How much does TrueFoundry cost?

Free Developer tier for up to 3 users with 10K requests per user per month. Pro is $25 per user per month with 20K requests and MCP tool calls per user included and $15 per additional 100K. Enterprise is custom, with VPC, on-prem and air-gapped deployment, data residency and SLAs. Agent Gateway and Agent Harness are custom priced for now. Model-provider charges are billed separately.

What are the best alternatives to TrueFoundry?

Based on documented capability coverage across the Agentic Index 14 point taxonomy, the closest alternatives to TrueFoundry among agent infrastructure platforms are Composio, OpenRouter, Braintrust, LangWatch. Each is graded on the same public evidence, and no vendor pays for placement.

Does TrueFoundry support MCP and tool calling?

Full under the Agentic Index verification standard. TrueFoundry publishes public evidence of Model Context Protocol (MCP) support, tool calling, and API or SDK extensibility for connecting agents to external tools. Evidence basis: TrueFoundry publishes an API reference and OpenAPI specifications for the platform and the AI Gateway, a Python SDK and a CLI, and the gateway playground generates integration code for the OpenAI SDK, the REST API and cURL; agents built in. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Does TrueFoundry have SOC 2, SSO and role based access control?

Full under the Agentic Index verification standard. TrueFoundry publishes public evidence of enterprise security and identity controls, covering a compliance posture such as SOC 2 or ISO 27001, single sign on (SSO or SAML), and role based access control (RBAC). Evidence basis: TrueFoundry SaaS maintains SOC 2 Type II, GDPR and HIPAA programs, with reports and trust documentation at trust.truefoundry.com, and customers get single sign-on over SAML or OIDC with SCIM provisioning, role-based access control across us. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Can TrueFoundry be self hosted or run in a private VPC?

Full under the Agentic Index verification standard. TrueFoundry publishes public evidence of self hosted or private VPC deployment, along with data residency options for controlling where agent data is processed and stored. Evidence basis: On TrueFoundry's managed SaaS the customer chooses the region the AI Gateway is deployed in and where request logs and traces are stored, and can bring its own Amazon S3, Azure Blob or Google Cloud Storage so logs and traces stay in its own. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Back to vendors

TrueFoundry

Also known as: TrueFoundry AI Gateway

Visit site

Agent infrastructureindependentVerified 2026-09-21

Entry priceFree Developer tier; Pro $25/user/mo; Enterprise contact salesFull pricing detail

Enterprise AI gateway for LLMs, MCP servers and agents, with a hosted agent harness, deployable as SaaS, VPC, on-prem or air-gapped.

TrueFoundry is an enterprise AI gateway for LLMs, MCP servers and agents. Its AI Gateway puts every enabled model provider behind one endpoint with role-based model access, per-user and per-team budgets and rate limits, content guardrails, and virtual models that back one logical name with several models for routing and failover. The MCP Gateway registers MCP servers centrally, holds their credentials, runs per-user OAuth, and pauses tools flagged as destructive for human approval before they run.

The platform also hosts an agent harness, TrueForge, TrueFoundry's open-source harness embedded unchanged and built from the platform sidebar. Agents built there draw on gateway models, MCP tools and a versioned Skills Registry, delegate subtasks to subagents, run code in an isolated sandbox, and pause for human checkpoints. Every agent session is traced with cost, tokens, tool calls and a turn-by-turn transcript, alongside gateway request logs, OpenTelemetry export and audit logging.

TrueFoundry runs as managed SaaS, where customers choose the region and can bring their own log storage, or self-hosted on AWS, GCP, Azure, OpenShift or on-prem, with VPC and air-gapped deployment on the Enterprise plan. The managed service holds SOC 2 Type II, GDPR and HIPAA programs with reports at its trust site, and supports SAML or OIDC single sign-on with SCIM provisioning. Pricing starts with a free Developer tier; Pro is $25 per user per month with a gateway request allowance and usage-based overage, and Enterprise is custom.

Vendor details

Canonical URL

https://www.truefoundry.com

Subcategory

LLM gateway and routing

Funding status

Independent.

Company status

independent

Use cases & customers

Primary use cases

enterprise LLM gatewayMCP tool governancemodel routing and failoverhosted agent harness

Target customers

enterpriseplatform teams

Deployment options

SaaSVPCon-premself-hostedair-gapped

Integrations

One AI Gateway endpoint across model providers, with virtual models for routing and failover and generated code for the OpenAI SDK, LangChain, LangGraph, Google ADK, LlamaIndex, the REST API and cURL. The MCP Gateway registers MCP servers centrally, holds credentials, runs per-user OAuth and pauses tools flagged as destructive for approval. Platform integrations cover GitHub, GitLab, Bitbucket, Slack, Microsoft Teams, PagerDuty and HashiCorp Vault.

In practice

Your enterprise needs one governed endpoint for every model provider. TrueFoundry's AI Gateway puts every enabled model behind one endpoint with role-based access, budgets, rate limits and guardrails, and virtual models handle routing and failover.

Your agents call internal tools and you cannot share credentials. The MCP Gateway holds credentials, runs per-user OAuth, and pauses tools flagged as destructive for a person's approval.

Regulation requires data to stay in your environment. You run TrueFoundry self-hosted, on-prem or air-gapped, or pick the SaaS region and bring your own storage for logs and traces.

Sources & related URLs

Research sources

https://www.truefoundry.com https://www.truefoundry.com/pricing https://www.truefoundry.com/docs/llms.txt https://www.truefoundry.com/docs/platform/saas-security https://www.truefoundry.com/docs/agent-platform/agent-harness/overview

Agentic Index coverage score

9.5 / 14 capabilities · 68%

Integrations & Tool Calling	Full
MCP servers registered in TrueFoundry's MCP Gateway are listed in the agent builder, where the customer picks the individual tools each agent sees; the gateway holds the credentials, runs per-user OAuth flows and refreshes tokens, and in the gateway playground a model uses a connected MCP server to act on outside systems such as a calendar or a database. That is tool-calling into external systems through a governed tool layer. Sourcetruefoundry.com/docs/agent-platform/agent-harness/what-truefoundry-addsread 2026-09-21
Workflow Orchestration	Partial
Planning, tool calls, context management, approvals and state all run in the agent's execution loop inside TrueFoundry's hosted agent harness, which delegates focused subtasks to parallel subagents and can chain MCP tool calls in a single sandbox script. That orchestrates autonomous agent steps. No deterministic workflow nodes, branching or retry paths that a run can combine with those steps are described. Sourcetruefoundry.com/docs/agent-platform/agent-harness/overviewread 2026-09-21
Knowledge Grounding & RAG	Not documented
Chat, embedding and rerank model calls route through TrueFoundry's AI Gateway, so a customer can run its own retrieval through the gateway, but no document ingestion, index or retrieval layer that TrueFoundry maintains over the customer's content is described. The Skills Registry holds versioned skills, not the customer's documents. Sourcetruefoundry.com/docs/ai-gateway/playground-overviewread 2026-09-21
Human Oversight & Guardrails	Full
Tools flagged as destructive at TrueFoundry's MCP Gateway automatically pause for human approval in every agent, and the hosted agent harness's human checkpoints pause a run for tool approval or ask the user a structured question before it continues. The gate is shipped, and it holds the agent's action until a person decides. Sourcetruefoundry.com/docs/agent-platform/agent-harness/what-truefoundry-addsread 2026-09-21
Security, Identity & Governance	Full
TrueFoundry SaaS maintains SOC 2 Type II, GDPR and HIPAA programs, with reports and trust documentation at trust.truefoundry.com, and customers get single sign-on over SAML or OIDC with SCIM provisioning, role-based access control across users, teams and virtual accounts, and personal and application tokens with lifetime and rotation controls. Sourcetruefoundry.com/docs/platform/saas-securityread 2026-09-21
Observability & Auditability	Full
Every agent session on TrueFoundry is captured with cost, tokens, turns, tool calls and a turn-by-turn transcript, with traces per run covering model calls, tool calls, sandbox executions and subagents, and it inherits the AI Gateway's request logs, analytics, OpenTelemetry export and Prometheus and Grafana. Audit logging of platform activity is available by dashboard and API, and request logs and traces follow the retention the customer configures. That shows what the agent did step by step, with an audit trail separate from runtime traces. Sourcetruefoundry.com/docs/agent-platform/agent-harness/what-truefoundry-addsread 2026-09-21
Memory & State Persistence	Partial
Agent state and context are managed by TrueFoundry's hosted agent harness, which keeps sessions in the platform under the organization's access control and summarizes older history when context nears the model's limit. That is session memory scoped by the platform's access control. No long term memory layer, and no way to review, edit or delete what an agent remembers, is described. Sourcetruefoundry.com/docs/agent-platform/agent-harness/overviewread 2026-09-21
Deployment & Data Residency	Full
On TrueFoundry's managed SaaS the customer chooses the region the AI Gateway is deployed in and where request logs and traces are stored, and can bring its own Amazon S3, Azure Blob or Google Cloud Storage so logs and traces stay in its own buckets. The control plane and gateway also install self-hosted on AWS, GCP, Azure, OpenShift or on-prem, and the Enterprise plan lists VPC, on-prem and air-gapped deployment. That is a documented region selection surface plus customer environment options. Sourcetruefoundry.com/docs/platform/saas-securityread 2026-09-21
Prebuilt Agents, Templates & Packs	Not documented
Agents draw on a versioned catalog of skills in TrueFoundry's Skills Registry, and its Agent Registry records the customer's own agents; neither is a catalog of prebuilt agents a buyer adopts, and TrueFoundry publishes no agent templates or packaged agents. Saved prompts serve as the customer's own templates. Sourcetruefoundry.com/docs/llms.txtread 2026-09-21
Triggers & Channel Coverage	Full
Agents, sessions and schedules live in the platform through TrueFoundry's hosted agent harness, shared with the organization under the same authentication and access control as the rest of TrueFoundry. A schedule sends work to an agent without a person starting it. Sourcetruefoundry.com/docs/agent-platform/agent-harness/what-truefoundry-addsread 2026-09-21
Model Flexibility & Routing	Full
Every model enabled for a user in TrueFoundry's AI Gateway appears in the agent builder's model picker, grouped by provider, and switching models is a one-click change; the gateway playground lets teams browse and select chat, embedding, rerank and image models across providers, and virtual models back one logical name with several models for routing and failover. The customer chooses the model and the provider. Sourcetruefoundry.com/docs/agent-platform/agent-harness/what-truefoundry-addsread 2026-09-21
APIs, SDKs & MCP Extensibility	Full
TrueFoundry publishes an API reference and OpenAPI specifications for the platform and the AI Gateway, a Python SDK and a CLI, and the gateway playground generates integration code for the OpenAI SDK, the REST API and cURL; agents built in the hosted harness are reachable through its HTTP API and TypeScript SDK. That makes the platform callable from outside through a documented API and SDK. Sourcetruefoundry.com/docs/llms.txtread 2026-09-21
Testing, Debugging & Optimization	Partial
Teams can test prompts, models, guardrails and MCP tools before production in TrueFoundry's AI Gateway playground, which shows a latency breakdown per request across the gateway and the model and saves versioned prompts, and the agent builder tests an agent against a live chat. No dataset runs or scoring of output quality are described. Sourcetruefoundry.com/docs/ai-gateway/playground-overviewread 2026-09-21
Browser & Computer Use	Not documented
Code, file and shell execution run in an isolated sandbox that TrueFoundry's hosted agent harness provisions, and browser tools reach an agent only as MCP servers the customer registers in the gateway. No browser, desktop or computer control that TrueFoundry ships is described. Sourcetruefoundry.com/docs/agent-platform/agent-harness/overviewread 2026-09-21

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Recent platform changes

2026-09-29·Human approval / guardrailsVerified

TrueForge 0.3.0, TrueFoundry's open source agent harness, adds an API for human approval and policy events during a turn, a durable inbox for them, and a way for a user to approve a tool for the rest of a session with an optional expiry. MCP tools labeled as writing or destructive now pause for approval by default.

Bears on: Human approval / guardrails

View source

2026-09-22·Pricing / packagingVerified

TrueFoundry 0.174.0 enables plan based feature gating for nonpaying tenants on managed control planes. Resource caps block further creation, and capabilities including agents, MCP tool approval, custom roles and SSO require higher plans. Existing configurations and traffic continue, but gated features disappear from the Developer plan UI; paying customers and self hosted or dedicated control planes are unaffected.

Bears on: Pricing / packaging

View source

2026-09-16·Agent capabilityPartially Verified

TrueFoundry v0.172.28 introduces TrueForge for managed agent creation, a unified agent registry and a new identity and access management experience.

Bears on: Agent capability

View source

View all 10 changes for TrueFoundry →Tracked since Jul 2026 · Verified from public vendor sources

Pricing

Free Developer tier; Pro $25/user/mo; Enterprise contact sales

per user plus gateway requests and MCP tool calls above the included allowance

Free tierTrial available

Included quota

Developer: free, up to 3 users, 10K requests per user per month. Pro: $25 per user per month, unlimited users, 20K requests and MCP tool calls per user per month. Enterprise: custom.

What is public

The pricing page publishes Developer (free) and Pro ($25 per user per month plus $15 per 100K requests over the included allowance) with a cost estimator; Enterprise and the Agent Gateway and Agent Harness are custom.

Billing mechanics

Seats and traffic are separate. Active users are the highest number of users at any point in the month. Every LLM request and every MCP tool call counts as one request; the MCP Gateway is not priced separately. Model-provider charges pass through separately.

Cost watchouts

Model-provider charges and managed external guardrail charges are not included. Agent Gateway and Agent Harness are custom priced through sales for now. VPC, on-prem and air-gapped deployment, data residency and SLAs sit on the Enterprise plan.

Variable cost rationale

Seats are a flat $25 per user, but gateway traffic above the included allowance bills at $15 per 100K requests and tool calls, and model-provider charges pass through separately, so workload volume drives most of the cost.

Overage / add-ons

Pro bills gateway traffic above the included allowance at $15 per additional 100K requests; each LLM request and each MCP tool call counts as one request, guardrail checks do not count, and seats and traffic are billed separately.

Sales call required

Mixed (some tiers require a call)

Free / trial

Free Developer tier (up to 3 users, 10K requests per user per month); 7-day free trial; live sandbox with no credit card

Lowest paid plan

Pro, $25 per user per month, 20K requests and tool calls per user included, $15 per additional 100K

Commercial notes

Independent. Self-serve Developer and Pro plans with a cost estimator on the pricing page; Enterprise is sales led.

Key ambiguities

Enterprise pricing and prices for the Agent Gateway and Agent Harness are not published; the pricing page says standard pricing for both is coming.

Agentic Index verified 2026-09-21

Official pricing page

Related vendors

Alternatives to TrueFoundry

The closest documented capability profiles to TrueFoundry among agent infrastructure platforms tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

Composio8.5 / 14A lighter documented profile than TrueFoundry
OpenRouter10.5 / 14Adds documented Browser & Computer Use
Braintrust10.0 / 14Adds documented Prebuilt Agents, Templates & Packs
LangWatch10.0 / 14Adds documented Prebuilt Agents, Templates & Packs
Metorial8.0 / 14A lighter documented profile than TrueFoundry
Thread AI11.0 / 14Adds documented Knowledge Grounding & RAG and Prebuilt Agents, Templates & Packs

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Compare TrueFoundry with other vendors →Compare all agent infrastructure platforms →See where TrueFoundry ranks →

Data confidence: high

Head to head

TrueFoundry vs LiteLLM

TrueFoundry

Vendor details

Canonical URL

Category

Subcategory

Funding status

Company status

Use cases & customers

Primary use cases

Target customers

Deployment options

Integrations

In practice

Sources & related URLs

Research sources

Agentic Index coverage score

Recent platform changes

Pricing

Related vendors

Alternatives to TrueFoundry

Head to head

Contact us