---
title: "Bifrost pricing"
description: "Compare Bifrost OSS and Enterprise pricing for an open-source AI gateway with drop-in SDK compatibility, automatic fallbacks, observability, MCP Gateway, and enterprise governance."
url: "https://www.getmaxim.ai/bifrost/pricing"
markdown: "https://www.getmaxim.ai/bifrost/pricing.md"
---

# Bifrost pricing

> Compare Bifrost OSS and Enterprise pricing for an open-source AI gateway with drop-in SDK compatibility, automatic fallbacks, observability, MCP Gateway, and enterprise governance.

## Important Links

- [View MCP Gateway](https://www.getmaxim.ai/bifrost/resources/mcp-gateway.md)
- [Features](https://www.getmaxim.ai/bifrost/#features)
- [Enterprise](https://www.getmaxim.ai/bifrost/enterprise)
- [Pricing](https://www.getmaxim.ai/bifrost/pricing.md)
- [Docs](https://docs.getbifrost.ai)
- [GitHub](https://github.com/maximhq/bifrost)
- [Book a Demo](https://www.getmaxim.ai/bifrost/book-a-demo)

## Pricing Plans

_OSS and Enterprise_

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 forever - OSS:** 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](https://github.com/maximhq/bifrost), [Docs](https://docs.getbifrost.ai).
- **Custom pricing - Enterprise:** 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](https://www.getmaxim.ai/bifrost/book-a-demo), [Enterprise](https://www.getmaxim.ai/bifrost/enterprise).

## Bifrost OSS

_Free forever_

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](https://github.com/maximhq/bifrost)
- [Quickstart docs](https://docs.getbifrost.ai/quickstart/gateway/setting-up)
- [Bifrost CLI resource](https://www.getmaxim.ai/bifrost/resources/bifrost-cli.md)

## Bifrost Enterprise

_Custom pricing_

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](https://www.getmaxim.ai/bifrost/resources/enterprise-deployment.md).
- **Governance:** Use SSO, RBAC, virtual keys, budgets, audit logs, and policy controls for production AI access. [Governance resource](https://www.getmaxim.ai/bifrost/resources/governance.md).
- **Guardrails:** Add enterprise safety controls for content moderation, PII handling, and policy enforcement. [Guardrails resource](https://www.getmaxim.ai/bifrost/resources/guardrails.md).

## OSS vs Enterprise Feature Comparison

_Capability matrix_

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

| Capability | OSS | Enterprise |
| --- | --- | --- |
| Single OpenAI-compatible API | Included | Included |
| Drop-in Replacement | Included | Included |
| OpenTelemetry | Included | Included |
| Built-in Observability | Included | Included |
| Budget and Rate Limits | Included | Included |
| Virtual Keys | Included | Included |
| Custom Routing Rules and Flows | Included | Included |
| Bifrost CLI | Included | Included |
| MCP Gateway | Included | Included |
| MCP Code Mode | Included | Included |
| Semantic Caching | Included | Included |
| Prometheus Metrics | Included | Included |
| Prompt Repository | Included | Included |
| Custom Plugin Development | Included | Included |
| Guardrails | Not included | Included |
| Clustering | Not included | Included |
| Adaptive Load Balancing | Not included | Included |
| SAML, OpenID, and Audit Reports | Not included | Included |
| Vault Support | Not included | Included |
| Log Exports | Not included | Included |
| In-VPC Deployments | Not included | Included |
| Identity Providers like Okta and Entra | Not included | Included |
| Role-Based Access Control | Not included | Included |
| MCP with Federated Auth | Not included | Included |
| Audit Logs | Not included | Included |
| External OTel Connectors | Not included | Included |
| Commercial onboarding and production support | Community | Included |

## When Enterprise Is The Right Fit

_Production requirements_

- **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.

## Features

### OSS Features

- **01 - Model Catalog:** Access 8+ providers and 1000+ AI models through a unified interface. Also supports custom deployed models.
- **02 - Budgeting:** Set spending limits and track costs across teams, projects, and models.
- **03 - Provider Fallback:** Automatic failover between providers ensures 99.99% uptime for your applications.
- **04 - MCP Gateway:** Centralize all MCP tool connections, governance, security, and auth. Your AI can safely use MCP tools with centralized policy enforcement. [MCP Gateway resource](https://www.getmaxim.ai/bifrost/resources/mcp-gateway.md).
- **05 - Virtual Key Management:** Create different virtual keys for different use cases with independent budgets and access control.
- **06 - Unified Interface:** One consistent API for all providers. Switch models without changing code.
- **07 - Drop-in Replacement:** Replace your existing SDK with just one line change. Compatible with OpenAI, Anthropic, LiteLLM, Google GenAI, LangChain, and more. [Drop-in replacement docs](https://docs.getbifrost.ai/features/drop-in-replacement).
- **08 - Built-in Observability:** Out-of-the-box OpenTelemetry support. Built-in dashboard for quick visibility without complex setup.
- **09 - Community Support:** Active Discord community with responsive support and regular updates.

### Enterprise Features

- **01 - Governance:** SAML support for SSO and role-based access control with policy enforcement for team collaboration. [Governance resource](https://www.getmaxim.ai/bifrost/resources/governance.md).
- **02 - Adaptive Load Balancing:** Automatically optimizes traffic distribution across provider keys and models based on real-time performance metrics.
- **03 - Cluster Mode:** High availability deployment with automatic failover and load balancing. Peer-to-peer clustering where every instance is equal.
- **04 - Alerts:** Real-time notifications for budget limits, failures, and performance issues on Email, Slack, PagerDuty, Teams, Webhook, and more.
- **05 - Log Exports:** Export and analyze request logs, traces, and telemetry data from Bifrost with enterprise-grade data export for compliance, monitoring, and analytics.
- **06 - Audit Logs:** Comprehensive logging and audit trails for compliance and debugging.
- **07 - Vault Support:** Secure API key management with HashiCorp Vault, AWS Secrets Manager, Google Secret Manager, and Azure Key Vault integration.
- **08 - VPC Deployment:** Deploy Bifrost within your private cloud infrastructure with VPC isolation, custom networking, and enhanced security controls. [Enterprise deployment resource](https://www.getmaxim.ai/bifrost/resources/enterprise-deployment.md).
- **09 - Guardrails:** Automatically detect and block unsafe model outputs with real-time policy enforcement and content moderation across all agents. [Guardrails resource](https://www.getmaxim.ai/bifrost/resources/guardrails.md).

## 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.

### OpenAI

_openai.py_

```
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!"}],
)
```

### Anthropic

_anthropic.py_

```
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"}],
)
```

### LiteLLM

_litellm.py_

```
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!"}],
)
```

### Google GenAI

_genai.py_

```
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.

- [Gateway setup docs](https://docs.getbifrost.ai/quickstart/gateway/setting-up)
- [Drop-in replacement docs](https://docs.getbifrost.ai/features/drop-in-replacement)

## Trust And Deployment

- **Open Source:** Bifrost is open source under the Apache 2.0 License. [GitHub](https://github.com/maximhq/bifrost).
- **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](https://www.getmaxim.ai/bifrost/resources/enterprise-deployment.md).
- **Deployment:** Enterprise resources cover VPC, on-premise, air-gapped, and multi-cloud use. [Enterprise deployment](https://www.getmaxim.ai/bifrost/resources/enterprise-deployment.md).

## FAQ

### What is Bifrost?

Bifrost is an open-source LLM gateway that introduces 11 microseconds of overhead at 5K RPS on a t3.xlarge machine. It provides a unified layer for model access, guardrails, and governance across AI systems. [Docs](https://docs.getbifrost.ai), [GitHub](https://github.com/maximhq/bifrost).

### How is my data protected?

Bifrost offers zero-touch in-VPC deployments, so no data ever leaves your environment or passes through Bifrost/Maxim servers. [Governance](https://www.getmaxim.ai/bifrost/resources/governance.md), [Enterprise deployment](https://www.getmaxim.ai/bifrost/resources/enterprise-deployment.md).

### Can Bifrost integrate with my existing AI stack?

Yes. Bifrost works with major LLM SDKs and frameworks. Compatible SDKs include OpenAI, Anthropic, Mistral, LangChain, LangGraph, and LiteLLM. [Drop-in replacement docs](https://docs.getbifrost.ai/features/drop-in-replacement).

### How much does Bifrost cost?

Pricing is based on the number of devices Edge runs on. Bifrost Edge is currently available in early access, and we are offering it at no cost to our existing enterprise customers. Full pricing will be released soon. [Pricing](https://www.getmaxim.ai/bifrost/pricing.md).

### How can I get started with Bifrost?

You can get started with the open-source version in seconds: npx @maximhq/bifrost [Docs](https://docs.getbifrost.ai), [GitHub](https://github.com/maximhq/bifrost).

## Related Resources

- [GitHub: Bifrost OSS](https://github.com/maximhq/bifrost)
- [Docs: Bifrost docs](https://docs.getbifrost.ai)
- [Resources: Bifrost resources](https://www.getmaxim.ai/bifrost/resources.md)
- [Buyer guide: LLM gateway buyer guide](https://www.getmaxim.ai/bifrost/resources/buyers-guide.md)
- [Enterprise deployment: private deployment](https://www.getmaxim.ai/bifrost/resources/enterprise-deployment.md)
- [Governance: Bifrost governance](https://www.getmaxim.ai/bifrost/resources/governance.md)
- [Guardrails: Bifrost guardrails](https://www.getmaxim.ai/bifrost/resources/guardrails.md)
- [Book a Demo: Bifrost demo](https://www.getmaxim.ai/bifrost/book-a-demo)

---

*This is a markdown version of [https://www.getmaxim.ai/bifrost/pricing](https://www.getmaxim.ai/bifrost/pricing) for AI/LLM consumption.*