Join the AI Security Webinar with Palo Alto. Register here

code
Developer

For explorers and early builders experimenting with AI workflows. Ideal for prototyping, testing ideas, and getting started without friction.

$ 0 / month
Get Started
arrow1
code
Pro*

For small teams ready to ship real AI features with usage-based predictability. Unlocks higher limits, better performance, and essential governance tools.

$ 499/ month
Get Started
arrow1
code
Enterprise

For medium and large organizations running AI at scale with strict compliance. Built for advanced governance, security, custom deployment, and mission-critical reliability.

Custom
Contact sales
arrow1

Features

Full Feature Comparision Between All Plans
Plans
code
Developer
code
Pro*
code
Enterprise
Requests per month
50k
1M
Custom
10M Plus per month
Users
3
10
Custom
AI Gateway
Universal API
RBAC on models
Virtual models
infinity
Self-hosted models
Playground
Multiple gateway endpoints
infinity
infinity
Simple caching
infinity
Semantic Caching
infinity
Control Center
Weight-based Routing
infinity
Latency-based Routing
infinity
Priority-based Routing
infinity
Fallbacks
infinity
With advanced features
Budget limiting
infinity
Rate limiting
infinity
Observability
Logs
With custom retention
Traces
Export to custom storage buckets
Feedback on traces
infinity
infinity
Custom Metadata
Custom pricing / model
infinity
Cost per team/user / model/application
infinity
Metadata filtering
infinity
Alerts
infinity
infinity
Export to other monitoring platforms
infinity
infinity
MCP Gateway
MCP Servers
Register up to 5
Register up to 25
Custom
Tool calls per month
50K
1M
Custom
RBAC on MCPs
Virtual MCP Servers
infinity
infinity
Metrics
Comprehensive
Logs
Support for advanced authentication
Self-hosted MCPs
Prompt Management
Number of saved prompts
Up to 10
Unlimited
Unlimited
Versioning & Variables
Guardrails
Partner Guardrails integration
infinity
Custom Guardrail Hooks
infinity
infinity
Security & Authentication
Role based access control
infinity
SSO
infinity
infinity
SOC2
GDPR, HIPAA Compliance Certificates
infinity
Org management
infinity
infinity
Audit logs
infinity
infinity
Deployment modes
SaaS
VPC / On-prem
infinity
infinity
Air-gapped deployment
infinity
infinity
Deployment customization
Data Lake Export
infinity
infinity
Connect multiple storage bucket
infinity
infinity
Multiple gateway planes
infinity
infinity
Gitops (Infrastructure as code)
Support
Support
Community Support
Production Support
Priority Support
Dedicated Onboarding
SLA
Standard SLA
Enterprise-Grade SLA
For AI Deployment Pricing
Contact sales
arrow1

Why

TrueFoundry makes your ML team 10x faster

50 %

Faster Experimentation

Improving your ML Team’s Productivity

15 min

to Productionisation

Instead of 4-8 weeks it takes in most companies

0 min

Monitoring Set-up

For both System and ML level Metrics

0 min

Faster Feedback Loop

Enabling quick iteration on ML Models

Testimonials

Why Enterprises Choose TrueFoundry

Pratik Agarwal
Sr. Director, Data Science & AI Innovation

TrueFoundry’s AI Gateway gave us a unified layer to manage model access, routing, guardrails, and cost controls across teams. It has accelerated productionization, increased visibility into spend and performance, and enabled us to scale AI experimentation safely across the organization.

Vibhas Gejji
Staff ML Engineer

With TrueFoundry’s AI Gateway, we finally have one consistent interface for all model providers, policies, and telemetry. It eliminated the overhead of managing keys, routing logic, and scattered observability. Introducing new models is now just configuration. The Gateway has improved developer velocity, reduced DevOps burden, and helped us operate multimodel systems with real-time insights and governance.

Indroneel G.
Intelligent Process Leader

TrueFoundry’s AI Gateway standardized how every team interacts with LLMs, embeddings, and RAG components. Instead of scattered integrations, we now control access, routing policies, and safety guardrails centrally. The ability to optimize for cost or latency without changing applications has been a game-changer. It’s made our AI architecture cleaner, more secure, and far easier to scale.

Nilav Ghosh
Senior Director, AI

TrueFoundry’s AI Gateway has become our control layer for safe, governed AI adoption. It consolidates security, observability, and model usage policies into one place, giving us full visibility into performance and spend. Developers get a consistent interface across clouds and models, while leadership gets governance and predictability. It has meaningfully reduced friction in scaling enterprise AI.

FAQs

Frequently asked Questions and their Answers

What happens if I exceed my request limits?

You’ll simply be billed for additional usage at transparent, per-unit rates. 2M requests and 5 API keys for additional $499 per month.

Do you support on-prem or VPC deployments?

Yes, Enterprise supports full VPC and air-gapped installations for both control and gateway planes.

Do you support multi-region deployments?

Yes, Enterprise plans can run workloads across regions for redundancy and performance. SaaS is already deployed with a globally distributed architecture. For on-prem/VPC deployment, we support multi-region deployment in the enterprise tier.

How TrueFoundry differentiates between pricing tiers?

Tiers are determined by usage, number of signed-up users on the TrueFoundry platform, and the depth of the offering (AI Gateway, MCP Gateway, etc.). TrueFoundry is the only platform that provides this level of capability. Pricing is based on usage (requests processed/users) and the level of customization required.

If you’re experimenting individually or exploring basic ideas, choose Developer.If you’re a small team that needs predictable, usage-based scalability, choose Pro for higher limits, better performance, and essential governance. If you’re a medium or large organization running AI at scale with strict compliance needs and deep customization, choose Enterprise.

What are the deployment options?

1. AI Gateway SaaS only
2. SaaS AI Gateway with data storage on your own infrastructure
3. Gateway Plane only
4. Control Plane + Gateway Plane

Will I have to bear additional infrastructure costs?

If you use the fully managed SaaS version of the AI Gateway, there are no hosting costs (only your own storage if you choose to store data on your infra). Hosting costs apply only when you choose to self-host the Gateway or both the Control and Gateway planes (~$600–$1,000/month).

Do you support enterprise-grade organization management?

Yes. We support full org-level management, including creating multiple tenants, managing accounts and teams, and enforcing granular role based access control(RBAC) on both Personal Access Tokens and System Tokens.

What’s the difference between the Standard SLA and the Enterprise SLA?

The Standard SLA typically offers a 24–48 hour response time, while the Enterprise SLA provides customizable response times and support levels based on the customer’s needs and premium tier.