- Home
- LLM Gateway Software
- TrueFoundry AI Gateway
TrueFoundry AI Gateway
San Francisco, California, United States
What it is
TrueFoundry AI Gateway sits between applications and model providers, providing one API for managing AI model access, routing, governance, observability, security, and cost controls. The unified API supports chat, completion, embedding, and reranking models. TrueFoundry says it connects with 1,000+ large language models across 35+ platforms, including OpenAI, AWS Bedrock, Google Vertex AI, Azure OpenAI, and Anthropic. Routing can use latency, weighted load balancing, and automatic fallback to secondary models. The gateway records token usage, latency, errors, and request volumes, with centrally stored request and response logs. Teams can set rate limits, cost or token quotas, and role-based access controls. MCP connections include tools such as Slack, GitHub, Confluence, and Datadog, with OAuth2, RBAC, and metadata policies. Guardrails include PII filtering and toxicity detection. SaaS is available, while Enterprise also offers VPC, on-premises, and air-gapped deployment. Developer is free for up to three users and 10,000 requests per user monthly. Pro costs $25 a month per user; Enterprise pricing is custom.
For and against
For
- One API for several model types
- Connects with 1,000+ models across 35+ platforms
- Supports fallback and weighted routing
- Usage analytics and budget controls
- Self-hosted Enterprise deployment options
Against
- Developer plan limits requests per user
- Pro charges $20 per additional 100K requests
- Enterprise pricing is custom
- Advanced guardrails are plan-dependent
The verdict
TrueFoundry AI Gateway centralizes model access, routing, controls, and monitoring behind one interface. Its free Developer plan provides an entry point, while Pro and Enterprise add capacity, support, and deployment choices.
Who it suits
This gateway suits teams managing access to multiple AI models and providers. It is relevant to organizations needing routing, usage controls, observability, MCP tool connections, or private deployment options.
Plans and prices
Developer
3 users · universal API · model RBAC · virtual and self-hosted models
Read 15 Oct 2026 · g2.com
Pro
10 users · 1M monthly requests · configurable routing · rate limiting
Read 15 Oct 2026 · g2.com
Pro Plus
25 users · SSO · GDPR and HIPAA certificates · VPC and air-gapped deployment
Read 15 Oct 2026 · g2.com
TrueFoundry Pro (AWS Marketplace)
Enterprise AI Gateway plan · additional AWS infrastructure costs may apply
Read 15 Oct 2026 · aws.amazon.com
TrueFoundry Enterprise (AWS Marketplace)
Enterprise AI Gateway plan · additional AWS infrastructure costs may apply
Read 15 Oct 2026 · aws.amazon.com
TrueFoundry On-Prem (AWS Marketplace)
On-premises AI Gateway plan · additional AWS infrastructure costs may apply
Read 15 Oct 2026 · aws.amazon.com
Enterprise
10M+ monthly requests · dedicated onboarding · enterprise SLAs
Read 15 Oct 2026 · g2.com
On the record
- Access controls
- Teams can apply rate limits and cost or token quotas and use role-based access control to manage usage.truefoundry.com · read 4 Oct 2026
- API authentication
- The metrics API accepts Personal Access Tokens or admin-created Virtual Account Tokens.truefoundry.com · read 15 Oct 2026
- API surface
- The documentation exposes endpoints for chat, embeddings, reranking, responses, images, audio, batches, files, fine-tuning, moderation and model listing.truefoundry.com · read 15 Oct 2026
- Company
- TrueFoundry lists its address as Ensemble Labs Inc, 355 Bryant Street, Suite 403, San Francisco, California 94107.truefoundry.com · read 4 Oct 2026
- Company size and location
- LinkedIn lists TrueFoundry as privately held, headquartered in San Francisco, with 51–200 employees and a 2021 founding year.linkedin.com · read 15 Oct 2026
- Configuration extensibility
- Gateway policies can be managed in the UI or declared in YAML and applied through the TrueFoundry CLI for GitOps workflows.truefoundry.com · read 15 Oct 2026
- Cost controls
- Usage visibility, token tracking, quotas, budgets, rate limits, caching and batching are provided to control inference spend.truefoundry.com · read 15 Oct 2026
- Deployment
- The gateway supports SaaS and, for Enterprise, VPC, on-premises and air-gapped deployment options.truefoundry.com · read 4 Oct 2026
- Deployment options
- The product is offered as SaaS and can also run in a customer VPC, on premises or in an air-gapped environment.aws.amazon.com · read 15 Oct 2026
- Documentation depth
- The docs include provider catalogs, authentication, self-hosted model setup, metrics APIs and a large endpoint reference covering multiple media and model operations.truefoundry.com · read 15 Oct 2026
- Funding
- TrueFoundry announced a $19 million Series A led by Intel Capital, bringing reported total funding to $21 million.truefoundry.com · read 15 Oct 2026
- Guardrails
- Configurable input and output controls can filter PII, detect prompt injection, assess toxicity and apply organization-specific safety policies.truefoundry.com · read 15 Oct 2026
- Limit: documentation and RBAC
- G2 reviewers mention documentation lag or insufficient onboarding detail, missing edge-case examples and requests for stronger RBAC or deployment approvals.g2.com · read 15 Oct 2026
- Limit: outage communication
- Gartner reviewers repeatedly ask TrueFoundry to communicate its own downtime more proactively.gartner.com · read 15 Oct 2026
- Limit: pricing
- G2 pricing analysis reports that some small businesses and startups consider the paid tiers expensive, especially for enterprise and on-premises deployments.g2.com · read 15 Oct 2026
- MCP integrations
- Native MCP support connects tools such as Slack, GitHub, Confluence and Datadog, with OAuth2, RBAC and metadata policies on tool calls.truefoundry.com · read 15 Oct 2026
- Microsoft Marketplace availability
- TrueFoundry AI Gateway is listed in Microsoft Marketplace as an Azure product for governed, observable AI-agent deployment.marketplace.microsoft.com · read 15 Oct 2026
- Model coverage
- TrueFoundry says the gateway connects more than 1,600 models, while its provider documentation lists integrations across more than 35 platforms and over 1,000 LLMs.truefoundry.com · read 15 Oct 2026
