Manifest
Manifest is an open-source LLM gateway for AI agents and agentic workflows, connecting them to any model provider through one OpenAI-compatible endpoint. It routes requests across subscriptions, pay-per-token, bring-your-own-key, local models and custom providers, falls back when providers are down, autofixes broken requests on the fly, and tracks every request, token and dollar for observability. It can be self-hosted (Docker image manifestdotbuild/manifest, code at github.com/mnfst/manifest) or used as a cloud service at app.manifest.build.
Manifest is listed with 1 API on the APIs.io network. Tagged areas include Company, LLM Gateway, AI Agents, Artificial Intelligence, and Open Source.
Manifest’s developer surface includes CLI, changelog, authentication, documentation, API reference, getting-started guide, engineering blog, and 29 more developer resources.
Kin Score
Standards implemented 3
Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.
APIs 1
Individual APIs this provider publishes, each with its own machine-readable definition.
Manifest LLM Gateway API
OpenAI- and Anthropic-compatible proxy API of the Manifest LLM gateway. Clients point at the gateway URL, send `auto` as the model and routing picks the real model; documented e...
MCP Servers 1
Model Context Protocol servers that expose these APIs to AI agents.
Manifest MCP Server
Official remote Model Context Protocol server run by the Manifest LLM gateway. It manages the authorizing user's workspace (harnesses, provider connections, routing, models, pri...
MCP SERVERManifest API pricing
Prices published by Manifest.
| Plan | Price |
|---|---|
| Self-hosted | $0 |
| Manifest Cloud | $19 |
| Enterprise | Let's Talk |
Plan details, limits and sources →
Rate limits
- Per-workspace request rate (M201): 200 requests per minute
- Per-IP request rate (M202): 500 requests per minute
- Per-workspace concurrency (M203): 10 requests in flight at once
Pricing Plans 1
Published pricing tiers and plan structures.
Rate Limits 1
Documented rate limits and quota policies.
Manifest Rate Limits
RATE LIMITSSecurity Posture 2
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Scopes 1
OAuth scopes governing access to this provider's APIs.
Resources
Get Started 3
Portal, sign-up, and the first successful call
Documentation 2
Reference material describing how the API behaves
Agent Surfaces 3
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 4
Pagination, idempotency, versioning, errors, and events
Build 6
SDKs, sample code, and the tooling you integrate with
Access & Security 3
Authentication, authorization, and security posture
Operate 5
Status, limits, changes, and where to get help
Commercial 4
Pricing, plans, and the legal terms of use
Company 2
The organization behind the API
Other 4
Properties that don't map to a standard resource type
Source (apis.yml)
Manifest API — frequently asked questions
Does Manifest have an API?
Yes. APIs.io lists 1 API from Manifest, including Manifest LLM Gateway API.
How do I authenticate with the Manifest API?
Manifest documents its authentication (3 schemes). The details are profiled on APIs.io as Manifest Authentication.
How much does the Manifest API cost?
Manifest publishes its prices; its Self-hosted plan is $0 as of 2026-11-05. APIs.io lists 3 pricing plans for Manifest, with each plan's price, limits and inclusions under Pricing on this page.
Does Manifest have an MCP server?
Yes. APIs.io lists 1 MCP server for Manifest: Official remote Model Context Protocol server run by the Manifest LLM gateway. It manages the authorizing user's workspace (harnesses, provider connections, routing, models, prices, request log) over
Is the Manifest API ready for AI agents?
Manifest has a Kin Score of 48.6 out of 100 (developing) and an Agent Readiness score of 27.6 (agent-aware), scored by API Evangelist on 2026-11-06.
Work with this as data
Every provider here is available over the APIs.io API and to AI agents over MCP.