 Astra. Sol is the efficient everyday model, same rate card as GPT-6.1 Sol, but it finishes the same work on fewer tokens. If you already route OpenAI traffic through Bifrost, switching is one line: change the model string to openai/gpt-6.2-astra or openai/gpt-6.2-sol. Your routing rules, fallbacks, virtual keys, budgets, guar

Nov 17, 2026•Akshay Deo
AI Gateway
Chain guardrail profiles and use decision models as judges: Keep redacted data out of later guardrail checks

Chain guardrail profiles and use decision models as judges: Keep redacted data out of later guardrail checks

Bifrost Enterprise already lets you choose the order guardrail profiles run in. Now, a redaction by one profile carries through to every profile check after it, and a judge at the end of a rule can be a decision model instead of a standard LLM. Security and IT teams use guardrails in Bifrost to check the prompts, responses and tool calls that pass through the Gateway. One rule may often link several profiles: a local regex that catches account numbers, an external content-safety check, and a ju

Nov 17, 2026•Madhu Shantan
Audit logs, now with receipts: See exactly what changed, without comparing config backups

Audit logs, now with receipts: See exactly what changed, without comparing config backups

With Bifrost Enterprise v2.4.0, each audit entry tells you what happened, shows the fields that changed with their old and new values, and records how a person signed in. Signatures cover more of each entry, signing keys can be rotated, and the audit trail moves to your log store. Bifrost's audit logs help IT & security teams keep track of administrative changes on the Gateway. Every time someone updates a virtual key, a provider, a role or an access profile, Bifrost records who made the change

Nov 16, 2026•Suresh Chaudhary
Multimodal embeddings in Bifrost: Embed images, audio, video and PDFs through a single API

Multimodal embeddings in Bifrost: Embed images, audio, video and PDFs through a single API

Bifrost's /v1/embeddings API can now embed images, audio, video and PDFs, and Bifrost translates each request into the format of the model serving it. Engineering teams use Bifrost as a single Gateway for their model traffic. Their text embedding calls already go through one /v1/embeddings API, with the same keys and governance irrespective of the provider being called. But what happens when the content you need to search isn't text, such as product photos or recorded support calls? Gemini Em

Nov 13, 2026•Samyabrata Maji
Sign-in with ChatGPT for Codex, routed through Bifrost: Keep your ChatGPT seats with Gateway governance

Sign-in with ChatGPT for Codex, routed through Bifrost: Keep your ChatGPT seats with Gateway governance

Bifrost can already help route Codex traffic through the Gateway with a virtual key and a provider key. With v2.4.0, developers can now stay signed in to Codex with their ChatGPT accounts, on the seats your company already pays for, but their model requests will go through Bifrost for centralised governance and observability. Platform and security admins use Bifrost to ensure model traffic goes through a single control plane, where they can decide which models each user or team can use and how

Nov 12, 2026•Suresh Chaudhary
Introducing View as User: See what any user sees, without a test account

Introducing View as User: See what any user sees, without a test account

With Bifrost Enterprise v2.4.0, admins can now view the dashboard as any user in a read-only mode, and check how access settings apply for their users. Setting up Bifrost for an enterprise means deciding, in several places, what each employee or user can access. A role decides the pages they can view and the actions they can take, and can carry access profiles with it. A data access scope limits which logs, keys and users they see. Access profiles grant models, MCP tools and budgets, and issue

Nov 11, 2026•Suresh Chaudhary
Features
Introducing Relays: Put any HTTP API behind the Gateway

Introducing Relays: Put any HTTP API behind the Gateway

An AI agent rarely runs on model calls alone. For example, consider an invoice agent your finance team runs behind Bifrost. Your sellers use a helper agent to access this invoice agent and it receives each invoice through the Agent Gateway, reads the PDF with a document API, asks an LLM for the vendor and the total, and looks the vendor up in the ERP through an MCP tool. Today, Bifrost governs and logs three of those four calls - but the document API sits outside it, with its own key, its own p

Nov 10, 2026•Anuj Parihar
Engineering
Claude Fable 5.2 is now available on Bifrost

Claude Fable 5.2 is now available on Bifrost

Anthropic just released Claude Fable 5.2, and Bifrost supports it from day one. It costs 20% less than Fable 5.1, does more at lower effort levels, and writes clearer reports after long agent runs. If you already route Claude through Bifrost, change one model string to anthropic/claude-fable-5-2. Your routing rules, fallbacks, virtual keys, budgets, guardrails and logs keep working as they are. Why Fable 5.2 Anthropic positions Fable 5.2 as a cheaper, sharper Fable 5.1 for agentic work. Per

Nov 09, 2026•Akshay Deo
Debunking Litellm Rust benchmarking: Part 1

Debunking Litellm Rust benchmarking: Part 1

LiteLLM says its new Rust gateway has about 7x lower overhead, 9x less memory and about 4.5x more requests per dollar than Bifrost. We checked those claims against their website, their blog post and the CSV and JSON files in their own ai-gateway-bench repo (2026-11-01). * This post covers their benchmark only. * In Part 2 we will run the same benchmarks with full disclosure and a like-for-like setup. * LiteLLM’s Rust port is still a partial migration. As checked on November 1, 2026, GitHub’s

Nov 01, 2026•Akshay Deo
AI Gateway
Bifrost CLI v1.0: One launcher to connect your coding agents to the Gateway and manage Bifrost

Bifrost CLI v1.0: One launcher to connect your coding agents to the Gateway and manage Bifrost

Bifrost CLI already enabled developers to launch coding agents such as Claude Code, Codex and OpenCode through Bifrost. With v1.0, developers can now choose which gateway instance to connect to, sign in with SSO or a virtual key, and manage the Gateway from the same terminal. A gateway can only govern the traffic that reaches it. That sounds obvious, but it became a real problem as coding agents moved into the terminal. Developers were using Claude Code, Codex CLI, Gemini CLI and OpenCode, oft

Oct 28, 2026•Raggav Subramani
GPT-6.1 Terra is now available on Birost

GPT-6.1 Terra is now available on Birost

OpenAI released GPT-6.1 Terra today, and you can call it through Bifrost right now. Change one model string. Your routing, fallbacks, budgets, guardrails and logs keep working as they are. Terra is OpenAI's new fast, low-cost model for computer use, visual reasoning and everyday writing. It costs half as much as GPT-6.1 Sol and, by OpenAI's numbers, matches GPT-6 Astra on agent benchmarks at a tenth of the price. Why Terra Terra is built for high-volume agentic work where cost and latency ma

Oct 26, 2026•Akshay Deo