TrueFoundry: Route, govern and observe AI traffic centrally
TrueFoundry is a Kubernetes-native AI infrastructure platform that provides an AI Gateway, MCP Gateway and deployment layer for LLM inference, fine-tuning, model serving, training and agent orchestration.
What is TrueFoundry?
TrueFoundry is a Kubernetes-native platform for running AI workloads. Its core is an AI Gateway that connects applications to model providers through one interface, handling routing, fallbacks, rate limits, cost controls and end-to-end observability. Separate gateways cover MCP servers and agent-to-agent communication, with centralized discovery, authentication, access control and tracing. Around the gateway sit deployment and governance features: model serving, fine-tuning, training, agent orchestration, role-based access control, SSO, audit logging and realtime guardrails. It can run in a VPC, on-premises, air-gapped or across multiple clouds, and the company states compliance with SOC 2, HIPAA and GDPR. Pricing starts with a free Developer tier, Pro at $25 per user per month, and custom Enterprise plans.
Focus areas: AI Gateway, Model Deployment.
Who is TrueFoundry for?
- Platform and MLOps teams running LLMs in production
- Data science teams deploying models across multiple clouds
- Enterprises needing governed access to models, tools and agents
How much does TrueFoundry cost?
TrueFoundry starts at $25/mo, read as a monthly price because the listing does not state the period. Always check the vendor’s own pricing page before you buy.
| Plan | Price | What you get |
|---|---|---|
| Developer | $0 | Up to 3 users, 10K requests & tool calls per user per month, 7-day log retention |
| Pro | $25 | Per user per month, unlimited users, 20K requests & tool calls per user per month, 30-day log retention |
| Enterprise | Custom | Annual commitment, custom log retention, VPC/on-prem, priority support and SLA |
Is TrueFoundry worth it?
A solid fit for teams that need one governed gateway and deployment layer across their AI stack
Where TrueFoundry is strong
- One gateway for LLM, MCP and agent traffic with routing, fallbacks and rate limits
- Deployment options include VPC, on-prem, air-gapped and multi-cloud
- Governance features such as RBAC, SSO, audit logging and realtime guardrails
Where it falls short
- Model provider charges and third-party guardrail usage are billed separately
- Agent Gateway and Agent Harness pricing is custom and not yet published
How do you get started with TrueFoundry?
- 01Sign up for the free Developer tier or start the live sandbox, which needs no credit card
- 02Connect model providers and MCP servers through the gateway and set routing and budget rules
- 03Add guardrails, roles and log retention settings, then move to Pro or Enterprise as usage grows
TrueFoundry: frequently asked questions
How much does TrueFoundry cost?
The Developer tier is free forever for up to 3 users with 10K requests and tool calls per user per month. Pro is $25 per user per month with 20K requests per user, and Enterprise is custom-priced on an annual commitment.
What counts as a request?
Each LLM request and each MCP tool call counts as one request. Retries and failed calls inside the gateway are not counted, and requests and tool calls count equally.
What happens if I exceed my included requests?
Overage is charged at $20 for every additional 100K requests. Seats and traffic are separate, so growing traffic does not require adding users.
Are model provider costs included?
No. Charges from model providers such as OpenAI, Anthropic, Google, Azure or AWS are billed separately, and managed external guardrail charges are also excluded.
TrueFoundry alternatives
The closest tools in our directory, matched on category, focus areas and audience.
| Tool | Best for | Free plan | Starting price | Focus areas |
|---|---|---|---|---|
| TrueFoundry | Teams centralizing LLM, MCP and agent traffic with governance | Yes | $25/mo | AI Gateway, Model Deployment |
| APIPark | Teams needing one open-source gateway for AI and API traffic | Unknown | — | AI Gateway |
| Higress | Teams centralizing LLM, Agent and MCP traffic behind one gateway | Unknown | — | AI Gateway, MCP |
| Orq | Teams governing many AI agents, models and tool calls | Unknown | — | AI Gateway, Guardrails |
| Portkey | Teams taking LLM apps to production with monitoring and control | Yes | $49/mo | AI Gateway, Guardrails, Prompt Management |
| Mistral AI | Teams needing controllable, self-hostable language models | Yes | $14.99/mo | — |
| Maxim AI | Teams centralising LLM access, cost control and observability | Yes | — | AI Gateway |
| Twelve Labs | Developers and media teams searching and analyzing large video libraries | Yes | — | — |
| Epigos AI | Epigos AI: simplifies AI computer vision model creation and deployment for businesses. | Yes | — | Model Deployment |
| Upstage AI | Teams automating document parsing and extraction with LLM APIs | No | $100/mo | — |
| Cohere | Enterprises needing private, controllable generative AI and retrieval | No | — | — |

