Manifest
Ranked in LLM gateways·Free plan·paid from $19/mo
About
Manifest is an open-source LLM gateway for routing requests, handling provider failures, repairing malformed requests, and tracking inference spending. It offers one endpoint compatible with OpenAI and Anthropic for models and subscriptions, and connects API keys, paid subscriptions, local models, and custom endpoints. If a provider goes down, the gateway retries through another provider. Autofix can repair malformed requests and resend them when retries do not resolve the problem. Its observability view shows spending by harness, which models served requests, and what failed. Named local integrations include Ollama, llama.cpp, and LM Studio. The self-hosted gateway runs in Docker, works offline, requires no account, and supports amd64 and arm64. Its Free plan includes unlimited self-hosted use, while the Cloud Free plan allows 10,000 routed requests per calendar month and cannot reach local models running on the user's machine. Pro costs 19.00 USD per month and includes unlimited routed requests on Manifest Cloud. Self-hosted routing and request data stay on customer servers except for documented telemetry and Autofix flows.
Who it is for
Manifest suits AI builders, teams, startups, and platforms or providers managing inference for agents and workflows. Its self-hosted option fits users who need offline operation, while Cloud users should consider the monthly request cap on Free.
What is good
- OpenAI- and Anthropic-compatible endpoint
- Retries through another provider after outages
- Autofix repairs malformed requests
- Self-hosted version works offline without an account
- Tracks spending, models, and failures
What to know first
- Cloud Free is limited to 10,000 monthly requests
- Cloud Free cannot reach local machine models
- Pro is single-user
- Cloud recordings are retained seven days on Free
Verdict
Manifest combines routing, fallback handling, request repair, and usage visibility in one gateway. Teams choosing Cloud should weigh the Free request limit and retention period against the $19.00 USD per month Pro plan; self-hosting is also available.
Compared on LLM gateways
- Free plan
- Yesmanifest.build
- Paid from
- $19/momanifest.build
- Fallback routing
- Yesmanifest.build
- Usage analytics
- Yesmanifest.build
- Self-hosted deployment
- Yesmanifest.build
- Budget controls
- Yesmanifest.build
- Virtual API keys
- Yesmanifest.build
Facts
- Product
- Manifest is an open-source LLM gateway that routes requests, provides fallbacks, repairs failing requests with Autofix, and tracks spending.manifest.build · 1 Oct 2026
- Routing API
- The gateway provides one OpenAI- and Anthropic-compatible endpoint for models and subscriptions.manifest.build · 1 Oct 2026
- Fallbacks
- Manifest automatically retries on another provider when one provider goes down.manifest.build · 1 Oct 2026
- Autofix
- Autofix repairs malformed requests and resends them instead of failing on errors that retries cannot fix.manifest.build · 1 Oct 2026
- Observability
- The product shows what each harness spent, which models served requests, and what failed.manifest.build · 1 Oct 2026
- Integrations
- Manifest connects API keys, paid subscriptions, local models, and custom endpoints; named local integrations include Ollama, llama.cpp, and LM Studio.manifest.build · 1 Oct 2026
- Self-hosting
- The self-hosted gateway runs with Docker, works offline, requires no account, and supports amd64 and arm64.manifest.build · 1 Oct 2026
- Cloud limit
- The Cloud Free plan includes 10,000 routed requests per calendar month and cannot reach local models running on the user's machine.manifest.build · 1 Oct 2026
- Data residency
- For the self-hosted version, routing and request data stay on the customer's servers except for documented telemetry and Autofix flows.manifest.build · 1 Oct 2026
- Security
- Manifest states that data in transit uses TLS, passwords are hashed, and Gateway provider credentials are encrypted with AES-256-GCM.manifest.build · 1 Oct 2026
- Retention
- Cloud request recordings are retained for 7 days on Free and 365 days on Pro.manifest.build · 1 Oct 2026
- Support
- Free includes community support through Discord, Pro includes basic platform and billing support, and Enterprise includes dedicated Slack and email support.manifest.build · 1 Oct 2026
- Audience
- Manifest says its gateway helps AI builders, teams and startups, and platforms or providers create reliable agents and workflows and manage inference consumption.manifest.build · 1 Oct 2026
- Compliance
- The Enterprise plan lists HIPAA and custom BAAs, SSO/SAML, audit logs, custom retention, and a contractual uptime SLA.manifest.build · 1 Oct 2026
Best Manifest alternatives
See all 20Where it ranks on Inferse
- Best LLM Gateways in 2026#9 of 33
Sources
- manifest.build/about/· checked 1 Oct 2026
- manifest.build/llm-gateway/docs/introduction/· checked 1 Oct 2026
- manifest.build· checked 1 Oct 2026
- manifest.build/self-hosted/· checked 1 Oct 2026
- manifest.build/privacy/· checked 1 Oct 2026
- manifest.build/pricing/· checked 1 Oct 2026
- manifest.build/llm-gateway/· checked 1 Oct 2026


