Developer
$0
- Up to 3 users, 10k gateway requests per user per month, 5 model accounts, 5 MCP servers, 1 budget rule, 7-day log retention, SaaS deployment
TrueFoundry AI Gateway: Pricing, Features, Pros & Cons
Founded 2021|Free tier, per-seat with included gateway requests, Enterprise custom
What is TrueFoundry?
TrueFoundry is an enterprise AI platform built around an AI Gateway that routes LLM, MCP, and agent traffic through one control layer. The company was founded in 2021 and is based in San Francisco. It started as a Kubernetes platform for deploying ML models and still sells model serving and fine-tuning alongside the gateway.
The gateway handles routing, fallbacks, rate limits, budgets, and guardrails, and TrueFoundry reports overhead typically under 5ms. Tracing is OpenTelemetry-compliant and exports to tools like Grafana, Datadog, and Prometheus. Evaluation is narrower: TrueFoundry runs LLM judges inline as guardrails, so datasets and offline experiments need a separate eval tool.
Deployment covers SaaS, VPC, on-premises, and air-gapped environments, with everything beyond SaaS on the Enterprise plan, which is where it differs most from the LLM gateways that run only as managed services. Pricing is per seat with gateway requests included, so traffic growth bills as request overage rather than as extra seats.
Key features
Core capabilities this platform advertises.
- AI Gateway with routing, fallbacks, rate limits, and budgets
- MCP Gateway for governed agent access to tools
- Agent Gateway for agent identity and access policies
- Built-in, custom, and third-party guardrails
Strengths and tradeoffs
What this tool does well, and the limitations to keep in mind.
Pros
- LLM, MCP, and agent traffic run through one gateway
- VPC, on-premises, and air-gapped deployment available on Enterprise
- Model serving and fine-tuning live in the same platform as the gateway
Cons
- LLM judges run inline as guardrails only, so datasets and offline experiments need another tool
- SSO, audit logs, and VPC or on-prem deployment require Enterprise
Plans & pricing
What's included in each plan, and how the tiers compare.
Pro
$25
Per user per month
- Unlimited users, 20k gateway requests per user per month pooled across the team, $20 per additional 100k requests, built-in guardrails, up to 10 guardrail policies, 30-day log retention
Enterprise
Custom
Contact sales for a quote
Common use cases
Enterprise platform and AI teams that need to govern LLM, MCP, and agent traffic, often in their own cloud or on-prem
- Centralizing LLM access and spend across teams
- Governing MCP tool access for agents
- Running a gateway inside a VPC, on-prem, or air-gapped environment
Using TrueFoundry with Respan
Respan is the AI router with observability and automated evals built in. Every request it routes is already a trace, priced and ready to score, so output quality is measured in the same place routing happens, with no separate eval tool to wire in.
- One API for 1,000+ models, and switching models takes a one-word change
- Automatic fallbacks when a provider errors or rate-limits
- Evals on test sets before shipping and on live production traffic after
- Click any score and land on the trace behind it
- Hard spend limits per key, per customer, or org-wide
Route every model call and score it in one place with Respan
10KFree traces/mo
1,000+Models
Best TrueFoundry alternatives & competitors
Top companies in LLM Gateways you can use instead of TrueFoundry.
Compare TrueFoundry
Side-by-side comparisons with other tools in this category.
Best integrations for TrueFoundry
Companies from adjacent layers in the AI stack that work well with TrueFoundry.
