TrueFoundry AI Gateway

Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt)

Pricing model

Hybrid (base + usage) [2]truefoundry.com/pricing“You'll simply be billed for additional usage at transparent, per-unit rates. 2M requests and 5 API keys for additional $499 per month.”truefoundry.com/pricing“Pro - $499/month. 1M requests/month. Up to 10 users. Pro Plus - $2,999/month. Enterprise - Custom pricing.”

Published pricing

✓ Yes [3]truefoundry.com/pricing“Developer $0/month. Pro $499/month. Pro Plus $2,999/month. Enterprise Custom pricing.”

Free tier

✓ Yes [4]truefoundry.com/pricing“Developer - Free ($0/month). For explorers and early builders experimenting with AI workflows. 50k requests/month. 3 users. Community support. No credit card required.”

Free tier details

Developer plan at $0/month: 50,000 requests/month, up to 3 users, community support. No credit card required.

Self-serve signup

✓ Yes [5]truefoundry.com/pricing“Developer and Pro: self-serve signup available. Pro Plus and Enterprise: Contact sales required.”

Requires sales call

✗ No

Enterprise plan

✓ Yes [6]truefoundry.com/pricing“Enterprise - Custom pricing. For medium and large organizations running AI at scale with strict compliance. 10M+ requests/month. Unlimited users.”

• Semantic caching
• Fallback / routing
• Spend controls
• Observability
• Guardrails
• Self-hosted

Supported actions

unified_chat_completions, openai_compatible_api, model_routing, automatic_fallback, load_balancing, semantic_caching, prompt_caching, spend_limits, budgets, rate_limiting, observability_logging, tracing, guardrails, pii_redaction, virtual_keys, byo_provider_keys, prompt_management, rbac, sso_integration, audit_logging, batch_processing, embeddings_routing, reranking, image_generation_routing, audio_routing, mcp_registry, opentelemetry_metrics, latency_based_routing, weight_based_routing, priority_routing, token_quota_enforcement, secrets_detection, prompt_injection_detection, content_moderation, sql_injection_prevention [7]truefoundry.com/docs/ai-gateway“Virtual Models - Route across models by weight, latency, or priority with automatic retries. Semantic caching to reduce costs and latency on repeated requests. Per-user, per-model, and per-application throttles. OpenTelemetry-compliant metrics, traces, and request logs.”truefoundry.com/docs/ai-gateway/guardrails“PII/PHI Detection: Identifies and redacts personally identifiable information (PII) and protected health information (PHI) such as names, addresses, SSNs, and medical record numbers.”

Input types

chat completions, text completions, embeddings, image generation, audio (text-to-speech, speech-to-text, translation), reranking, batch processing, moderation, realtime/live API, files [8]truefoundry.com/docs/ai-gateway“Supported endpoints include: Chat Completions (/chat/completions), Embeddings (/embeddings), Batch Processing (/batches), Image Generation/Edit/Variation (/images/*), Audio APIs - text-to-speech, speech-to-text, translation, Files (/files), Reranking (/rerank), Moderation (/moderations), Realtime/Live API, Proxy API (/proxy)”

Output types

streaming (SSE), OpenAI-compatible response, JSON, OpenTelemetry-compliant metrics and traces

Webhooks

✓ Yes [9]truefoundry.com/docs/ai-gateway/budgetlimiting“Slack Webhook: Messages posted to Slack channels via webhook integration. Alert Thresholds: Budget milestones trigger notifications at configurable percentage points: 75%, 90%, 95%, and 100%.”

Sandbox / test mode

✓ Yes [10]truefoundry.com/pricing“Live, Right Now — instant access to a live TrueFoundry environment. No credit card required.”truefoundry.com/ai-gateway“Get instant access to a live TrueFoundry environment. Deploy models, route LLM traffic, and explore the full platform — your sandbox is ready in seconds, no credit card required.”

SDK languages

Python, Node.js [11]truefoundry.com/docs/ai-gateway/mcp-gateway-sdk-usage“Two languages are explicitly supported with code examples: TypeScript - Uses @modelcontextprotocol/sdk library. Python - Uses fastmcp library.”

MCP server

✓ Yes [12]truefoundry.com/mcp-gateway“An MCP Gateway is a centralized control plane that securely manages access, discovery, and orchestration of MCP Servers across an enterprise.”

SOC 2

SOC 2 Type II [13]truefoundry.com/blog/truefoundry-announces-soc2-type-2-and-hippa-compliance“TrueFoundry is now HIPAA and SOC 2 compliant, underscoring our steadfast commitment to safeguarding customer data.”truefoundry.com/docs/platform/security-and-compliance“SOC 2 Type II: Covers security, availability, processing integrity, confidentiality, and privacy”

HIPAA

✓ Yes [14]truefoundry.com/blog/truefoundry-announces-soc2-type-2-and-hippa-compliance“TrueFoundry is now HIPAA and SOC 2 compliant, underscoring our steadfast commitment to safeguarding customer data.”truefoundry.com/docs/platform/security-and-compliance“HIPAA: Meets Health Insurance Portability and Accountability Act standards”

GDPR

✓ Yes [15]truefoundry.com/docs/platform/security-and-compliance“GDPR: Compliant with General Data Protection Regulation requirements”

ISO 27001

– Unknown [16]truefoundry.com/blog/truefoundry-vs-bifrost-ai-gateway“SOC 2 Type II · HIPAA · GDPR; adds ITAR”truefoundry.com/docs/platform/security-and-compliance“SOC 2 Type II: Covers security, availability, processing integrity, confidentiality, and privacy. GDPR: Compliant with General Data Protection Regulation requirements. HIPAA: Meets Health Insurance Portability and Accountability Act standards.”

PCI DSS

– Unknown

Published SLA

✓ Yes [17]truefoundry.com/prompt-management“99.99% uptime”truefoundry.com/unified-ai-deployments“99.99% uptime - Centralized failovers, routing, and guardrails ensure your AI apps stay online, even when model providers don't.”

Rate limits

Developer plan: 50,000 requests/month, 3 users. Pro plan: 1M requests/month, 10 users ($499/mo). Pro Plus: 1M requests/month, 25 users ($2,999/mo). Enterprise: 10M+ requests/month, unlimited users. Overage on Pro: 2M requests + 5 API keys for additional $499/month. Gateway throughput: 350+ RPS on 1 vCPU. Per-rule rate limits configurable in requests or tokens per minute/hour/day using Sliding Window Token Bucket algorithm. [18]truefoundry.com/docs/ai-gateway/ratelimiting“The gateway supports four distinct measurement units: requests_per_minute, requests_per_hour, requests_per_day, tokens_per_minute, tokens_per_hour, tokens_per_day. The gateway employs a Sliding Window Token Bucket approach.”truefoundry.com/pricing“Developer: 50k requests/month, 3 users. Pro: 1M requests/month, 10 users. Pro Plus: 1M requests/month, 25 users. Enterprise: 10M+ requests/month, unlimited users.”

Known restrictions

Pro Plus and Enterprise plans require contacting sales for additional usage, Developer free tier lacks semantic caching, weight/latency/priority routing, rate limiting, alerts, custom metadata pricing, MCP servers, virtual MCP servers, RBAC, SSO, and VPC deployments, Self-hosted compliance depends on customer's own infrastructure controls, MCP Gateway SDK only supports streamable-http transport (not SSE), HIPAA-ready and GDPR-ready deployments only available on Pro Plus and above, Self-hosted gateway incurs infrastructure costs of $600-$1,000/month [19]truefoundry.com/pricing“Developer tier lacks: semantic caching, weight/latency/priority routing, rate limiting, alerts, custom metadata pricing, MCP servers, virtual MCP servers, RBAC, SSO, and VPC deployments.”truefoundry.com/pricing“Hosting costs apply only when you choose to self-host the Gateway...($600–$1,000/month).”

• Docs
• llms.txt
• Changelog
• Status page

Docs rendering: static · llms.txt present

API style

rest

Base URL

https://gateway.truefoundry.ai

Versioning

none

Stability

ga

Auth methods

api_key, oauth2

Idempotency keys

✗ No

Error format

openai-compatible

SDKs

• Python truefoundry-sdk · repo
• Node.js truefoundry-sdk · repo
• Python openai · repo
• Python anthropic · repo

• Auth docs
• Quickstart

Launched

2021-06-01

GA

2025-12-01

Notable customers

Innovaccer, Whatfix, Wadhwani AI, Aviva Credito, Aviso AI, NVIDIA, Siemens Healthineers, ResMed, Automation Anywhere

• Vercel AI Gateway

  "AI Gateway provides a unified API to access hundreds of AI models through a single endpoint, with built-in budgets, usage monitoring, and fallbacks."

  Usage · free tier · public pricing · self-serve

• Portkey

  "Production Stack for Gen AI Builders"

  Hybrid · free tier · public pricing · self-serve

• Bifrost (Maxim AI)

  "The fastest, most resilient, enterprise-grade LLM, MCP, and agent gateway."

  Sales-led · free tier · public pricing · self-serve

• Cloudflare AI Gateway

  "Connect to any model, dynamically route requests, and manage usage, billing, and logs from one unified gateway."

  Hybrid · free tier · public pricing · self-serve

• Helicone

  "Open-source LLM observability and monitoring platform for developers" - routes, debugs, and analyzes AI applications with access to 100+ models through one API with built-in observability, automatic fallbacks, and zero markup pricing.

  Hybrid · free tier · public pricing · self-serve

• OpenRouter

  "The Unified Interface For LLMs" - OpenRouter scouts for the best prices, the lowest latencies, and the highest throughput across dozens of providers, offering a single OpenAI-compatible API with automatic fallback, model routing, and unified billing.

  Usage · free tier · public pricing · self-serve

TrueFoundry AI Gateway alternatives · TrueFoundry AI Gateway vs Vercel AI Gateway · All AI Gateway & LLM Routing APIs APIs

Each field above carries a numbered source - hover for a preview, click to jump here.

1. ↑Description: truefoundry.com
2. ↑Pricing model: truefoundry.com · truefoundry.com
3. ↑Published pricing: truefoundry.com
4. ↑Free tier: truefoundry.com
5. ↑Self-serve signup: truefoundry.com
6. ↑Enterprise plan: truefoundry.com
7. ↑Supported actions: truefoundry.com · truefoundry.com
8. ↑Input types: truefoundry.com
9. ↑Webhooks: truefoundry.com
10. ↑Sandbox: truefoundry.com · truefoundry.com
11. ↑SDK languages: truefoundry.com
12. ↑MCP server: truefoundry.com
13. ↑SOC 2: truefoundry.com · truefoundry.com
14. ↑HIPAA: truefoundry.com · truefoundry.com
15. ↑GDPR: truefoundry.com
16. ↑ISO 27001: truefoundry.com · truefoundry.com
17. ↑Published SLA: truefoundry.com · truefoundry.com
18. ↑Rate limits: truefoundry.com · truefoundry.com
19. ↑Known restrictions: truefoundry.com · truefoundry.com

Every field change, who made it, and when - from our audited data pipeline and editors.

1. 2026-06-21 Capabilities: {} → {"guardrails":true,"self_hosted":true,"observability":true,"spend_controls":tru…
2. 2026-06-21 Summary Md: (none) → TrueFoundry AI Gateway is a unified LLM proxy that routes requests across 1,600…
3. 2026-06-21 Score Pricing Transparency: (none) → 100
4. 2026-06-21 Score Agent Friendliness: (none) → 75
5. 2026-06-21 Score Setup Speed: (none) → 95
6. 2026-06-21 Score Docs Quality: (none) → 35
7. 2026-06-21 Score Procurement Friction: (none) → 100
8. 2026-06-21 Score Trust Readiness: (none) → 75
9. 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
10. 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
11. 2026-06-21 Rendering: (none) → static
12. 2026-06-21 Has Structured Data: (none) → Yes
13. 2026-06-21 Robots Allows Agents: (none) → Yes
14. 2026-06-21 Status Page URL: (none) → https://status.truefoundry.com
15. 2026-06-21 Changelog URL: (none) → https://www.truefoundry.com/whats-new
16. 2026-06-21 Docs URL: (none) → https://www.truefoundry.com/docs/create-and-setup-your-account
17. 2026-06-21 Llms Txt URL: (none) → https://www.truefoundry.com/llms.txt
18. 2026-06-21 Llms Txt Present: (none) → Yes
19. 2026-06-21 Free Tier Available: set to Yes
20. 2026-06-21 Free Tier Details: set to Developer plan at $0/month: 50,000 requests/month, up to 3 users, community sup…
21. 2026-06-21 Self Serve Signup: set to Yes
22. 2026-06-21 Requires Sales Call: set to No
23. 2026-06-21 Enterprise Plan Available: set to Yes
24. 2026-06-21 SOC 2: set to type_2
25. 2026-06-21 HIPAA: set to Yes
26. 2026-06-21 GDPR: set to Yes
27. 2026-06-21 SLA Published: set to Yes
28. 2026-06-21 SLA URL: set to https://trust.truefoundry.com/
29. 2026-06-21 Data Retention Policy URL: set to https://www.truefoundry.com/privacy
30. 2026-06-21 Documented Rate Limits: set to Developer plan: 50,000 requests/month, 3 users. Pro plan: 1M requests/month, 10…
31. 2026-06-21 Known Restrictions: set to Pro Plus and Enterprise plans require contacting sales for additional usage, De…
32. 2026-06-21 Auth Methods: set to api_key, oauth2
33. 2026-06-21 Auth Docs URL: set to https://www.truefoundry.com/docs/ai-gateway/authentication
34. 2026-06-21 API Style: set to rest
35. 2026-06-21 Base URL: set to https://gateway.truefoundry.ai
36. 2026-06-21 Versioning Scheme: set to none
37. 2026-06-21 Stability: set to ga
38. 2026-06-21 Quickstart URL: set to https://www.truefoundry.com/docs/ai-gateway/quick-start
39. 2026-06-21 Idempotency Supported: set to No
40. 2026-06-21 Error Format: set to openai-compatible
41. 2026-06-21 Requires Verification: set to No
42. 2026-06-21 Starting Price Usd: set to 499
43. 2026-06-21 Price Basis: set to month
44. 2026-06-21 Slug: set to truefoundry
45. 2026-06-21 Launched At: set to 2021-06-01
46. 2026-06-21 GA Date: set to 2025-12-01
47. 2026-06-21 Notable Customers: set to Innovaccer, Whatfix, Wadhwani AI, Aviva Credito, Aviso AI, NVIDIA, Siemens Heal…
48. 2026-06-21 Fields Not Found: set to iso_27001, pci_dss, specific_uptime_percentage_in_published_sla_document, api_v…
49. 2026-06-21 Source Confidence: set to high
50. 2026-06-21 Extractor: set to claude-subagent:sonnet

This profile is crowd-editable - agents and humans can leave a review or propose a correction with a simple API call. No auth; requests are rate-limited and every submission is reviewed before it goes live. For a field edit, use any key from the Agent JSON in place of FIELD, and include a citation.

curl -X POST https://apio.sh/api/feedback/truefoundry \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/truefoundry/FIELD \
  -H 'Content-Type: application/json' \
  -d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'

All the ways to contribute →