LLM 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

Usage-based [2]llmgateway.io/pricing“Platform fee: 5% on credit usage. Volume discounts available. International cards: +1.5% intl fee.”llmgateway.io/referrals“Lower than competitors. OpenRouter charges 5.5%. Bring your own keys and pay zero platform fees.”

Published pricing

✓ Yes

Free tier

✓ Yes [3]llmgateway.io/pricing“$0 forever — 280+ models across 35+ providers, 3 free models (rate limited), 30-day activity log retention, chat and API access”llmgateway.io“Free tier included. No credit card required. Setup in 30 seconds”

Free tier details

Free plan at $0 forever: access to 280+ models across 35+ providers via BYOK, 3 free (rate-limited) models, 30-day activity log retention, chat and API access. Free models rate-limited to 5 requests per 10 minutes (upgrades to 20 req/min once any credits are added). Open-source self-host also available under AGPLv3. [4]llmgateway.io/pricing“$0 forever — 280+ models across 35+ providers, 3 free models (rate limited), 30-day activity log retention, chat and API access”docs.llmgateway.io/self-host“self-hosted deployment for data control and customization”

Self-serve signup

✓ Yes [5]llmgateway.io“Free tier included. No credit card required. Setup in 30 seconds”

Requires sales call

✗ No

Enterprise plan

✓ Yes [6]llmgateway.io/enterprise“Enterprise Cloud: Fully managed with custom scaling. Every plan starts with a 30-day trial.”

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

Supported actions

unified_chat_completions, openai_compatible_api, model_routing, automatic_fallback, load_balancing, response_caching, prompt_caching, spend_limits, budgets, rate_limiting, observability_logging, request_analytics, cost_tracking, guardrails, pii_redaction, virtual_keys, byo_provider_keys, embeddings, image_generation, audio_speech_synthesis, video_generation, content_moderation, custom_providers, provider_compliance_policies, ip_restrictions, sso_saml_oidc, audit_logs, mcp_server [7]docs.llmgateway.io/features/routing“LLMGateway automatically retries failed requests on alternate providers. This happens transparently within the same API call.”llmgateway.io/enterprise“SSO (SAML/OIDC) via Okta, Azure AD, Google Workspace; Tamper-evident audit logs; Server-side guardrails (prompt injection, PII, secrets detection)”

Regions

US, EU, APAC [8]llmgateway.io/reliability“Multi-region redundancy spans US, EU, and APAC. This geographic distribution ensures regional outages don't cause service interruption.”

Input types

chat completions, embeddings, image generation, audio speech synthesis, video generation, content moderation

Output types

streaming (SSE), JSON, OpenAI-compatible response

Webhooks

✓ Yes [9]llmgateway.io/blog/embeddable-ai-credits-stripe-for-ai“Webhooks are signed and SSRF-safe, with events signed so you can verify them, and only public HTTPS endpoints can be registered.”

Sandbox / test mode

✗ No [10]llmgateway.io/pricing“Free Plan — $0 forever — no dedicated sandbox/test-mode keys mentioned; free tier is the live environment with rate-limited free models”

SDK languages

Node.js / TypeScript (Vercel AI SDK), Python / any (OpenAI SDK drop-in)

MCP server

✓ Yes [11]llmgateway.io/mcp“LLM Gateway provides an MCP (Model Context Protocol) server enabling access to 280+ models from OpenAI, Anthropic, Google, and more through AI assistants like Claude Code and Cursor.”docs.llmgateway.io/guides/mcp“Server URL: https://api.llmgateway.io/mcp”

SOC 2

SOC 2 Type II [12]llmgateway.io/enterprise“SOC 2 Type II: Independently audited against the AICPA Trust Services Criteria for security, availability, and confidentiality”security.llmgateway.io“SOC 2 Type 2: Compliant status confirmed. Controls verified over sustained period.”

HIPAA

✗ No [13]security.llmgateway.io“Page does not mention HIPAA certification. Only SOC 2 Type 2 and GDPR (in progress) are listed.”llmgateway.io/enterprise“ISO 27001 & HIPAA: Supported through provider compliance policies feature”

GDPR

✓ Yes [14]llmgateway.io/enterprise“GDPR: Data processing aligned with regulations; DPA and subprocessor list available”security.llmgateway.io“GDPR: In progress”

ISO 27001

✗ No [15]security.llmgateway.io“Page does not mention ISO 27001 certification. Only SOC 2 Type 2 and GDPR listed.”llmgateway.io/enterprise“ISO 27001 & HIPAA: Supported through provider compliance policies feature — this refers to routing to compliant providers, not LLM Gateway's own certification”

PCI DSS

✗ No [16]security.llmgateway.io“No PCI DSS certification claimed. Trust center lists only SOC 2 Type 2 and GDPR (in progress).”

Published SLA

✓ Yes [17]llmgateway.io/legal/terms“Any service levels, support commitments, or uptime targets apply only if expressly stated in a separate written agreement signed by us.”llmgateway.io/reliability“Enterprise plans include 99.9% SLAs with service credits for non-compliance.”

Rate limits

Free models (no credits): 5 requests per 10 minutes. Free models (with any credits added): 20 requests per minute. Paid models: no rate limiting. Enterprise: custom rate limits. [18]docs.llmgateway.io/resources/rate-limits“5 requests per 10 minutes for organizations with zero credits. 20 requests per minute once any credits are purchased. No rate limiting applies to paid AI models.”

Known restrictions

5% gateway fee applied to credit usage on paid plans, Non-US cards incur additional 1.5% international fee, IP restriction rules (CIDR-based) are Enterprise-only, No formal SLA for free/standard PAYG accounts - SLA applies only if expressly stated in a separate written agreement, Self-hosted AGPLv3 open-source version lacks enterprise features (SSO, audit logs, spend controls, guardrails), Image disk saving only works on self-hosted instances with UPLOAD_DIR configured, HIPAA and ISO 27001 are routing-policy features (restrict to compliant providers), not LLM Gateway's own certifications [19]llmgateway.io/pricing“5% on credit usage; Non-US cards incur an additional 1.5% international fee”llmgateway.io/legal/terms“Any service levels, support commitments, or uptime targets apply only if expressly stated in a separate written agreement signed by us.”

• Docs
• llms.txt
• Changelog
• Status page

Docs rendering: static · llms.txt present

API style

rest

Base URL

https://api.llmgateway.io/v1

Version

v1

Versioning

url

Stability

ga

Auth methods

api_key

Error format

openai-compatible

Rate limit

5 / minute

SDKs

• Node.js / TypeScript (Vercel AI SDK) @llmgateway/ai-sdk-provider · repo
• Python / any (OpenAI SDK drop-in) openai · repo

• Auth docs
• Quickstart
• MCP server

Launched

2025-05-01

GA

2025-05-01

Notable customers

Samsung, Harvard, Coloop.ai, FieldKo

• 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

• TrueFoundry AI Gateway

  "A unified AI gateway to securely manage and govern AI across 1600+ models with policy control, real-time monitoring, and up to 30% cost reduction."

  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

LLM Gateway alternatives · LLM 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: llmgateway.io
2. ↑Pricing model: llmgateway.io · llmgateway.io
3. ↑Free tier: llmgateway.io · llmgateway.io
4. ↑Free tier details: llmgateway.io · docs.llmgateway.io
5. ↑Self-serve signup: llmgateway.io
6. ↑Enterprise plan: llmgateway.io
7. ↑Supported actions: docs.llmgateway.io · llmgateway.io
8. ↑Regions: llmgateway.io
9. ↑Webhooks: llmgateway.io
10. ↑Sandbox: llmgateway.io
11. ↑MCP server: llmgateway.io · docs.llmgateway.io
12. ↑SOC 2: llmgateway.io · security.llmgateway.io
13. ↑HIPAA: security.llmgateway.io · llmgateway.io
14. ↑GDPR: llmgateway.io · security.llmgateway.io
15. ↑ISO 27001: security.llmgateway.io · llmgateway.io
16. ↑PCI DSS: security.llmgateway.io
17. ↑Published SLA: llmgateway.io · llmgateway.io
18. ↑Rate limits: docs.llmgateway.io
19. ↑Known restrictions: llmgateway.io · llmgateway.io

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) → LLM Gateway is a unified routing layer that sends requests across 280+ models t…
3. 2026-06-21 Score Agent Friendliness: (none) → 65
4. 2026-06-21 Score Pricing Transparency: (none) → 75
5. 2026-06-21 Score Setup Speed: (none) → 80
6. 2026-06-21 Score Docs Quality: (none) → 35
7. 2026-06-21 Score Procurement Friction: (none) → 90
8. 2026-06-21 Score Trust Readiness: (none) → 60
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 Robots Allows Agents: (none) → Yes
13. 2026-06-21 Status Page URL: (none) → https://status.llmgateway.io
14. 2026-06-21 Changelog URL: (none) → https://llmgateway.io/changelog
15. 2026-06-21 Has Structured Data: (none) → Yes
16. 2026-06-21 Docs URL: (none) → https://docs.llmgateway.io/
17. 2026-06-21 Llms Txt Present: (none) → Yes
18. 2026-06-21 Llms Txt URL: (none) → https://llmgateway.io/llms.txt
19. 2026-06-21 Has Published Pricing: set to Yes
20. 2026-06-21 Free Tier Available: set to Yes
21. 2026-06-21 Free Tier Details: set to Free plan at $0 forever: access to 280+ models across 35+ providers via BYOK, 3…
22. 2026-06-21 Self Serve Signup: set to Yes
23. 2026-06-21 Requires Sales Call: set to No
24. 2026-06-21 Enterprise Plan Available: set to Yes
25. 2026-06-21 SOC 2: set to type_2
26. 2026-06-21 HIPAA: set to No
27. 2026-06-21 GDPR: set to Yes
28. 2026-06-21 ISO 27001: set to No
29. 2026-06-21 PCI DSS: set to No
30. 2026-06-21 SLA Published: set to Yes
31. 2026-06-21 SLA URL: set to https://status.llmgateway.io/
32. 2026-06-21 Status: set to published
33. 2026-06-21 Data Retention Policy URL: set to https://llmgateway.io/legal/privacy
34. 2026-06-21 Documented Rate Limits: set to Free models (no credits): 5 requests per 10 minutes. Free models (with any cred…
35. 2026-06-21 Rate Limit Requests: set to 5
36. 2026-06-21 Rate Limit Window: set to minute
37. 2026-06-21 Known Restrictions: set to 5% gateway fee applied to credit usage on paid plans, Non-US cards incur additi…
38. 2026-06-21 Auth Methods: set to api_key
39. 2026-06-21 Auth Docs URL: set to https://docs.llmgateway.io/features/api-keys
40. 2026-06-21 API Style: set to rest
41. 2026-06-21 Base URL: set to https://api.llmgateway.io/v1
42. 2026-06-21 API Version: set to v1
43. 2026-06-21 Versioning Scheme: set to url
44. 2026-06-21 Stability: set to ga
45. 2026-06-21 MCP URL: set to https://api.llmgateway.io/mcp
46. 2026-06-21 Quickstart URL: set to https://docs.llmgateway.io/quick-start
47. 2026-06-21 Error Format: set to openai-compatible
48. 2026-06-21 Requires Verification: set to No
49. 2026-06-21 Price Basis: set to % of spend
50. 2026-06-21 Free Tier Limit: set to 3 free models (rate-limited); open-source self-host available (AGPLv3)

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/llmgateway \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/llmgateway/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 →