Bifrost pricing

OSS and Enterprise

Pricing Plans

Bifrost pricing is split into a free open-source plan and a custom-priced enterprise plan.

Bifrost OSS is free forever for developers, small teams, and self-managed deployments. Bifrost Enterprise is for teams running production AI systems at scale with private deployment, governance, identity, compliance, and support requirements.

• Free foreverOSS. Self-hosted with Docker, Kubernetes, or Go binary. Includes drop-in replacement, OpenTelemetry-compatible metrics and traces, built-in observability, budget management, virtual keys, routing rules, Bifrost CLI, automatic fallbacks, caching, MCP Gateway with Code Mode, prompt repository, custom plugins, Maxim AI integration, docs, and community support. [GitHub] [Docs]
• Custom pricingEnterprise. Includes everything in OSS plus guardrails, cluster mode, adaptive load balancing, enterprise SSO via SAML and OIDC, vault support, MCP with federated auth, log exports, audit logs, role-based access control, SLA-backed enterprise support, and enterprise-ready VPC, on-prem, and air-gapped deployment. [Book a Demo] [Enterprise]

Free forever

Bifrost OSS

The OSS plan is meant for developers, small teams, and self-managed deployments that want a high-performance LLM gateway without a commercial license.

It includes the core routing, fallback, observability, virtual key, budget, cache, MCP, CLI, plugin, and drop-in replacement capabilities needed to run Bifrost locally or in self-managed infrastructure. [GitHub] [Quickstart docs] [Bifrost CLI resource]

Custom pricing

Bifrost Enterprise

The Enterprise plan adds production controls for organizations standardizing AI usage across teams, applications, and regulated environments.

Enterprise capabilities focus on private deployment, identity provider integration, RBAC, auditability, guardrails, adaptive load balancing, clustering, vault-backed secrets, log exports, federated MCP authentication, and commercial support.

• Private deployment. Deploy Bifrost in VPC, on-premise, air-gapped, or multi-cloud environments. [Enterprise deployment]
• Governance. Use SSO, RBAC, virtual keys, budgets, audit logs, and policy controls for production AI access. [Governance resource]
• Guardrails. Add enterprise safety controls for content moderation, PII handling, and policy enforcement. [Guardrails resource]

Capability matrix

OSS vs Enterprise Feature Comparison

OSS includes the core open-source gateway capabilities. Enterprise adds private deployment, identity, governance, compliance, reliability, and support controls for production organizations.

Production requirements

When Enterprise Is The Right Fit

• Private networking and deployment. Choose Enterprise when Bifrost must run inside private cloud infrastructure with network isolation and stronger security boundaries.
• Advanced governance. Choose Enterprise when identity provider integration, Okta or Entra support, RBAC, audit logs, vault-backed key management, and compliance workflows are required.
• Enterprise-grade reliability. Choose Enterprise when production AI systems need guardrails, adaptive load balancing, clustering, zero-downtime deployment support, log exports, and SLA-backed support.

Open Source & Enterprise

Drop-in replacement for compatible AI SDKs

Change one line of code to point compatible SDKs at Bifrost. Works with OpenAI, Anthropic, LiteLLM, Google GenAI, LangChain, and Vercel AI SDK. [Gateway setup docs] [Drop-in replacement docs]

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("OPENAI_API_KEY"),
    base_url="https://<bifrost_url>/openai",
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
)

import os
from anthropic import Anthropic

anthropic = Anthropic(
    api_key=os.environ.get("ANTHROPIC_API_KEY"),
    base_url="https://<bifrost_url>/anthropic",
)

message = anthropic.messages.create(
    model="claude-3-5-sonnet-20241022",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello, Claude"}],
)

import litellm

# Set the base URL to your Bifrost deployment
litellm.api_base = "https://<bifrost_url>"

response = litellm.completion(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
)

import google.generativeai as genai

genai.configure(
    api_key="YOUR_API_KEY",
    transport="rest",
    client_options={"api_endpoint": "<bifrost_url>/google"},
)

model = genai.GenerativeModel("gemini-pro")
response = model.generate_content("Hello!")

• Point the SDK base URL at your Bifrost deployment.
• Keep API keys in your environment or secret manager.
• See the docs for provider-specific configuration and deployment steps.

Trust

• Open Source. Bifrost is open source under the Apache 2.0 License. [GitHub]
• Publisher. Bifrost is published by H3 Labs Inc. and Maxim AI.
• Compliance. The site references SOC 2 Type II, GDPR, HIPAA, and ISO 27001 signals. [Enterprise deployment]
• Deployment. Enterprise resources cover VPC, on-premise, air-gapped, and multi-cloud use. [Enterprise deployment]

FAQ

Related resources

• [GitHub: Bifrost OSS]
• [Docs: Bifrost docs]
• [Resources: Bifrost resources]
• [Buyer guide: LLM gateway buyer guide]
• [Enterprise deployment: private deployment]
• [Governance: Bifrost governance]
• [Guardrails: Bifrost guardrails]
• [Book a Demo: Bifrost demo]