Comet From $19/mo · Free plan 9.3 Visit TrueFoundry AI Gateway
truefoundry.com
What it is
TrueFoundry AI Gateway sits between applications and model providers to manage model access, routing, governance, observability, security, and cost controls. Its unified API supports chat, completion, embedding, and reranking models. TrueFoundry says the gateway connects to more than 1,000 LLMs across more than 35 platforms, including OpenAI, AWS Bedrock, Google Vertex AI, Azure OpenAI, and Anthropic. Routing options include latency-based selection, weighted load balancing, and automatic fallbacks. The service tracks token usage, latency, errors, and request volumes, and supports centrally stored request and response logs. Teams can set rate limits and cost or token quotas, with role-based access controls. MCP connections include tools such as Slack, GitHub, Confluence, and Datadog, with policies for tool calls. Deployment includes SaaS, with VPC, on-premises, and air-gapped options for Enterprise. Developer is free; Pro costs $25 a month, billed per user. Developer includes 10,000 requests per user monthly, while Pro includes 20,000 and charges $20 per additional 100,000 requests.
Spec sheet
- What it does
- TrueFoundry AI Gateway is a control layer that connects applications to models, tools and agents while centralizing routing, governance, observability and cost controls.Read 15 Oct 2026 · truefoundry.com
- Purpose
- TrueFoundry AI Gateway sits between applications and model providers to manage AI model access, routing, governance, observability, security and cost controls.Read 4 Oct 2026 · truefoundry.com
- Deployment
- The gateway supports SaaS and, for Enterprise, VPC, on-premises and air-gapped deployment options.Read 4 Oct 2026 · truefoundry.com
- Privacy
- TrueFoundry says that when deployed in VPC, on-premises or air-gapped environments, sensitive data can remain within enterprise boundaries.Read 4 Oct 2026 · truefoundry.com
- Support
- The listed support options are an in-app chatbot and Discord for Developer, a support portal for Pro, and priority support, SLA and a dedicated Slack channel for Enterprise.Read 4 Oct 2026 · truefoundry.com
- Headquarters
- San Francisco, California, United StatesRead 23 Sep 2026 · truefoundry.com
- Founded
- TrueFoundry states it was founded in 2021 by Nikunj Bajaj, Abhishek Choudhary and Anuraag Gutgutia.Read 4 Oct 2026 · truefoundry.com
- Company
- TrueFoundry lists its address as Ensemble Labs Inc, 355 Bryant Street, Suite 403, San Francisco, California 94107.Read 4 Oct 2026 · truefoundry.com
- Access controls
- Teams can apply rate limits and cost or token quotas and use role-based access control to manage usage.Read 4 Oct 2026 · truefoundry.com
- API authentication
- The metrics API accepts Personal Access Tokens or admin-created Virtual Account Tokens.Read 15 Oct 2026 · truefoundry.com
- API surface
- The documentation exposes endpoints for chat, embeddings, reranking, responses, images, audio, batches, files, fine-tuning, moderation and model listing.Read 15 Oct 2026 · truefoundry.com
- Company size and location
- LinkedIn lists TrueFoundry as privately held, headquartered in San Francisco, with 51–200 employees and a 2021 founding year.Read 15 Oct 2026 · linkedin.com
- Configuration extensibility
- Gateway policies can be managed in the UI or declared in YAML and applied through the TrueFoundry CLI for GitOps workflows.Read 15 Oct 2026 · truefoundry.com
- Cost controls
- Usage visibility, token tracking, quotas, budgets, rate limits, caching and batching are provided to control inference spend.Read 15 Oct 2026 · truefoundry.com
- Deployment options
- The product is offered as SaaS and can also run in a customer VPC, on premises or in an air-gapped environment.Read 15 Oct 2026 · aws.amazon.com
- 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.Read 15 Oct 2026 · truefoundry.com
- Funding
- TrueFoundry announced a $19 million Series A led by Intel Capital, bringing reported total funding to $21 million.Read 15 Oct 2026 · truefoundry.com
- Guardrails
- Configurable input and output controls can filter PII, detect prompt injection, assess toxicity and apply organization-specific safety policies.Read 15 Oct 2026 · truefoundry.com
- 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.Read 15 Oct 2026 · g2.com
- Limit: outage communication
- Gartner reviewers repeatedly ask TrueFoundry to communicate its own downtime more proactively.Read 15 Oct 2026 · gartner.com
- Limit: pricing
- G2 pricing analysis reports that some small businesses and startups consider the paid tiers expensive, especially for enterprise and on-premises deployments.Read 15 Oct 2026 · g2.com
- MCP integrations
- Native MCP support connects tools such as Slack, GitHub, Confluence and Datadog, with OAuth2, RBAC and metadata policies on tool calls.Read 15 Oct 2026 · truefoundry.com
- Microsoft Marketplace availability
- TrueFoundry AI Gateway is listed in Microsoft Marketplace as an Azure product for governed, observable AI-agent deployment.Read 15 Oct 2026 · marketplace.microsoft.com
- 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.Read 15 Oct 2026 · truefoundry.com
- Model providers
- TrueFoundry says the gateway integrates with 1,000+ LLMs across 35+ platforms, including OpenAI, AWS Bedrock, Google Vertex AI, Azure OpenAI and Anthropic.Read 4 Oct 2026 · truefoundry.com
- Notable news
- TrueFoundry announced TrueFailover in January 2026 to reroute enterprise AI traffic automatically during model-provider outages.Read 15 Oct 2026 · truefoundry.com
- Observability
- Monitoring covers requests, tokens, cost, latency percentiles, time to first token, inter-token latency and request-level traces.Read 15 Oct 2026 · truefoundry.com
- Praise: deployment and governance
- G2 reviewers praise one-click deployment, centralized infrastructure and governance, observability, routing and reduced DevOps work.Read 15 Oct 2026 · g2.com
- Praise: VPC governance
- Gartner reviewers praise VPC or on-premises deployment, a unified API, rate limiting, guardrails, cost tracking and responsive support.Read 15 Oct 2026 · gartner.com
- Rating on AWS Marketplace
- 4.6 out of 5 from 65 ratingsRead 15 Oct 2026 · aws.amazon.com
- Rating on G2
- 4.6 out of 5 from 59 reviewsRead 15 Oct 2026 · g2.com
- Rating on Gartner Peer Insights
- 4.8 out of 5 from 249 reviewsRead 15 Oct 2026 · gartner.com
- Routing
- The gateway supports latency-based routing, weighted load balancing and automatic fallbacks to secondary models.Read 4 Oct 2026 · truefoundry.com
- Routing and failover
- Requests can be load-balanced by weights, latency or priority, with fallback chains for provider errors and timeouts.Read 15 Oct 2026 · truefoundry.com
- SDKs
- A public Python gateway SDK supports synchronous and asynchronous clients, streaming agent responses over Server-Sent Events, retries, pagination and custom clients.Read 15 Oct 2026 · github.com
- Security claims
- TrueFoundry states SOC 2, HIPAA and GDPR compliance and supports RBAC, OAuth2, API-key authentication and auditability.Read 15 Oct 2026 · aws.amazon.com
- Self-hosted models
- External or self-hosted models can be registered by endpoint URL and authentication data and then use gateway routing, guardrails, rate limits, cost tracking and observability.Read 15 Oct 2026 · truefoundry.com
- Supported operations
- The gateway supports chat, completion, embedding and reranking model types.Read 15 Oct 2026 · truefoundry.com
- Unified API
- The gateway presents one API and key pattern across OpenAI, Anthropic, Bedrock, self-hosted models and other providers.Read 15 Oct 2026 · truefoundry.com
- Usage limits
- Developer includes 10,000 AI Gateway requests per user per month, while Pro includes 20,000 per user per month and charges $20 per additional 100,000 requests.Read 4 Oct 2026 · truefoundry.com
Plans and prices
Developer Free Up to 3 users · 10k requests/user/month · 5 model accounts · 5 MCP servers Read 4 Oct 2026 · truefoundry.com
Developer Free Free 3 users · universal API · model RBAC · virtual and self-hosted models · playground Read 15 Oct 2026 · g2.com
Pro $25 a month per user No user limit · 20k requests/user/month · $20 per additional 100K requests Read 4 Oct 2026 · truefoundry.com
Pro $499 a month $499/month 10 users · 1M monthly requests · configurable routing · rate limiting · up to 25 MCP servers Read 15 Oct 2026 · g2.com
Pro Plus $2,999 a month $2,999/month 25 users · SSO · GDPR and HIPAA certificates · VPC and air-gapped deployment · data-lake export Read 15 Oct 2026 · g2.com
TrueFoundry Pro (AWS Marketplace) $6,250 a month 1-month contract Enterprise AI Gateway plan · additional AWS infrastructure costs may apply Read 15 Oct 2026 · aws.amazon.com
TrueFoundry Enterprise (AWS Marketplace) $12,500 a month 1-month contract Enterprise AI Gateway plan · additional AWS infrastructure costs may apply Read 15 Oct 2026 · aws.amazon.com
TrueFoundry On-Prem (AWS Marketplace) $16,666.66 a month 1-month contract On-premises AI Gateway plan · additional AWS infrastructure costs may apply Read 15 Oct 2026 · aws.amazon.com
Enterprise Priced on request Contact Us 10M+ monthly requests · dedicated onboarding · enterprise SLAs Read 15 Oct 2026 · g2.com
Strong points and limits
Strong points
- One API supports four model types.
- Offers latency routing and automatic fallbacks.
- Tracks token use, latency, errors, and volumes.
- Supports quotas, rate limits, and role-based access.
- Self-hosted deployment options are listed.
Limits
- Developer is limited to 10,000 requests per user monthly.
- Pro costs $25 a month per user.
- Enterprise pricing is custom.
Who it suits
It suits teams that need a common interface for model access, routing, usage monitoring, and controls. Enterprise deployment options are listed for organizations requiring VPC, on-premises, or air-gapped hosting.
Verdict
The gateway specifies model access, routing, monitoring, and usage controls, with SaaS and Enterprise deployment choices. The free Developer plan has request and account limits; Pro is billed per user.
Where Specifiction places it
- Model Registry Software#4 of 368.6
- Model registries#5 of 389.1
- Byok System#4 of 248.6
- LLM gateways#6 of 338.9
- LLM Gateway Software#7 of 348.7
