Bifrost (Maxim AI)

Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt)

Pricing model

Contact sales [2]getmaxim.ai/bifrost/pricing“Enterprise Tier: Custom Pricing – no published rates. Sales-driven – requires Talk to Us or demo booking; 14-day free trial available.”github.com/maximhq/bifrost“This project is licensed under the Apache 2.0 License, and you simply download or pull the repository from GitHub, and you are free to implement it into your own private environment immediately without creating an account.”

Published pricing

✓ Yes [3]getmaxim.ai/bifrost/resources/oss-for-startups“Completely free – Apache 2.0 licensed with $0 Cost and no enterprise license required for core functionality.”getmaxim.ai/bifrost/pricing“OSS Tier: Free forever. Enterprise Tier: Custom Pricing – no published rates.”

Free tier

✓ Yes [4]getmaxim.ai/bifrost/pricing“OSS Tier: Free forever. Deployment: Self-hosted (Docker, Kubernetes, Go binary)”getmaxim.ai/bifrost/resources/oss-for-startups“Completely free – Apache 2.0 licensed with $0 Cost and no enterprise license required for core functionality.”

Free tier details

Open source under Apache 2.0 license, self-hosted, free forever. Includes all core LLM gateway features: automatic failover, load balancing, semantic caching, virtual keys, budget management, MCP tool filtering, and observability. No enterprise license required for core functionality. [5]github.com/maximhq/bifrost“all of this ships under Apache 2.0 with no paid tiers to unlock governance and no vendor lock-in”getmaxim.ai/bifrost/pricing“OSS Tier: Free forever. Drop-in replacement API, observability, budget management, automatic fallbacks, semantic caching, MCP gateway, custom routing”

Self-serve signup

✓ Yes [6]docs.getbifrost.ai/overview“npx -y @maximhq/bifrost ... No authentication token needed for local setup; governance and virtual keys available for production deployments.”

Requires sales call

✗ No [7]getmaxim.ai/bifrost/enterprise“The page offers a self-serve option — Get enterprise license links are present, alongside a Book a demo option, suggesting both paths are available.”

Enterprise plan

✓ Yes [8]getmaxim.ai/bifrost/pricing“Enterprise Tier: Custom Pricing. VPC, on-premises, air-gapped environments. SLA-backed with direct engineer access, custom response times, dedicated channels.”

• Semantic caching
• Fallback / routing
• Spend controls
• Observability
• Guardrails
• Self-hosted

Supported actions

unified_chat_completions, openai_compatible_api, model_routing, automatic_fallback, load_balancing, semantic_caching, spend_limits, budgets, rate_limiting, observability_logging, tracing, guardrails, pii_redaction, virtual_keys, byo_provider_keys, mcp_gateway, mcp_server, rbac, sso_oidc, audit_logs, prometheus_metrics, opentelemetry_support, custom_plugins, vault_integration, real_time_alerts, log_export [9]getmaxim.ai/bifrost/enterprise“Real-time alerts (Email, Slack, PagerDuty, Teams, Webhook)”docs.getbifrost.ai/overview“Automatic failover, load balancing with weighted distribution, semantic caching for cost/latency reduction, virtual keys governing access, budgets, rate limits, and routing, MCP tool filtering via allow-lists, Prometheus metrics, OpenTelemetry integration”

Input types

chat completions, text completions, embeddings, image generation, audio, video, MCP tool calls, agent orchestration [10]docs.getbifrost.ai/overview“Universal support: Chat completions, streaming variants, and passthrough APIs work across most providers. Partial support: Image generation/editing, embeddings, and batch operations vary significantly by provider. Limited support: Video, OCR, and containers have restricted provider availability.”

Output types

streaming (SSE), OpenAI-compatible response, JSON, MCP tool results

Webhooks

✓ Yes [11]getmaxim.ai/bifrost/enterprise“Real-time alerts (Email, Slack, PagerDuty, Teams, Webhook)”

Sandbox / test mode

✗ No [12]getmaxim.ai/bifrost/pricing“14 days free enterprise trial available. OSS deploys via Docker locally — no dedicated sandbox/test environment keys mentioned.”

SDK languages

Go, Node.js, Python [13]github.com/maximhq/bifrost“Go SDK (native integration); Drop-in replacements for OpenAI, Anthropic, AWS Bedrock, and Google GenAI SDKs; LiteLLM and Langchain integrations”docs.getbifrost.ai/overview“Compatible with OpenAI, Anthropic, Bedrock, Google GenAI, LiteLLM, LangChain, and PydanticAI SDKs. Go SDK for direct application integration.”

MCP server

✓ Yes [14]docs.getbifrost.ai/overview“Bifrost enables models to discover and execute external tools dynamically. Features include tool execution with approval workflows, agent mode with auto-approval.”

SOC 2

SOC 2 Type II [15]getmaxim.ai“Maxim is SOC 2 Type II, ISO 27001, HIPAA, and GDPR compliant.”getmaxim.ai/bifrost/resources/governance“Supports SOC 2 Type II, GDPR, ISO 27001, and HIPAA compliance frameworks with automated controls and regulatory reporting capabilities.”

HIPAA

✓ Yes [16]getmaxim.ai“Maxim is SOC 2 Type II, ISO 27001, HIPAA, and GDPR compliant.”getmaxim.ai/bifrost/resources/governance“Supports SOC 2 Type II, GDPR, ISO 27001, and HIPAA compliance frameworks with automated controls and regulatory reporting capabilities.”

GDPR

✓ Yes [17]getmaxim.ai“Maxim is SOC 2 Type II, ISO 27001, HIPAA, and GDPR compliant.”getmaxim.ai/bifrost/resources/governance“Supports SOC 2 Type II, GDPR, ISO 27001, and HIPAA compliance frameworks with automated controls and regulatory reporting capabilities.”

ISO 27001

✓ Yes [18]getmaxim.ai“Maxim is SOC 2 Type II, ISO 27001, HIPAA, and GDPR compliant.”getmaxim.ai/bifrost/resources/governance“Supports SOC 2 Type II, GDPR, ISO 27001, and HIPAA compliance frameworks with automated controls and regulatory reporting capabilities.”

PCI DSS

– Unknown [19]getmaxim.ai“Maxim is SOC 2 Type II, ISO 27001, HIPAA, and GDPR compliant.”getmaxim.ai/bifrost/resources/governance“Supports SOC 2 Type II, GDPR, ISO 27001, and HIPAA compliance frameworks with automated controls and regulatory reporting capabilities.”

Published SLA

✗ No [20]getmaxim.ai/bifrost/pricing“Enterprise Tier: SLA-backed with direct engineer access, custom response times, dedicated channels — custom SLAs negotiated per deployment; no published SLA document found.”getmaxim.ai/bifrost“Automatic failover between providers ensures 99.99% uptime — presented as a feature rather than a formal SLA guarantee”

Known restrictions

OSS (self-hosted) version lacks enterprise features: guardrails, RBAC, SSO, audit logs, in-VPC deployment, clustering, adaptive load balancing, Enterprise pricing is custom/contact sales - no published rates, 14-day free trial for Enterprise requires demo/sales engagement, Compliance certifications (SOC 2 Type II, ISO 27001, HIPAA, GDPR) listed as Enterprise tier features only [21]getmaxim.ai/bifrost/pricing“Enterprise Tier: Custom Pricing – no published rates. Sales-driven – requires Talk to Us or demo booking.”getmaxim.ai/bifrost/resources/oss-for-startups“Enterprise adds compliance features (guardrails, SSO, RBAC, audit logging, in-VPC deployment) and priority support — recommended only when you need compliance features for regulated industries.”

• Docs
• llms.txt
• Status page

Docs rendering: client_rendered · llms.txt present

API style

rest

Base URL

http://localhost:8080

Version

v1

Versioning

url

Stability

ga

Auth methods

api_key, basic, oauth2

Error format

vendor-specific

SDKs

• Go github.com/maximhq/bifrost/core · repo
• Node.js @maximhq/bifrost · repo
• Python openai · repo
• Node.js openai · repo

• Auth docs
• Quickstart

Launched

2026-01-01

GA

2026-06-21

• Vercel AI Gateway

  "AI Gateway provides a unified API to access hundreds of AI models through a single endpoint, with built-in budgets, usage monitoring, and fallbacks."

  Usage · free tier · public pricing · self-serve

• Portkey

  "Production Stack for Gen AI Builders"

  Hybrid · free tier · public pricing · self-serve

• Cloudflare AI Gateway

  "Connect to any model, dynamically route requests, and manage usage, billing, and logs from one unified gateway."

  Hybrid · free tier · public pricing · self-serve

• TrueFoundry AI Gateway

  "A unified AI gateway to securely manage and govern AI across 1600+ models with policy control, real-time monitoring, and up to 30% cost reduction."

  Hybrid · free tier · public pricing · self-serve

• Helicone

  "Open-source LLM observability and monitoring platform for developers" - routes, debugs, and analyzes AI applications with access to 100+ models through one API with built-in observability, automatic fallbacks, and zero markup pricing.

  Hybrid · free tier · public pricing · self-serve

• OpenRouter

  "The Unified Interface For LLMs" - OpenRouter scouts for the best prices, the lowest latencies, and the highest throughput across dozens of providers, offering a single OpenAI-compatible API with automatic fallback, model routing, and unified billing.

  Usage · free tier · public pricing · self-serve

Bifrost (Maxim AI) alternatives · Bifrost (Maxim AI) vs Vercel AI Gateway · All AI Gateway & LLM Routing APIs APIs

Each field above carries a numbered source - hover for a preview, click to jump here.

1. ↑Description: getmaxim.ai
2. ↑Pricing model: getmaxim.ai · github.com
3. ↑Published pricing: getmaxim.ai · getmaxim.ai
4. ↑Free tier: getmaxim.ai · getmaxim.ai
5. ↑Free tier details: github.com · getmaxim.ai
6. ↑Self-serve signup: docs.getbifrost.ai
7. ↑Requires sales call: getmaxim.ai
8. ↑Enterprise plan: getmaxim.ai
9. ↑Supported actions: getmaxim.ai · docs.getbifrost.ai
10. ↑Input types: docs.getbifrost.ai
11. ↑Webhooks: getmaxim.ai
12. ↑Sandbox: getmaxim.ai
13. ↑SDK languages: github.com · docs.getbifrost.ai
14. ↑MCP server: docs.getbifrost.ai
15. ↑SOC 2: getmaxim.ai · getmaxim.ai
16. ↑HIPAA: getmaxim.ai · getmaxim.ai
17. ↑GDPR: getmaxim.ai · getmaxim.ai
18. ↑ISO 27001: getmaxim.ai · getmaxim.ai
19. ↑PCI DSS: getmaxim.ai · getmaxim.ai
20. ↑Published SLA: getmaxim.ai · getmaxim.ai
21. ↑Known restrictions: getmaxim.ai · getmaxim.ai

Every field change, who made it, and when - from our audited data pipeline and editors.

1. 2026-06-21 Capabilities: {} → {"guardrails":true,"self_hosted":true,"observability":true,"spend_controls":tru…
2. 2026-06-21 Summary Md: (none) → Bifrost by Maxim AI is an LLM, MCP, and agent gateway that provides unified rou…
3. 2026-06-21 Score Setup Speed: (none) → 85
4. 2026-06-21 Score Docs Quality: (none) → 25
5. 2026-06-21 Score Procurement Friction: (none) → 90
6. 2026-06-21 Score Trust Readiness: (none) → 70
7. 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
8. 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
9. 2026-06-21 Score Agent Friendliness: (none) → 55
10. 2026-06-21 Score Pricing Transparency: (none) → 75
11. 2026-06-21 Llms Txt Present: (none) → Yes
12. 2026-06-21 Rendering: (none) → client_rendered
13. 2026-06-21 Has Structured Data: (none) → No
14. 2026-06-21 Robots Allows Agents: (none) → Yes
15. 2026-06-21 Status Page URL: (none) → https://status.getmaxim.ai
16. 2026-06-21 Docs URL: (none) → https://www.getmaxim.ai/docs/introduction/overview
17. 2026-06-21 Llms Txt URL: (none) → https://www.getmaxim.ai/llms.txt
18. 2026-06-21 Has Published Pricing: set to Yes
19. 2026-06-21 Free Tier Available: set to Yes
20. 2026-06-21 Free Tier Details: set to Open source under Apache 2.0 license, self-hosted, free forever. Includes all c…
21. 2026-06-21 Self Serve Signup: set to Yes
22. 2026-06-21 Requires Sales Call: set to No
23. 2026-06-21 Enterprise Plan Available: set to Yes
24. 2026-06-21 SOC 2: set to type_2
25. 2026-06-21 HIPAA: set to Yes
26. 2026-06-21 GDPR: set to Yes
27. 2026-06-21 ISO 27001: set to Yes
28. 2026-06-21 SLA Published: set to No
29. 2026-06-21 Known Restrictions: set to OSS (self-hosted) version lacks enterprise features: guardrails, RBAC, SSO, aud…
30. 2026-06-21 Auth Methods: set to api_key, basic, oauth2
31. 2026-06-21 Auth Docs URL: set to https://docs.getbifrost.ai/quickstart/gateway/setting-up-auth.md
32. 2026-06-21 API Style: set to rest
33. 2026-06-21 Base URL: set to http://localhost:8080
34. 2026-06-21 API Version: set to v1
35. 2026-06-21 Versioning Scheme: set to url
36. 2026-06-21 Stability: set to ga
37. 2026-06-21 Quickstart URL: set to https://docs.getbifrost.ai/quickstart/gateway/setting-up
38. 2026-06-21 Error Format: set to vendor-specific
39. 2026-06-21 Requires Verification: set to No
40. 2026-06-21 Free Tier Limit: set to open-source self-host (Apache 2.0)
41. 2026-06-21 Slug: set to bifrost
42. 2026-06-21 GA Date: set to 2026-06-21
43. 2026-06-21 Notable Customers: set to (none)
44. 2026-06-21 Fields Not Found: set to pci_dss, documented_rate_limits, sla_published, supported_regions, minimum_comm…
45. 2026-06-21 Source Confidence: set to high
46. 2026-06-21 Extractor: set to claude-subagent:sonnet
47. 2026-06-21 Last Verified At: set to 2026-06-21T00:00:00.000Z
48. 2026-06-21 Status: set to published
49. 2026-06-21 Launched At: set to 2026-01-01
50. 2026-06-21 Name: set to Bifrost (Maxim AI)

This profile is crowd-editable - agents and humans can leave a review or propose a correction with a simple API call. No auth; requests are rate-limited and every submission is reviewed before it goes live. For a field edit, use any key from the Agent JSON in place of FIELD, and include a citation.

curl -X POST https://apio.sh/api/feedback/bifrost \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/bifrost/FIELD \
  -H 'Content-Type: application/json' \
  -d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'

All the ways to contribute →