Bifrost
Bifrost is a high-performance open-source AI gateway that unifies access to 20+ AI providers through a single OpenAI-compatible API. It supports 1,000+ models with adaptive load balancing, automatic failover, semantic caching, and enterprise observability features. Bifrost is open-source under Apache 2.0.
Real signal across most facets with visible, nameable gaps — the contract exists but is thin, or the portal is good while governance and commercial terms are absent.
API Evangelist profiles Bifrost the way a machine reads it — 54 machine-readable artifacts across 4 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — Bifrost scores 58.5/100 (developing), with a separate agent-readiness read of 48/100 (agent ready). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile Bifrost
Each block below is one kind of artifact we hold for Bifrost. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 4
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
Bifrost Go SDK
The Bifrost Go SDK provides a native Go client for embedding the Bifrost AI gateway directly into Go applications using the github.com/maximhq/bifrost/core package.
Bifrost MCP Gateway
The Bifrost Model Context Protocol (MCP) Gateway enables AI agents to discover and execute external tools through a standardized protocol, with OAuth 2.0 authentication and tool...
Bifrost Chat API
Chat completions compatible with OpenAI chat API
Bifrost Health API
Gateway health and status endpoints
Pricing Plans 1
Pricing is part of the interface. Machine-readable plans tell you what a tier costs and includes before you commit — one of the six things the Kin Score reads for commercial clarity.
Published pricing tiers and plan structures.
Rate Limits 1
Rate limits are the difference between a demo that works and a production integration that doesn't fall over. Publishing them is an operational-transparency signal — and a hard requirement for any agent that plans its own throughput.
Documented rate limits and quota policies.
Bifrost Rate Limits
RATE LIMITSFinOps 1
Cost, billing, and metering signals let a buyer model the financial operations of an API before it's live. We profile them for the same reason we profile pricing: the money is part of the contract.
Cost, billing, and metering signals for API financial operations.
Bifrost Finops
FINOPSFeatures 8
The notable capabilities this provider advertises, captured as structured features so they can be searched and compared instead of read one landing page at a time.
Notable capabilities this provider offers.
OpenAI-Compatible API
Single API interface compatible with OpenAI SDK for all 20+ providers.
Adaptive Load Balancing
Distribute requests across providers and models based on availability and performance.
Automatic Failover
Automatically retry failed requests on alternative providers without client changes.
Semantic Caching
Cache semantically similar prompts to reduce latency and API costs.
MCP Gateway
Model Context Protocol gateway for AI agent tool discovery and execution.
Go SDK
Native Go library for embedding Bifrost gateway directly into applications.
Enterprise Observability
Built-in metrics, tracing, and logging for production AI gateway deployments.
Provider Key Management
Centralized API key management for all connected AI providers.
Scroll within the panel for all 8 ·
Semantic Vocabularies 1
JSON-LD contexts give the data shared meaning across APIs. We profile them because semantics are what let a machine reconcile 'customer' here with 'customer' somewhere else.
JSON-LD contexts and semantic vocabularies used across these APIs.
Bifrost Context
JSON-LDSpectral Rules 2
Governance rulesets we run against this provider's specs — the automated checks behind parts of the score. Profiling them makes the quality bar explicit and re-runnable, not a matter of opinion.
Bifrost API Rules
SPECTRALBifrost API Rules
SPECTRALJSON Schema 7
Standalone JSON Schema definitions describe the data models behind the API. We profile them so the shapes are validatable on their own — useful long after a single request is forgotten.
Standalone JSON Schema definitions for this provider's data models.
ChatChoice
JSON SCHEMAChatCompletionRequest
JSON SCHEMAChatCompletionResponse
JSON SCHEMAChatMessage
JSON SCHEMAHealthResponse
JSON SCHEMAProviderStatus
JSON SCHEMAUsageStats
JSON SCHEMAScroll within the panel for all 7 ·
JSON Structure 7
JSON Structure captures the data shapes in a form built for tooling — a complement to JSON Schema that keeps the model machine-legible.
JSON Structure definitions describing this provider's data shapes.
Bifrost Chat Choice Structure
JSON STRUCTUREBifrost Chat Completion Request Structure
JSON STRUCTUREBifrost Chat Completion Response Structure
JSON STRUCTUREBifrost Chat Message Structure
JSON STRUCTUREBifrost Health Response Structure
JSON STRUCTUREBifrost Provider Status Structure
JSON STRUCTUREBifrost Usage Stats Structure
JSON STRUCTUREScroll within the panel for all 7 ·
Examples 7
Real request and response payloads are what turn a spec from abstract into obvious — and they're one of the twelve things an agent needs to call an API correctly on the first try.
Example request and response payloads for these APIs.
Bifrost Chat Choice Example
EXAMPLEBifrost Chat Message Example
EXAMPLEBifrost Usage Stats Example
EXAMPLEScroll within the panel for all 7 ·
Security Posture 3
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.
Recommended x-agentic-access execution contracts for AI agents.
Use Cases 5
What developers actually build with this provider — captured so the catalogue answers 'what is this for', not just 'what does this expose'.
What developers build with this provider.
Multi-Provider AI Applications
Build applications that can seamlessly switch between OpenAI, Anthropic, and other providers.
Cost Optimization
Route requests to cheaper providers during peak costs or use caching to reduce API spend.
High Availability AI
Ensure AI features remain available by failing over across multiple provider accounts.
AI Agent Tooling
Enable AI agents to discover and execute tools through the MCP gateway protocol.
LLM Provider Evaluation
A/B test different models and providers without changing application code.
Integrations 6
Pre-built integrations with other platforms tell you where this provider already fits in a stack.
Pre-built integrations with other platforms and tools.
OpenAI
Route to OpenAI GPT-4o, GPT-4, and other OpenAI models.
Anthropic
Route to Claude 3.5 Sonnet, Claude 3 Opus, and other Anthropic models.
Cohere
Route to Cohere Command and other Cohere models.
AWS Bedrock
Route to models hosted on AWS Bedrock including Titan and Claude.
Azure OpenAI
Route to Azure-hosted OpenAI deployments.
Google Vertex AI
Route to Gemini and other models on Google Vertex AI.
Resources
Every other property we hold for Bifrost — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 2
Portal, sign-up, and the first successful call
Documentation 1
Reference material describing how the API behaves
Agent Surfaces 2
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 2
Pagination, idempotency, versioning, errors, and events
Build 2
SDKs, sample code, and the tooling you integrate with
Access & Security 3
Authentication, authorization, and security posture
Operate 2
Status, limits, changes, and where to get help
← All providers · Data indexed from github.com/api-evangelist/bifrost · machine-readable index on apis.io