Cloudflare 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]developers.cloudflare.com/ai-gateway/reference/pricing/“AI Gateway's core features available today are offered for free... A 5% fee is applied to all credits purchased through Unified Billing... Logpush is only available on the Workers Paid plan. Pricing: 10 million requests monthly included; additional requests cost $0.05 per million.”

Published pricing

✓ Yes

Free tier

✓ Yes [3]developers.cloudflare.com/ai-gateway/reference/pricing/“AI Gateway's core features available today are offered for free, including dashboard analytics, caching, and rate limiting. Only a Cloudflare account and basic setup required.”

Free tier details

Core features (dashboard analytics, caching, rate limiting) are free on all Cloudflare plans. Workers Free plan includes 100,000 logs per account across all gateways. DLP scanning is free on all plans (2 predefined profiles without Zero Trust subscription). [4]developers.cloudflare.com/ai-gateway/reference/pricing/“Workers Free: 100,000 logs total [per account]. Workers Paid: 10,000,000 logs per gateway. DLP scanning is free on all plans.”developers.cloudflare.com/ai-gateway/reference/limits/“Free Plan — Gateways: 10 per account; Log storage: 100,000 per account across all gateways; Logpush jobs: 4 per account”

Self-serve signup

✓ Yes

Requires sales call

✗ No

Enterprise plan

✓ Yes [5]developers.cloudflare.com/ai-gateway/reference/pricing/“If you are an Enterprise customer, reach out to your account team to confirm pricing details.”

• Fallback / routing
• Spend controls
• Observability
• Guardrails

Supported actions

unified_chat_completions, openai_compatible_api, anthropic_compatible_api, model_routing, automatic_fallback, dynamic_routing, rate_limiting, exact_match_caching, prompt_caching, spend_limits, budgets, observability_logging, analytics, cost_tracking, guardrails, pii_redaction, dlp_scanning, byo_provider_keys, custom_costs, custom_metadata, opentelemetry_tracing, workers_logpush, websocket_support, evaluations, audit_logs, graphql_analytics_api [6]developers.cloudflare.com/ai-gateway/features/caching/“This means caching is based on exact match of the entire request. We plan on adding semantic search for caching in the future to improve cache hit rates.”developers.cloudflare.com/ai-gateway/observability/“Monitor AI Gateway traffic with analytics, logging, cost tracking, and OpenTelemetry integration”

Input types

chat completions, text completions, image generation, text-to-speech, automatic speech recognition, embeddings, agentic workflows (responses API)

Output types

streaming (SSE), JSON, OpenAI-compatible response, Anthropic-compatible response

Webhooks

✗ No [7]blog.cloudflare.com/ai-gateway-spend-limits/“the team is working to add the capability for you to also send alerts when a limit is reached, indicating alert functionality is in development but not yet available.”

Sandbox / test mode

✗ No

SDK languages

JavaScript/TypeScript, JavaScript/TypeScript (OpenAI SDK drop-in) [8]developers.cloudflare.com/fundamentals/api/reference/sdks/“Cloudflare currently offers the following SDKs [for Go, TypeScript, and Python] allowing developers to interact with the Cloudflare API in language-specific syntax”

MCP server

✓ Yes [9]developers.cloudflare.com/agents/model-context-protocol/mcp-servers-for-cloudflare/“AI Gateway server — available at https://ai-gateway.mcp.cloudflare.com/mcp and enables users to search your logs, get details about the prompts and responses.”

SOC 2

SOC 2 Type II [10]cloudflare.com/trust-hub/“Cloudflare protects our customers and their users by complying with a wide range of important security certifications... ISO 27001, ISO 27701, PCI DSS, SOC 2 Type II”blog.cloudflare.com/updates-to-cloudflare-security-and-privacy-certifications-and-reports/“Cloudflare maintains annual SOC reports covering security, confidentiality, and availability trust principles with third-party assessor engagement yearly.”

HIPAA

✓ Yes [11]blog.cloudflare.com/updates-to-cloudflare-security-and-privacy-certifications-and-reports/“Enterprise security product customers can leverage Business Associate Agreements for healthcare data protection compliance.”

GDPR

✓ Yes [12]blog.cloudflare.com/updates-to-cloudflare-security-and-privacy-certifications-and-reports/“ISO 27701:2019 certification as both data processor and controller, providing assurance that we have a formal privacy program that is aligned to GDPR.”

ISO 27001

✓ Yes [13]blog.cloudflare.com/updates-to-cloudflare-security-and-privacy-certifications-and-reports/“ISO 27001:2013 — Certified since 2019, demonstrating a formal information security management program that adheres to a globally recognized standard.”

PCI DSS

✓ Yes [14]blog.cloudflare.com/updates-to-cloudflare-security-and-privacy-certifications-and-reports/“PCI DSS — Evaluated annually as a Level 1 Merchant and Service Provider by a Qualified Security Assessor, enabling secure payment data transmission.”

Published SLA

✓ Yes [15]cloudflare.com/business-sla/“100% Uptime. The Service will serve Customer Content 100% of the time without qualification.”

Rate limits

Free plan: 100,000 logs per account; Paid plan: 10,000,000 logs per gateway; log storage rate: 500 logs per second per gateway; individual log size: 10 MB; Unified Billing request rate: 200 requests per 60 seconds per gateway; cacheable request size: 25 MB per request; cache TTL max: 1 month; free plan: 10 gateways per account; paid plan: 20 gateways per account [16]developers.cloudflare.com/ai-gateway/reference/limits/“Log storage rate: 500 logs per second per gateway; Individual log size: 10 MB per log; Unified Billing request rate: 200 requests per 60 seconds per gateway; Cacheable request size: 25 MB per request; Cache TTL: 1 month”

Known restrictions

AI Gateway is not compatible with Cloudflare Regional Services or Geo Key Manager (no data residency controls), HIPAA BAA only available for Enterprise customers, Logpush only available on Workers Paid plan, Guardrails pricing scales with token usage via Workers AI inference, Unified Billing applies a 5% fee to all credits purchased (inference pricing from providers is passed through with no markup), Free plan DLP limited to 2 predefined profiles (full suite requires Zero Trust subscription), Cache applies exact-match only; semantic caching not yet available (planned for future release), AI Gateway token permissions cannot be restricted to a single gateway - tokens grant access to all gateways in an account [17]developers.cloudflare.com/ai-gateway/reference/pricing/“A 5% fee is applied to all credits purchased through Unified Billing. inference pricing from providers is passed through with no markup.”developers.cloudflare.com/ai-gateway/features/caching/“This means caching is based on exact match of the entire request. We plan on adding semantic search for caching in the future to improve cache hit rates.”

• Docs
• API reference
• llms.txt
• Changelog

Docs rendering: static · llms.txt present

API style

rest

Base URL

https://api.cloudflare.com/client/v4/accounts/{account_id}/ai

Version

v1

Versioning

url

Stability

ga

Auth methods

api_key

Error format

vendor-specific

Rate limit

200 / minute

SDKs

• JavaScript/TypeScript ai-gateway-provider · repo
• JavaScript/TypeScript (OpenAI SDK drop-in) openai · repo

• Auth docs
• Quickstart
• MCP server
• Deprecation policy

Launched

2023-09-27

GA

2024-05-22

Notable customers

RightBlogger

• 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

• 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

• 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

Cloudflare AI Gateway alternatives · Cloudflare 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: cloudflare.com · developers.cloudflare.com
2. ↑Pricing model: developers.cloudflare.com
3. ↑Free tier: developers.cloudflare.com
4. ↑Free tier details: developers.cloudflare.com · developers.cloudflare.com
5. ↑Enterprise plan: developers.cloudflare.com
6. ↑Supported actions: developers.cloudflare.com · developers.cloudflare.com
7. ↑Webhooks: blog.cloudflare.com
8. ↑SDK languages: developers.cloudflare.com
9. ↑MCP server: developers.cloudflare.com
10. ↑SOC 2: cloudflare.com · blog.cloudflare.com
11. ↑HIPAA: blog.cloudflare.com
12. ↑GDPR: blog.cloudflare.com
13. ↑ISO 27001: blog.cloudflare.com
14. ↑PCI DSS: blog.cloudflare.com
15. ↑Published SLA: cloudflare.com
16. ↑Rate limits: developers.cloudflare.com
17. ↑Known restrictions: developers.cloudflare.com · developers.cloudflare.com

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

1. 2026-06-21 Capabilities: {} → {"guardrails":true,"observability":true,"spend_controls":true,"fallback_routing…
2. 2026-06-21 Summary Md: (none) → Cloudflare AI Gateway is a unified proxy layer for teams routing requests acros…
3. 2026-06-21 Score Pricing Transparency: (none) → 75
4. 2026-06-21 Score Setup Speed: (none) → 80
5. 2026-06-21 Score Docs Quality: (none) → 55
6. 2026-06-21 Score Procurement Friction: (none) → 90
7. 2026-06-21 Score Trust Readiness: (none) → 100
8. 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
9. 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
10. 2026-06-21 Score Agent Friendliness: (none) → 65
11. 2026-06-21 Llms Txt Present: (none) → Yes
12. 2026-06-21 Rendering: (none) → static
13. 2026-06-21 Has Structured Data: (none) → Yes
14. 2026-06-21 Robots Allows Agents: (none) → Yes
15. 2026-06-21 API Reference URL: (none) → https://developers.cloudflare.com/fundamentals/api/reference/sdks/
16. 2026-06-21 Changelog URL: (none) → https://developers.cloudflare.com/changelog
17. 2026-06-21 Docs URL: (none) → https://developers.cloudflare.com/api/
18. 2026-06-21 Llms Txt URL: (none) → https://developers.cloudflare.com/llms.txt
19. 2026-06-21 Free Tier Available: set to Yes
20. 2026-06-21 Versioning Scheme: set to url
21. 2026-06-21 Free Tier Details: set to Core features (dashboard analytics, caching, rate limiting) are free on all Clo…
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 Yes
27. 2026-06-21 GDPR: set to Yes
28. 2026-06-21 ISO 27001: set to Yes
29. 2026-06-21 PCI DSS: set to Yes
30. 2026-06-21 SLA Published: set to Yes
31. 2026-06-21 SLA URL: set to https://www.cloudflare.com/business-sla/
32. 2026-06-21 Data Retention Policy URL: set to https://www.cloudflare.com/privacypolicy/
33. 2026-06-21 Documented Rate Limits: set to Free plan: 100,000 logs per account; Paid plan: 10,000,000 logs per gateway; lo…
34. 2026-06-21 Rate Limit Requests: set to 200
35. 2026-06-21 Rate Limit Window: set to minute
36. 2026-06-21 Known Restrictions: set to AI Gateway is not compatible with Cloudflare Regional Services or Geo Key Manag…
37. 2026-06-21 Auth Methods: set to api_key
38. 2026-06-21 Auth Docs URL: set to https://developers.cloudflare.com/ai-gateway/configuration/authentication/
39. 2026-06-21 API Style: set to rest
40. 2026-06-21 Base URL: set to https://api.cloudflare.com/client/v4/accounts/{account_id}/ai
41. 2026-06-21 API Version: set to v1
42. 2026-06-21 Stability: set to ga
43. 2026-06-21 Deprecation Policy URL: set to https://developers.cloudflare.com/fundamentals/api/reference/deprecations/
44. 2026-06-21 MCP URL: set to https://ai-gateway.mcp.cloudflare.com/mcp
45. 2026-06-21 Quickstart URL: set to https://developers.cloudflare.com/ai-gateway/get-started/
46. 2026-06-21 Error Format: set to vendor-specific
47. 2026-06-21 Slug: set to cloudflare-ai-gateway
48. 2026-06-21 Free Tier Limit: set to Core features (analytics, caching, rate limiting) free on all plans; 100,000 lo…
49. 2026-06-21 Launched At: set to 2023-09-27
50. 2026-06-21 GA Date: set to 2024-05-22

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

curl -X POST https://apio.sh/api/suggest/cloudflare-ai-gateway/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 →