TF
TrueFoundry AI Gateway
Enterprise AI gateway with private and self-hosted deployment
Enterprise AI gatewayResearch complete
Company overview
TrueFoundry's AI gateway combines guardrails, caching, routing and usage visibility with deployment inside a customer's own cloud, aimed at enterprises that cannot send prompts to a third-party SaaS.
Ideal customer: Regulated enterprises and platform teams with data-residency constraints
- Running an AI gateway in a private cloud or VPC
- Guardrails on sensitive data in prompts
- Caching and routing across internal and external models
GateYourAI verdict
TrueFoundry's differentiator is deployment posture: gateway capability inside the customer's own environment. That matters for organisations where prompt content itself is the regulated asset. Capability marks await documentation verification.
Best for: Enterprises that need gateway capabilities inside their own cloud boundary. Read how we assess platforms.
Security capabilities
A capability is marked available only when an official page or documentation says so. “Not publicly documented” means we could not find it — not that the vendor lacks it.
| Capability | Status | Verification | Source |
|---|---|---|---|
| Prompt-injection detectionIdentifies attempts to override system instructions in prompts or tool output.Listed among gateway guardrails. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Prompt-injection blockingBlocks the request before it reaches the model, rather than only logging it.Guardrails can block requests inline. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Jailbreak detectionDetects known jailbreak and guardrail-evasion patterns. | Verification pendingVerification pending. Verification pending. | Verification pending | — |
| PII detectionIdentifies personal information in prompts or responses. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| PII redactionMasks or removes personal information before it leaves the gateway.PII can be masked before the request leaves the gateway. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Secret & credential scanningDetects API keys, tokens and credentials in prompts or output. | Verification pendingVerification pending. Verification pending. | Verification pending | — |
| Input inspectionInspects outbound requests before they reach the model. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Output inspectionInspects inbound model responses before they reach the application. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Content moderationClassifies harmful or policy-violating content. Not equivalent to injection defense. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Policy enforcementConfigurable rules applied per route, team, key or environment.Guardrail policies are attached per team, model or route. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Agent & tool controlsConstrains tool calls, autonomous actions and agent permissions.Tool and agent access is governed through the gateway. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| MCP securityControls or inspects Model Context Protocol server traffic.MCP server registry and governed tool access. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Audit logsDurable, reviewable record of requests and policy decisions. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Access controlsRoles, teams, keys and scoped permissions.RBAC across teams and environments. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
Cost-optimization capabilities
Token reduction, avoided calls, cheaper-model routing, budgets and reporting are tracked separately because they are not interchangeable.
| Capability | Status | Verification | Source |
|---|---|---|---|
| Prompt compressionReduces the number of tokens actually sent to the model. | Not publicly documentedNot publicly documented. Not publicly documented. | Not publicly documented | — |
| Exact cachingReturns a stored response for a byte-identical request. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Semantic cachingReturns a stored response for a semantically similar request using embeddings.Caching is documented; semantic matching not explicitly stated. | LimitedLimited. Partially documented. | Partially documented | TrueFoundry AI Gateway product page |
| Intelligent model routingChooses a model per request based on task, cost or performance. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Automatic fallbackRetries against an alternate model or provider on failure. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Load balancingDistributes traffic across keys, regions or providers. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Token budgetsHard or soft limits expressed in tokens. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Dollar budgetsSpending limits expressed in currency.Budget limits per team and per use case. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Rate limitsRequest throttling. Throttling is not the same as token reduction. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Cost attributionAttributes spend to teams, keys, users or features.Spend attributed to teams, users and models. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Cost analyticsDashboards and reporting on token and dollar usage. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Savings reportingReports the spend avoided by compression, caching or routing. | Verification pendingVerification pending. Verification pending. | Verification pending | — |
Supported models and deployment options
Self-hosted and private-cloud deployment advertised. Verification pending.
| Capability | Status | Verification | Source |
|---|---|---|---|
| OpenAISupports OpenAI models. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| AnthropicSupports Anthropic models. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Google GeminiSupports Google Gemini models. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| AWS BedrockSupports AWS Bedrock as a provider. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Azure OpenAISupports Azure OpenAI deployments. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Open-source modelsSupports open-weight models or self-hosted inference endpoints. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| SaaS deploymentVendor-hosted managed service. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| VPC / private cloudDeployable inside a customer cloud account. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| On-premiseDeployable in a customer data centre.On-premise and air-gapped deployment are advertised. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Self-hostedCustomer runs and operates the gateway themselves. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| Open-source optionSource code published under an open-source licence. | Verification pendingVerification pending. Verification pending. | Verification pending | — |
| APIProgrammatic API for configuration or traffic. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
| SDKOfficial client libraries. | AvailableAvailable. Verified from official product page. | Verified from official product page | TrueFoundry AI Gateway product page |
Pricing status
Verification pending.
| Capability | Status | Verification | Source |
|---|---|---|---|
| Public pricingList pricing published on the vendor website. | Verification pendingVerification pending. Verification pending. | Verification pending | — |
| Free tierA permanently free usage tier. | Verification pendingVerification pending. Verification pending. | Verification pending | — |
| Free trialA time-limited or credit-limited trial. | Verification pendingVerification pending. Verification pending. | Verification pending | — |
| Enterprise planA named enterprise tier. | Verification pendingVerification pending. Verification pending. | Verification pending | — |
| Contact sales requiredPricing requires contacting the vendor. | Verification pendingVerification pending. Verification pending. | Verification pending | — |
Strengths
- Private-cloud and self-hosted deployment are central to the product
- Covers both guardrails and cost controls in one layer
Limitations
- Per-feature verification is still queued
- Pricing detail not yet verified
Alternatives to TrueFoundry AI Gateway
PortkeyTeams that want an open-source gateway with guardrails and spend controlsKong AI GatewayPlatform teams already running Kong that want AI policy in the same data planeConstellation Gate AITeams running coding agents that want prompt security and token reduction in one hop
You can also compare TrueFoundry AI Gateway against up to three other platforms, or read the AI Gate pillar page.
Sources
- TrueFoundry AI Gateway product page TrueFoundry · Official product page · Accessed 2026-07-30
- TrueFoundry AI Gateway quick start TrueFoundry · Official documentation · Accessed 2026-07-30Primary source of truth for capability marks.
Last reviewed: 2026-07-30
Newsletter
The AI Gateway Brief
A weekly briefing on AI security threats, gateway technology, token economics, model routing, and the infrastructure controlling enterprise AI.