LLM Gateway
8.2#4 in llm gatewaysFree planFree planWebAPIExtensionLinux
Visit| Fact | LLM Gateway | Manifest |
|---|---|---|
| Company size | LinkedIn classifies llm-gateway as a self-employed information-services organization with 2–10 employees. | LinkedIn lists Manifest as a 2–10 employee software-development company. |
| Documentation depth | The documentation includes feature guides, dashboard knowledge-base articles, integration material, self-hosting sections, developer tools and an API reference. | The documentation includes installation, first-request examples, provider setup, environment variables, CLI guidance and deployment paths. |
| Integrations | Published integration guides cover Claude Code, Cursor, Cline, n8n, VS Code, Codex CLI, OpenCode, Continue, Kilo Code, Kimi Code and other coding tools. | Manifest connects API keys, paid subscriptions, local models, and custom endpoints; named local integrations include Ollama, llama.cpp, and LM Studio. |
| Licence | The core gateway, dashboard, API and worker are released under AGPLv3, while code in the ee directory has commercial licensing. | The repository publishes the software under the MIT licence. |
| Observability | Dashboards expose requests, tokens, latency, errors, cache status and spending broken down by model, provider, project and API key. | Usage views show spending, selected models, token consumption and failed requests for each harness. |
| Product | LLM Gateway provides one OpenAI-compatible API to route requests across 250+ models from 40+ providers. | Manifest is an open-source LLM gateway that routes requests, provides fallbacks, repairs failing requests with Autofix, and tracks spending. |
| Provider coverage | The service advertises more than 40 providers and over 250 models, including OpenAI, Anthropic, Google, AWS Bedrock, Azure, Mistral and DeepSeek. | The public repository lists 35 built-in provider connections, 18 subscription flows, 300-plus models and custom OpenAI- or Anthropic-compatible endpoints. |
| SDK compatibility | The product supports existing OpenAI SDKs, cURL, any programming language and a dedicated AI SDK provider package. | Because the API is OpenAI-compatible, existing OpenAI-style SDKs and agents can point at Manifest by changing the base URL. |
| Security | The company states that it is SOC 2 Type II audited and GDPR-aligned, and describes TLS in transit and AES-256 encryption at rest. | Manifest states that data in transit uses TLS, passwords are hashed, and Gateway provider credentials are encrypted with AES-256-GCM. |
LLM Gateway suits product and platform teams routing application requests to multiple model providers. Organizations deploying LLM infrastructure across teams may consider its enterprise identity, guardrail, and support options.
Manifest suits AI builders, teams, startups, and platforms or providers that need to route model requests and track inference use. Self-hosting may suit users who want an offline gateway without an account.