{ "data": { "a": { "slug": "cloudflare-ai-gateway", "name": "Cloudflare AI Gateway", "vendor": "Cloudflare, Inc.", "vendorUrl": "https://www.cloudflare.com", "kind": "router", "category": "inference", "summary": "AI Gateway is Cloudflare's proxy and router for model providers. Agents call OpenAI-style, Anthropic-style or native endpoints on the Cloudflare API, with logging, caching, rate and spend limits, retries, fallbacks and one prepaid credit balance.", "url": "https://www.anchorterminal.com/tools/cloudflare-ai-gateway", "markdownUrl": "https://www.anchorterminal.com/tools/cloudflare-ai-gateway.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/cloudflare-ai-gateway.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/cloudflare-ai-gateway.json", "dns": "cloudflare-ai-gateway.grade.anchorterminal.com", "repo": "https://github.com/cloudflare/ai", "license": "Proprietary service under Cloudflare's Self-Serve Subscription Agreement and its service-specific terms. Third-party models carry their providers' terms, linked from each model page. `ai-gateway-provider` is MIT and Cloudflare's OpenAPI repository is BSD-3-Clause", "transports": [ "http" ], "remoteUrl": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai", "packages": [ { "registry": "npm", "name": "ai-gateway-provider" }, { "registry": "npm", "name": "cloudflare" }, { "registry": "pypi", "name": "cloudflare" } ], "auth": "api-key", "authNotes": "A Cloudflare API token as a Bearer header, created by a person in the dashboard. The `/ai/*` inference routes need Workers AI Read, and the `/ai-gateway/*` management routes need AI Gateway Read or Edit. Provider-native endpoints on `gateway.ai.cloudflare.com` take the token in `cf-aig-authorization`. Tokens can carry an expiry and an IP address filter and cannot be limited to one gateway. Access is self-serve, with no review or sales step.", "pricing": "freemium", "pricingNotes": "Free on all plans for analytics, caching, rate limiting and DLP scanning, with a Cloudflare account. Third-party models are paid from prepaid Unified Billing credits at provider prices plus a 5 per cent fee on each credit purchase, or with the caller's own provider keys at no Cloudflare charge. Guardrails are billed as Workers AI inference. Accounts whose first gateway dates from 24 September 2026 or later keep logs in Workers Logs at Workers Logs pricing, older accounts in Legacy Logs (100,000 logs on Workers Free, 10,000,000 per gateway on Workers Paid). Logpush follows Logpush pricing (https://developers.cloudflare.com/ai-gateway/reference/pricing/, checked 2026-11-01).", "priceSummary": "5% fee", "where": "hosted", "x402": { "level": "partial", "evidence": "Machine Payments, in beta since 30 September 2026, takes x402 payment on `POST /ai/run` for four open models when the request carries `Payment-Method: x402`. It needs a Cloudflare API token, a United States account and a card on file. The OpenAI-style and Anthropic-style routes are not covered. We did not call it (https://developers.cloudflare.com/ai-gateway/features/machine-payments/, checked 2026-10-09).", "endpoints": [ { "url": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run", "priceUsd": null, "network": "" } ] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 250648, "pypiWeekly": null, "asOf": "2026-10-09" }, "docsUrl": "https://developers.cloudflare.com/ai-gateway/", "llmsTxt": "https://developers.cloudflare.com/ai-gateway/llms.txt", "openapi": "https://raw.githubusercontent.com/cloudflare/api-schemas/main/openapi.json", "capabilities": [ "inference.llm", "inference.router", "obs.gateway", "guard.moderation", "guard.pii" ], "tags": [ "hosted", "router", "free-tier", "usage-based", "x402", "openapi", "llms-txt", "openai-compatible", "typescript", "python", "go", "status-page", "bug-bounty" ], "lastRelease": "2026-10-21", "graded": true, "anchor": { "graded": true, "score": 67.8, "grade": "B", "agentReady": false, "rank": 301, "ranked": true, "rankOf": 1510, "categoryRank": 12, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 73, "maintenance": 75, "payments": 52, "reliability": 66, "schema": 75, "security": 80, "transparency": 74 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -3, "negativeNotes": [ "6 October 2026. Rejected-credential responses on `POST /ai/run` changed status (ElevenLabs 403, Vertex 500 and other providers' 402 became 401 with code 2009, and Unified Billing rejections became 503) on the day of the changelog entry, with no advance notice found. On 8 October new log IDs and request IDs changed from ULIDs and random UUIDs to UUIDv7, announced the same day with advice to update code that checks the ULID format. Repeats of one kind fold into one term. Three points (https://developers.cloudflare.com/ai-gateway/changelog/)." ], "verdict": "The gateway layer is free, per-model prices are public with no markup, and logs, spend limits and fallbacks are set per gateway. API tokens cannot be limited to one gateway, the service terms take third-party models outside Cloudflare's DPA, no SLA names the product, and error codes and log ID formats changed in October 2026 with same-day notice.", "bestFor": "Teams that already hold a Cloudflare account and want one token, one bill, logs, budgets and fallbacks in front of several model providers, or that want to keep their own provider keys behind a proxy with spend limits.", "strengths": [ "Core gateway functions (analytics, caching, rate limiting) are free on all plans, and provider prices pass through with no markup", "One Cloudflare API token reaches 241 catalogue models through OpenAI Chat Completions, OpenAI Responses, Anthropic Messages or the native `/ai/run` route", "Spend limits block requests with a 429 once a budget is reached, scoped by model, provider or request metadata, with up to 20 rules a gateway", "Logging is switched per gateway and per request, and `cf-aig-collect-log-payload: false` keeps token and cost metadata without storing prompts", "x402 payment (Machine Payments, beta since 30 September 2026) works on `POST /ai/run` for four open models" ], "weaknesses": [ "API tokens are account-scoped. Any token with AI Gateway Run can send requests through every gateway in the account and spend its stored provider keys", "The service-specific terms say the DPA and Information Security Exhibit do not apply to third-party models reached through AI Gateway", "No SLA naming AI Gateway was found. The Enterprise SLA lists service-specific SLAs for R2, Queues and Workers only", "On 6 October 2026 rejected-credential responses on `/ai/run` changed to 401 with code 2009, and on 8 October log IDs became UUIDv7, each announced the same day", "Unified Billing traffic is capped at 200 requests per 60 seconds per gateway, and a 5 per cent fee applies to credit purchases", "Section 2.2(e) of the Self-Serve Subscription Agreement bars automated agents that generate automated requests into the Services, which matters before any probe is run", "`ai-gateway-provider` was feature frozen and deprecated on 21 October 2026 in favour of `createAI` in the Agents SDK" ], "agentNotes": [ "Use the REST API at `api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1` with a token holding Workers AI Read. A token with only an AI Gateway permission returns 401 with code 10000", "Send `cf-aig-gateway-id` on every Workers AI (`@cf/`) call and on dynamic routes. Without it a dynamic route resolves against the default gateway and returns 404", "Set `cf-aig-collect-log: false` or `cf-aig-collect-log-payload: false` on sensitive requests. Logging of prompts and responses is on by default", "Treat a 429 as a rate limit or a spent budget and a 401 with code 2009 as a rejected provider key. Do not retry a 2009", "Set `byok_only` on the gateway or send `cf-aig-no-wholesale: true` to stop a request without a provider key falling through to paid Unified Billing credits", "Use `createAI` from the `agents` package for new AI SDK code. `ai-gateway-provider` is deprecated and gets no new work" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 67.8 } ], "editorialScores": { "ergonomics": 73, "maintenance": 75, "payments": 52, "reliability": 66, "schema": 75, "security": 80, "transparency": 51 }, "provenanceScore": 96, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl -X POST \"https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions\" \\\n --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n --header \"Content-Type: application/json\" \\\n --data '{\n \"model\": \"openai/gpt-4.1-mini\",\n \"messages\": [{\"role\": \"user\", \"content\": \"What is Cloudflare?\"}]\n }'", "x402": "curl -iX POST \"https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run\" \\\n --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n --header \"Payment-Method: x402\" \\\n --header \"Content-Type: application/json\" \\\n --data '{\"model\":\"z-ai/glm-4.7-flash\",\"input\":{\"messages\":[{\"role\":\"user\",\"content\":\"What is Cloudflare?\"}]}}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/cloudflare-ai-gateway" }, "sameCompany": [ "cloudflare-workers-ai", "cloudflare-sandbox-sdk", "cloudflare-workers-oauth-provider", "cloudflare-web-search", "cloudflare-clairic", "cloudflare-ai-search", "cloudflare-cli", "cloudflare-mcp", "cloudflare-email-service", "cloudflare-r2", "cloudflare-clef" ], "area": "models", "unitPrices": [ { "item": "Unified Billing credit purchase fee", "unit": "pct", "usd": 5, "note": "a $100 purchase is charged $105" } ], "provenance": { "legalEntity": "Cloudflare, Inc.", "domain": "cloudflare.com", "domainRegistered": "2009-02-17", "endpointOnVendorDomain": true, "terms": "https://www.cloudflare.com/terms/", "privacy": "https://www.cloudflare.com/privacypolicy/", "statusPage": "https://www.cloudflarestatus.com", "changelog": "https://developers.cloudflare.com/ai-gateway/changelog/", "securityTxt": "valid", "checked": "2026-10-09", "notes": [ "Terms are the Self-Serve Subscription Agreement, last updated 12 September 2025, which names Cloudflare, Inc. at 101 Townsend St, San Francisco.", "The service-specific terms (https://www.cloudflare.com/service-specific-terms-developer-platform/), last updated 28 September 2026, have a section for Workers AI and AI Gateway that supplements the agreement.", "The privacy policy is effective from 4 November 2025. The customer DPA is version 6.4, effective 3 April 2026.", "www.cloudflare.com/.well-known/security.txt, read on 9 October 2026, names HackerOne and a disclosure policy and has no Expires field. It is recorded as valid, although RFC 9116 asks for that field.", "The inference endpoints are on api.cloudflare.com and gateway.ai.cloudflare.com.", "The status page lists AI Gateway as its own component, operational on 9 October 2026.", "RDAP for cloudflare.com gives a registration date of 2009-02-17." ], "score": 96 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cloudflare-ai-gateway.json", "live": { "slug": "cloudflare-ai-gateway", "probe": { "target": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai", "method": "get", "lastAt": "2026-11-07T19:22:00.000167341Z", "lastOk": true, "lastStatus": 404, "lastMs": 64, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 43, "p95ms24h": 148, "samples24h": 238, "samples30d": 7215, "days": [ { "date": "2026-10-09", "probes": 85, "ok": 85 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 248, "ok": 248 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "vendorStatus": { "page": "https://www.cloudflarestatus.com", "indicator": "major", "summary": "Partial System Outage", "checkedAt": "2026-11-07T19:21:16.420324083Z" }, "versions": [ { "registry": "github", "name": "cloudflare/ai", "version": "ai-gateway-provider@4.0.2", "released": "2026-10-20", "seenAt": "2026-11-06T23:15:38.559571341Z" }, { "registry": "npm", "name": "ai-gateway-provider", "version": "4.0.2", "seenAt": "2026-11-06T23:15:36.263846681Z" }, { "registry": "npm", "name": "cloudflare", "version": "7.3.0", "seenAt": "2026-11-06T23:15:36.494835591Z" }, { "registry": "pypi", "name": "cloudflare", "version": "5.10.0", "released": "2026-11-05", "seenAt": "2026-11-06T23:15:38.451058045Z" } ], "githubStars": 1214, "npmWeekly": 232984, "pypiWeekly": 584250, "securityTxt": { "url": "https://cloudflare.com/.well-known/security.txt", "state": "valid", "checkedAt": "2026-11-07T16:00:23.467095484Z" }, "llmsTxt": { "url": "https://developers.cloudflare.com/ai-gateway/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:31:51.067852107Z" }, "domain": { "domain": "cloudflare.com", "registered": "2009-02-17", "source": "https://rdap.verisign.com/com/v1/domain/cloudflare.com", "checkedAt": "2026-11-01T14:18:56.122446983Z" }, "pages": [ { "url": "https://developers.cloudflare.com/ai-gateway/changelog/", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:03:42.700833734Z", "changedAt": "2026-11-07T14:03:42.700833734Z", "fingerprint": "e12d8cc0ccb6" }, { "url": "https://developers.cloudflare.com/ai-gateway/reference/pricing/", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:03:44.942884533Z", "changedAt": "2026-11-05T12:27:58.285650461Z", "fingerprint": "37ec41081ede" }, { "url": "https://www.cloudflare.com/privacypolicy/", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:26:53.030074077Z", "changedAt": "2026-11-06T13:47:54.357995184Z", "fingerprint": "282aa4b71b3e" }, { "url": "https://www.cloudflare.com/terms/", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:26:55.359645005Z", "changedAt": "2026-10-22T01:30:41.491480215Z", "fingerprint": "515e09b3c6ed" } ], "github": { "repo": "cloudflare/ai", "checkedAt": "2026-11-02T08:39:38.372041532Z", "stars": 1210, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-27T10:39:35Z", "openIssues": 63, "openPRs": 21, "issuesOpened90d": 21, "issuesClosed90d": 12, "prsMerged90d": 6, "ci": { "branch": "main", "runs": 50, "success": 49, "failure": 0, "other": 1, "latest": "success", "latestAt": "2026-10-27T10:42:34Z" }, "advisories": [ { "ghsa": "GHSA-v85r-hgf6-q875", "severity": "medium", "published": "2025-11-04T18:27:48Z" } ], "replies": { "sampled": 25, "unanswered": 14, "medianDays": 0.1 } }, "updatedAt": "2026-11-07T19:22:00.000167341Z" } }, "answer": "Cloudflare AI Gateway scores 67.8 (B) on agent readiness against LiteLLM's 62.4 (B), and leads in 2 of 7 scored categories. LiteLLM leads on schema \u0026 documentation, agent ergonomics, payments \u0026 pricing and maintenance \u0026 community.", "b": { "slug": "litellm", "name": "LiteLLM", "vendor": "BerriAI", "vendorUrl": "https://www.litellm.ai", "kind": "router", "category": "inference", "summary": "Open-source Python SDK and self-hosted AI gateway from BerriAI that puts 100+ model providers behind one OpenAI-compatible API, with virtual keys, spend tracking, budgets, fallbacks, guardrails and an MCP gateway.", "url": "https://www.anchorterminal.com/tools/litellm", "markdownUrl": "https://www.anchorterminal.com/tools/litellm.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/litellm.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/litellm.json", "dns": "litellm.grade.anchorterminal.com", "repo": "https://github.com/BerriAI/litellm", "license": "MIT, except the enterprise/ directory, which is under its own licence and needs an Enterprise licence key", "transports": [ "http" ], "packages": [ { "registry": "pypi", "name": "litellm" }, { "registry": "docker", "name": "docker.litellm.ai/berriai/litellm" } ], "auth": "api-key", "authNotes": "The gateway takes a Bearer key. `LITELLM_MASTER_KEY` is required at start-up and has full admin rights. Virtual keys, stored hashed, carry model, route, MCP server, budget, rate-limit and expiry limits and can be blocked. Key rotation with a grace period, SSO beyond five users, SCIM and JWT/OIDC auth need an Enterprise licence. `/key/info` takes the key being looked up as a `?key=` query parameter.", "pricing": "freemium", "pricingNotes": "Free to self-host under MIT, with no account or card. Model calls bill at each upstream provider's own prices on the operator's keys. Enterprise (SSO, audit logs, key rotation, team-scoped guardrails, support SLAs) is an annual licence priced through sales, with a 30-day trial key emailed after a form and no card (https://www.litellm.ai/pricing, https://www.litellm.ai/enterprise).", "priceSummary": "Freemium", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs index or the llms-full.txt file, read 2026-10-06. The gateway forwards to providers on the operator's keys.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 62841, "npmWeekly": null, "pypiWeekly": 22493278, "asOf": "2026-11-06" }, "docsUrl": "https://docs.litellm.ai", "llmsTxt": "https://docs.litellm.ai/llms.txt", "openapi": "https://docs.litellm.ai/api-reference/", "capabilities": [ "inference.router", "obs.gateway", "agent.mcp-client", "guard.pii" ], "tags": [ "self-hosted", "open-source", "router", "gateway", "mcp", "openapi", "llms-txt", "python", "docker", "bug-bounty", "soc2" ], "lastRelease": "2026-11-05", "graded": true, "anchor": { "graded": true, "score": 62.4, "grade": "B", "agentReady": false, "rank": 559, "ranked": true, "rankOf": 1510, "categoryRank": 20, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 79, "maintenance": 82, "payments": 60, "reliability": 70, "schema": 91, "security": 72, "transparency": 63 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": -12, "negativeNotes": [ "2026-03-24, -6. litellm 1.82.7 and 1.82.8 were uploaded to PyPI with a credential stealer that read environment variables, SSH keys, cloud and Kubernetes credentials and sent them to models.litellm.cloud. They were live for about 40 minutes before PyPI quarantined them, after a token leaked through the Trivy compromise. BerriAI published indicators, checksums and a rebuilt pipeline (v1.83.0, 30 March). A supply-chain incident that reached users, fixed, documented and six months old. https://docs.litellm.ai/blog/security-update-march-2026, https://api.osv.dev/v1/vulns/GHSA-5mg7-485q-xm76", "2026-04-24, -2. GHSA-r75f-5x8p-qvmc (CVE-2026-42208, critical). An unauthenticated SQL injection through the `Authorization` header in proxy key verification, affecting 1.81.16 up to 1.83.7. Fixed and published, inside six months. https://api.osv.dev/v1/vulns/GHSA-r75f-5x8p-qvmc", "2026-06-16, -2. GHSA-4xpc-pv4p-pm3w (CVE-2026-49468, critical). A crafted Host header could reach protected management routes without authentication where nothing upstream normalises Host. Fixed in 1.84.0. https://api.osv.dev/v1/vulns/GHSA-4xpc-pv4p-pm3w", "2026-08-27, -2. GHSA-6wvf-77m9-58rm (CVE-2026-37004, critical). Server-side template injection in /prompts/test let unauthenticated callers run OS commands in 1.82.4 and earlier, fixed in 1.83.7. Published months after the fix. https://api.osv.dev/v1/vulns/GHSA-6wvf-77m9-58rm", "Not deducted separately. 26 other GitHub advisories published between 6 November 2025 and 6 November 2026 (one more critical, ten high, six moderate and nine low), among them an OIDC cache-key collision (GHSA-jjhc-v7c2-5hh6), authenticated credential exfiltration through request-body routing (GHSA-3cv6-jpf6-8222, 30 September 2026) and, on 27 October 2026, privilege escalation from internal_user to proxy_admin through reuse of the salt key (GHSA-7hp6-4w63-5g45, high) and an arbitrary local file read by internal_user_viewer (GHSA-g5ff-637f-6q2m, high). All handled in public with fixes. https://api.osv.dev/v1/query" ], "verdict": "An MIT-licensed gateway that puts 100+ model providers behind one OpenAI-compatible API, with virtual keys, budgets, fallbacks and an MCP gateway, released several times a week. Its security record is the main limitation. Two PyPI releases carried a credential stealer on 24 March 2026, and 30 GitHub advisories followed in 12 months, five of them critical.", "bestFor": "Teams that want one OpenAI-compatible endpoint over many providers on their own infrastructure, with per-key budgets, model allowlists and an MCP gateway.", "strengths": [ "MIT core, self-hosted, with no telemetry when self-hosted per the data security page", "Virtual keys limited by model, route, MCP server, budget, rate and expiry, and blockable at once", "Every proxy serves Swagger, ReDoc and /openapi.json, and the docs have llms.txt with a Markdown twin of every page", "Error reference tells a gateway 429 (with `retry-after`, `rate_limit_type`, `reset_at`) from a provider 429", "v1.108.1 on 5 November 2026, 125 tags since 8 August, and four stable minor lines supported with patches" ], "weaknesses": [ "litellm 1.82.7 and 1.82.8 on PyPI carried a credential stealer for about 40 minutes on 24 March 2026", "30 GitHub advisories from 6 November 2025 to 6 November 2026, five critical, including unauthenticated SQL injection fixed in 1.83.7", "Key rotation, audit logs and SSO beyond five users need an Enterprise licence, priced only through sales", "Breaking changes ship in weekly minor releases on the 1.x line, and lines older than the latest four stop getting fixes", "The default Docker image runs as root, and the Swagger, ReDoc and OpenAPI pages are public until switched off" ], "agentNotes": [ "Pin an exact litellm version or image digest, verify the cosign signature, and never install an unpinned latest in CI", "Give each agent a virtual key limited to its models, routes and MCP servers, with a budget and an expiry", "Treat a 429 with `retry-after` as the gateway's own limit and wait that long; a 429 without it came from the provider", "Set `NO_DOCS`, `NO_REDOC` and `NO_OPENAPI` to True in production, and use the `-non_root` image variant", "Set `LITELLM_LOCAL_MODEL_COST_MAP=True` where egress is blocked, since start-up otherwise fetches the price map from GitHub" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62.4 } ], "editorialScores": { "ergonomics": 79, "maintenance": 82, "payments": 60, "reliability": 70, "schema": 91, "security": 72, "transparency": 77 }, "provenanceScore": 49, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install litellm # SDK; gateway: curl -sSLO https://github.com/BerriAI/litellm/raw/main/docker/docker-compose.quickstart.yml \u0026\u0026 docker compose -f docker-compose.quickstart.yml up -d", "http": "curl http://localhost:4000/v1/chat/completions \\\n -H 'Authorization: Bearer sk-\u003cyour-virtual-key\u003e' \\\n -H 'Content-Type: application/json' \\\n -d '{\n \"model\": \"gpt-5.6-terra\",\n \"messages\": [{\"role\": \"user\", \"content\": \"Say hello in five words.\"}]\n }'", "claudeCode": "export ANTHROPIC_BASE_URL=\"http://localhost:4000\"\nexport ANTHROPIC_AUTH_TOKEN=\"sk-\u003cyour-virtual-key\u003e\"\nexport ANTHROPIC_MODEL=\"\u003ca model_name from your config\u003e\"\nclaude" }, "letme": { "capability": "https://letme.dev/inference.router", "tool": "https://letme.dev/litellm" }, "area": "models", "provenance": { "legalEntity": "Berrie AI Incorporated", "domain": "litellm.ai", "domainRegistered": "2023-08-07", "endpointOnVendorDomain": false, "terms": "", "privacy": "https://docs.litellm.ai/docs/data_security", "statusPage": "", "changelog": "https://docs.litellm.ai/release_notes", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The data security page names the legal entity as Berrie AI Incorporated, with krrish@berri.ai as the security contact.", "The gateway is software the operator runs, so there's no vendor endpoint and no status page.", "No terms of service or privacy policy found on www.litellm.ai (/terms, /privacy and /legal return 404). The data security page in the docs covers self-hosted data handling.", "www.litellm.ai/.well-known/security.txt and the docs host both return 404. Reports go to GitHub private vulnerability reporting under security.md.", "RDAP for litellm.ai gives a registration date of 2023-08-07.", "Rechecked 2026-11-06: www.litellm.ai/terms, /privacy, /legal, /terms-of-service and /privacy-policy all return 404, and neither host serves security.txt. Both robots.txt files allow all." ], "score": 49 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/litellm.json", "live": { "slug": "litellm", "versions": [ { "registry": "github", "name": "BerriAI/litellm", "version": "v1.108.2", "released": "2026-11-06", "seenAt": "2026-11-06T23:40:24.985518384Z" }, { "registry": "pypi", "name": "litellm", "version": "1.108.2", "released": "2026-11-06", "seenAt": "2026-11-06T23:40:24.735967257Z" } ], "githubStars": 62845, "pypiWeekly": 22493278, "securityTxt": { "url": "https://litellm.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:25.60777972Z" }, "llmsTxt": { "url": "https://docs.litellm.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:52.845519783Z" }, "pages": [ { "url": "https://docs.litellm.ai/release_notes", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:06:55.608946935Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e493aadf92b2" }, { "url": "https://www.litellm.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:30:56.79408028Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "45e60222905c" }, { "url": "https://docs.litellm.ai/docs/data_security", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:06:53.531435979Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "a2363610f7ad" } ], "updatedAt": "2026-11-07T16:01:25.60777972Z" } }, "edges": [ { "by": 16, "category": "schema", "leads": "litellm", "name": "Schema \u0026 documentation", "reasons": { "a": "Router, scored on the API lines. Cloudflare's public OpenAPI 3.0.3 document, updated 9 October 2026, has 36 paths and 67 operations under `/ai-gateway` and includes `POST /ai/run`. The `/ai/v1/chat/completions`, `/ai/v1/responses` and `/ai/v1/messages` routes and the `gateway.ai.cloudflare.com` endpoints are not in it (20 of 25). An AI Gateway `llms.txt` and a Markdown copy of every page (10). Every management operation has a description, and the usage pages say which endpoint to use for new work and which are deprecated (15 of 20). Gateway settings are typed with enums and required fields, while the `input` object of `/ai/run` is free-form and depends on the model (10 of 15). Curl, SDK and Worker examples on most pages. No table of gateway error codes was found. The troubleshooting page still tells callers to keep the Cloudflare token out of `Authorization`, which the authentication page contradicts for the REST API, and the changelog of 6 October links a BYOK address that differs from the docs index (9 of 15). A dated changelog with RSS. The API has no version of its own beyond `/client/v4`, and the move of new customers to Workers Logs on 24 September 2026 has no changelog entry (11 of 15).", "b": "Every gateway serves Swagger at /, ReDoc at /redoc and the raw schema at /openapi.json, and the docs host a public Swagger explorer (25). llms.txt, llms-full.txt and a Markdown twin of every page via `.md` (10). Pages say what a feature is for and where its limits are, and the key-auth page explains how permissions are inherited and where they aren't, but the reference is very large for a model to navigate (16 of 20). OpenAI-shaped request schemas from Pydantic models, with `metadata`, `litellm_params` and config blocks left as free-form objects (10 of 15). A full error reference with the envelope, every status, response headers and how to tell gateway limits from provider limits, plus examples on every page (15). Release notes per version with dates, newest v1.108.0 and v1.106.7 on 4 November 2026 (15)." }, "scores": { "a": 75, "b": 91 } }, { "by": 11, "category": "transparency", "leads": "cloudflare-ai-gateway", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service under the Self-Serve Subscription Agreement and service-specific terms with a section for Workers AI and AI Gateway. Each model page links the provider's terms, `ai-gateway-provider` is MIT and the OpenAPI repository is BSD-3-Clause (16 of 30). The service terms, the logging and Zero Data Retention pages, the DPA (version 6.4, 3 April 2026) and the privacy policy of 4 November 2025 were read. The privacy policy gives retention criteria, not periods. The terms take third-party models outside the DPA, while the sub-processor list names five model providers for AI Gateway, and the two are hard to square (17 of 30). No deprecation policy was found. Deprecated endpoints carry notices with no dates, and section 8 of the agreement lets Cloudflare modify or discontinue a service without notice (6 of 20). The sub-processor list, last updated 1 October 2025, names Google, Anthropic, OpenAI, xAI and Groq for AI Gateway with locations. The catalogue on 9 October 2026 also carries models from Alibaba, ByteDance, MiniMax and others that the list does not name (12 of 20). The terms, DPA, privacy policy and sub-processor list are per the 9 October check, not re-read on 1 November.", "b": "MIT for everything outside enterprise/, which has its own licence (25 of 30). The data security page (updated 6 November 2026) and security.md agree that a self-hosted gateway sends no data or telemetry to BerriAI, and the gateway stores prompts and spend in the operator's own Postgres. We found no terms of service or privacy policy on litellm.ai for its site, trial or Enterprise licence (20 of 30). A version support policy since 29 June 2026 (four stable minor lines), deprecated pages labelled in the docs, and release notes with breaking-change bullets (15 of 20). Usage telemetry, new in v1.107.0, is off by default, lists every field it can send and goes only to a table or endpoint the operator sets. A main-branch commit of 23 October 2026 made the Admin UI chat post a hashed user id to chat-telemetry.litellm.ai, and it was removed on 24 October before any tagged release contained it, so it isn't deducted. The start-up fetch of the price map from GitHub is documented with an opt-out (17 of 20)." }, "scores": { "a": 74, "b": 63 } }, { "by": 8, "category": "security", "leads": "cloudflare-ai-gateway", "name": "Security \u0026 auth", "reasons": { "a": "Router, read on the model lines. Cloudflare API tokens are revocable, split into AI Gateway Read, Run and Edit and Workers AI Read, and take an expiry and an IP address filter. They cannot be limited to one gateway, so a Run token can spend the provider keys stored on every gateway in the account. The OpenAPI document also lists the older API key with account email (24 of 30). The service-specific terms of 28 September 2026 say Cloudflare does not use Customer Content to train generative AI tools. The same section says the DPA and Information Security Exhibit do not apply to third-party models reached through AI Gateway, so training and retention there rest on each provider's terms (13 of 20). Prompts and responses are logged by default. Two headers switch off the whole log or the payload per request, Zero Data Retention routing exists for Unified Billing on marked models, and new customers' logs are kept 3 or 7 days while Legacy Logs persist until deleted (11 of 15). Per-request logs carry prompt, response, tokens, cost and user agent, account audit logs record gateway creation, update and deletion, and Logpush and OpenTelemetry export exist (14 of 15). security.txt, re-read on 1 November, names a HackerOne programme and a disclosure policy, with no Expires field. Cloudflare's ISO certifications page, read on 1 November, says it is certified to ISO 27001 (since 2019, now 27001:2022), ISO 27018 and ISO 27701, with a scope of the Cloudflare global cloud platform, which doesn't name AI Gateway. 2 held back for the missing Expires field, which RFC 9116 requires, as cloudflare-r2, cloudflare-workers-ai, cloudflare-sandbox-sdk and cloudflare-email-service read the same evidence (18 of 20, 13 before, when certifications went unread). Guardrails and DLP scanning are available per gateway and are not scored on these lines. 24 + 13 + 11 + 14 + 18 = 80.", "b": "Read with the tool checklist for self-hosted software. Virtual keys are hashed, revocable and blockable, with model, route, MCP server, budget, rate and expiry limits, and a `proxy_admin_viewer` read-only role exists. Rotation with a grace period is Enterprise only, so 25, less 10 because the docs pass a key as `?key=` on `/key/info` and on the Claude Code marketplace manifest (15 of 30). `allowed_routes`, MCP permissions by key and team, an approval queue for submitted MCP servers and stdio MCP servers off by default from 1.104.0 (15 of 20). Guardrails can run before a model call and on MCP tool results, and an OWASP LLM Top 10 page maps each risk to a control, but prompt-injection detectors such as Lakera need an Enterprise licence and all of it is off by default (12 of 15). Request and spend logs per key in the open-source build; audit logs of admin actions are Enterprise only (12 of 15). security.md with GitHub private reporting, a bug bounty from $500 to $3,000 for P0 and P1 reports, a security announcements list, SOC 2 Type II per the data security page, CodeQL, OSV and Scorecard workflows, and advisories published on GitHub. No security.txt, and reports without a video are closed unread (18 of 20)." }, "scores": { "a": 80, "b": 72 } }, { "by": 8, "category": "payments", "leads": "litellm", "name": "Payments \u0026 pricing", "reasons": { "a": "x402 is in beta on `POST /ai/run` since 30 September 2026 for four open models of 241 in the catalogue. It still needs a Cloudflare API token, a United States account and a card on file, and the OpenAI-style and Anthropic-style routes are not covered. We did not call it (12 of 40). The gateway's own prices, the 5 per cent credit fee and per-model token prices are published without a login (20). Core functions are free on all plans, and calls made with the caller's own provider keys carry no Cloudflare charge. We did not sign up to confirm that no card is asked for (20). A person creates the account and the first token in a browser, and the x402 route needs both (0). The Machine Payments page (last updated 30 September, the same four models) and the pricing page (last updated 30 October) were re-read on 1 November. 12 + 20 + 20 + 0 = 52.", "b": "Read with the self-hosted rule, since an agent uses the free gateway and Enterprise is a sales-led licence for the same software. No x402, MPP or L402 (0). MIT with no account and no card, so 20, 20 and 20 on the last three lines. Model calls cost what the operator's provider keys cost." }, "scores": { "a": 52, "b": 60 } }, { "by": 7, "category": "maintenance", "leads": "litellm", "name": "Maintenance \u0026 community", "reasons": { "a": "Router, read on the model lines. The newest changelog entry is 21 October 2026 (`createAI` in the Agents SDK replaces `ai-gateway-provider` and `workers-ai-provider`, which are feature frozen and deprecated), after UUIDv7 log IDs on 8 October and the error-code change on 6 October (30). No minimum notice for API changes was found. The Universal Endpoint and the compat route are marked deprecated with a promise to keep working and no end date, and the error-code change of 6 October and the log ID format change of 8 October took effect on the day each was announced (5 of 12). No gateway endpoint was shut down in the last 90 days that we found. Thirteen dataset, evaluation and spending-limit operations are marked deprecated in the OpenAPI document with no changelog entry, per the 9 October check (5 of 8). A dated changelog with RSS and thirteen entries between 5 August and 21 October 2026. The Discord community was not sampled (11 of 15). Replies on the SDK repositories were not examined (3 of 10). `cloudflare` for TypeScript 7.3.0 and Python 5.9.0 are the newest tags on 1 November, per the other Cloudflare re-checks' clones that day, and `ai-gateway-provider` is deprecated in favour of `createAI` in the `agents` package, an official successor (14 of 15). The OpenAPI repository was updated on 9 October 2026, per the 9 October check, not re-read on 1 November (7 of 10). 30 + 5 + 5 + 11 + 3 + 14 + 7 = 75.", "b": "v1.108.1 tagged on 5 November 2026, v1.108.0 and v1.106.7 on 3 and 4 November (30). 125 tags between 8 August and 6 November, stable, patch, release-candidate and dev builds, with patch releases for four minor lines at once (20). Reply times not measured. On the issues page 7 of the 15 newest had a reply on the day, workflows auto-close duplicates and label issues, and Discord is the listed community channel (12 of 25). The package is the official SDK, current, with OpenAI and Anthropic SDKs working against the gateway (12 of 15). Dependency and image scanning (OSV, zizmor, Scorecard, grype) run in CI, with pass state unchecked (8 of 10)." }, "scores": { "a": 75, "b": 82 } }, { "by": 6, "category": "ergonomics", "leads": "litellm", "name": "Agent ergonomics", "reasons": { "a": "Router, read on the model lines (tool use, structured output, caching, context, batch, SDKs, errors). Three provider request formats pass through, OpenAI Chat Completions, OpenAI Responses and Anthropic Messages, and provider-native tools such as web search are documented. Tool behaviour depends on the routed model (15 of 20). No gateway page on structured output was found, so it rests on each provider's format (8 of 15). A response cache for identical requests with TTLs up to a month and custom keys, off by default, and cached-input prices on model pages (11 of 15). The catalogue lists models with a context of about one million tokens, a judgement call since a router has no default model (15). Background requests on `/ai/run` post the result to a webhook, best-effort and with no retry, and no batch discount is stated (5 of 10). The OpenAI and Anthropic SDKs work with a changed base URL, and Cloudflare's own SDKs cover TypeScript, Python and Go (10). Status codes are documented page by page (401 with 10000 or 2009, 400, 404, 429, 503) with `cf-aig-step` and routing headers on responses, and no consolidated error reference (9 of 15).", "b": "Read with the API lines for the gateway an agent calls. Responses size through the usual `max_tokens` and streaming, and the MCP gateway can replace a large tool catalogue with four virtual tools (tool search) or filter tools by semantic relevance, which cuts context cost (20 of 25). Key, team and spend listings page and filter, though we didn't check every list call (15 of 20). Errors keep the OpenAI envelope with a string `code`, gateway 429s carry `retry-after`, `rate_limit_type` and `reset_at`, management routes answer RFC 9457 problem+json, and a table says which errors are safe to retry (20). Retries, cooldowns and fallbacks run inside the gateway and the docs say which errors to retry, but there are no idempotency keys for the management writes (12 of 20). Any OpenAI or Anthropic SDK works by changing the base URL, but the only first-party client is the Python SDK, and keys and spend need Postgres and a master key before the first call (12 of 15)." }, "scores": { "a": 73, "b": 79 } } ], "facts": [ { "a": "Model router", "b": "Model router", "name": "Kind" }, { "a": "Cloudflare, Inc.", "b": "BerriAI", "name": "Vendor" }, { "a": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Freemium", "b": "Freemium", "name": "Pricing" }, { "a": "payer tooling only", "b": "no", "name": "x402" }, { "a": "Proprietary service under Cloudflare's Self-Serve Subscription Agreement and its service-specific terms. Third-party models carry their providers' terms, linked from each model page. `ai-gateway-provider` is MIT and Cloudflare's OpenAPI repository is BSD-3-Clause", "b": "MIT, except the enterprise/ directory, which is under its own licence and needs an Enterprise licence key", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-21", "b": "2026-11-05", "name": "Last release" }, { "a": "2025-09-12", "b": "no document linked", "name": "Terms last updated" }, { "a": "no date given", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not read yet", "name": "Customer content may train models" }, { "a": "yes", "b": "not read yet", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not read yet", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "not read yet", "name": "Arbitration or class-action waiver" }, { "a": "251k npm/wk", "b": "63k stars, 22.5M PyPI/wk", "name": "Popularity" }, { "a": "3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Cloudflare AI Gateway scores 67.8 (B) on agent readiness against LiteLLM's 62.4 (B), and leads in 2 of 7 scored categories. LiteLLM leads on schema \u0026 documentation, agent ergonomics, payments \u0026 pricing and maintenance \u0026 community.", "question": "Which is better for AI agents, Cloudflare AI Gateway or LiteLLM?" }, { "answer": "Both need an API key.", "question": "Do Cloudflare AI Gateway and LiteLLM need an API key?" }, { "answer": "Cloudflare AI Gateway has a hosted endpoint at https://api.cloudflare.com/client/v4/accounts/{account_id}/ai. No hosted endpoint is listed for LiteLLM.", "question": "Can an agent call Cloudflare AI Gateway and LiteLLM without installing anything?" }, { "answer": "No open-source release is listed for Cloudflare AI Gateway. LiteLLM is open source (MIT, except the enterprise/ directory, which is under its own licence and needs an Enterprise licence key).", "question": "Are Cloudflare AI Gateway and LiteLLM open source?" } ], "goodFor": [ { "aheadOn": [ "Security \u0026 auth, 80 against 72", "Transparency \u0026 trust, 74 against 63" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "Teams that already hold a Cloudflare account and want one token, one bill, logs, budgets and fallbacks in front of several model providers, or that want to keep their own provider keys behind a proxy with spend limits.", "slug": "cloudflare-ai-gateway", "watchFor": "API tokens are account-scoped. Any token with AI Gateway Run can send requests through every gateway in the account and spend its stored provider keys" }, { "aheadOn": [ "Schema \u0026 documentation, 91 against 75", "Agent ergonomics, 79 against 73", "Payments \u0026 pricing, 60 against 52", "Maintenance \u0026 community, 82 against 75" ], "also": [ "Open source" ], "goodFor": "Teams that want one OpenAI-compatible endpoint over many providers on their own infrastructure, with per-key budgets, model allowlists and an MCP gateway.", "slug": "litellm", "watchFor": "litellm 1.82.7 and 1.82.8 on PyPI carried a credential stealer for about 40 minutes on 24 March 2026" } ], "history": { "cloudflare-ai-gateway": [ { "causes": [ "evidence" ], "date": "2026-11-01", "delta": 0.9, "from": 66.9, "fromGrade": "B", "to": 67.8, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 66.8, "fromGrade": "B", "to": 66.9, "toGrade": "B" } ], "litellm": null }, "job": { "capability": "inference.router", "name": "Model routing" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-cloudflare-ai-gateway.json", "title": "Amazon Bedrock vs Cloudflare AI Gateway", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-cloudflare-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-cloudflare-ai-gateway.json", "title": "Claude API vs Cloudflare AI Gateway", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-cloudflare-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/azure-openai-vs-cloudflare-ai-gateway.json", "title": "Azure OpenAI in Foundry Models vs Cloudflare AI Gateway", "url": "https://www.anchorterminal.com/compare/azure-openai-vs-cloudflare-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-cloudflare-ai-gateway.json", "title": "BlockRun.AI vs Cloudflare AI Gateway", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-cloudflare-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-cloudflare-ai-gateway.json", "title": "Cerebras Inference vs Cloudflare AI Gateway", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-cloudflare-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-cloudflare-workers-ai.json", "title": "Cloudflare AI Gateway vs Cloudflare Workers AI", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-cloudflare-workers-ai" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-cohere-chat.json", "title": "Cloudflare AI Gateway vs Cohere Chat API (Command models)", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-cohere-chat" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-deepinfra.json", "title": "Cloudflare AI Gateway vs DeepInfra", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-deepinfra" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-deepseek-api.json", "title": "Cloudflare AI Gateway vs DeepSeek API", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-deepseek-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-eden-ai.json", "title": "Cloudflare AI Gateway vs Eden AI", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-eden-ai" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-elorian-glimpse.json", "title": "Cloudflare AI Gateway vs Glimpse", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-elorian-glimpse" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-fireworks-inference.json", "title": "Cloudflare AI Gateway vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-fireworks-inference" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-gemini-api.json", "title": "Cloudflare AI Gateway vs Gemini Developer API", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-gemini-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-groq.json", "title": "Cloudflare AI Gateway vs GroqCloud", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-groq" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-hugging-face-inference-providers.json", "title": "Cloudflare AI Gateway vs Hugging Face Inference Providers", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-hugging-face-inference-providers" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-inkling-2-small.json", "title": "Cloudflare AI Gateway vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-jais-3.json", "title": "Cloudflare AI Gateway vs Jais 3", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-meta-model-api.json", "title": "Cloudflare AI Gateway vs Meta Model API", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-minimax-api.json", "title": "Cloudflare AI Gateway vs MiniMax API", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-minimax-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-mistral-api.json", "title": "Cloudflare AI Gateway vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-muse-spark-open.json", "title": "Cloudflare AI Gateway vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-nemotron-3-5-super-vl.json", "title": "Cloudflare AI Gateway vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-novita-ai.json", "title": "Cloudflare AI Gateway vs Novita AI", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-openai-api.json", "title": "Cloudflare AI Gateway vs OpenAI API", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-openrouter.json", "title": "Cloudflare AI Gateway vs OpenRouter", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-prism-inference.json", "title": "Cloudflare AI Gateway vs Prism Inference", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-ramp-router.json", "title": "Cloudflare AI Gateway vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-reflection-beam.json", "title": "Cloudflare AI Gateway vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-routerplus.json", "title": "Cloudflare AI Gateway vs RouterPlus", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-sambanova.json", "title": "Cloudflare AI Gateway vs SambaCloud", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-siliconflow.json", "title": "Cloudflare AI Gateway vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-simplismart.json", "title": "Cloudflare AI Gateway vs Simplismart", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-stepfun-api.json", "title": "Cloudflare AI Gateway vs StepFun API", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-swe-2-flash.json", "title": "Cloudflare AI Gateway vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-tencent-tokenhub.json", "title": "Cloudflare AI Gateway vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-together-inference.json", "title": "Cloudflare AI Gateway vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-vercel-ai-gateway.json", "title": "Cloudflare AI Gateway vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-vertex-ai.json", "title": "Cloudflare AI Gateway vs Vertex AI (Gemini Enterprise Agent Platform)", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-vertex-ai" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-xai-api.json", "title": "Cloudflare AI Gateway vs xAI API (Grok)", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-xai-api" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-cloudflare-ai-gateway.json", "title": "Antseed vs Cloudflare AI Gateway", "url": "https://www.anchorterminal.com/compare/antseed-vs-cloudflare-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-litellm.json", "title": "Antseed vs LiteLLM", "url": "https://www.anchorterminal.com/compare/antseed-vs-litellm" }, { "json": "https://www.anchorterminal.com/compare/eden-ai-vs-litellm.json", "title": "Eden AI vs LiteLLM", "url": "https://www.anchorterminal.com/compare/eden-ai-vs-litellm" }, { "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-litellm.json", "title": "Hugging Face Inference Providers vs LiteLLM", "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-litellm" }, { "json": "https://www.anchorterminal.com/compare/litellm-vs-openrouter.json", "title": "LiteLLM vs OpenRouter", "url": "https://www.anchorterminal.com/compare/litellm-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/litellm-vs-ramp-router.json", "title": "LiteLLM vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/litellm-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/litellm-vs-routerplus.json", "title": "LiteLLM vs RouterPlus", "url": "https://www.anchorterminal.com/compare/litellm-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/litellm-vs-tencent-tokenhub.json", "title": "LiteLLM vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/litellm-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/litellm-vs-vercel-ai-gateway.json", "title": "LiteLLM vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/litellm-vs-vercel-ai-gateway" } ], "panel": null, "scores": [ { "by": 4, "cloudflare-ai-gateway": 66, "edge": "litellm", "key": "reliability", "litellm": 70, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 16, "cloudflare-ai-gateway": 75, "edge": "litellm", "key": "schema", "litellm": 91, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 6, "cloudflare-ai-gateway": 73, "edge": "litellm", "key": "ergonomics", "litellm": 79, "name": "Agent ergonomics", "weight": 13 }, { "by": 8, "cloudflare-ai-gateway": 80, "edge": "cloudflare-ai-gateway", "key": "security", "litellm": 72, "name": "Security \u0026 auth", "weight": 14 }, { "by": 8, "cloudflare-ai-gateway": 52, "edge": "litellm", "key": "payments", "litellm": 60, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 7, "cloudflare-ai-gateway": 75, "edge": "litellm", "key": "maintenance", "litellm": 82, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 11, "cloudflare-ai-gateway": 74, "edge": "cloudflare-ai-gateway", "key": "transparency", "litellm": 63, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Cloudflare AI Gateway scores 67.8 (B) on agent readiness against LiteLLM's 62.4 (B), and leads in 2 of 7 scored categories. LiteLLM leads on schema \u0026 documentation, agent ergonomics, payments \u0026 pricing and maintenance \u0026 community. Both do model routing.", "tasks": null, "tutorials": [], "verdicts": { "cloudflare-ai-gateway": "The gateway layer is free, per-model prices are public with no markup, and logs, spend limits and fallbacks are set per gateway. API tokens cannot be limited to one gateway, the service terms take third-party models outside Cloudflare's DPA, no SLA names the product, and error codes and log ID formats changed in October 2026 with same-day notice.", "litellm": "An MIT-licensed gateway that puts 100+ model providers behind one OpenAI-compatible API, with virtual keys, budgets, fallbacks and an MCP gateway, released several times a week. Its security record is the main limitation. Two PyPI releases carried a credential stealer on 24 March 2026, and 30 GitHub advisories followed in 12 months, five of them critical." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-litellm", "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-litellm.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-litellm.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-litellm.min.md" }, "markdown": "Cloudflare AI Gateway scores 67.8 (B) on agent readiness against LiteLLM's 62.4 (B), and leads in 2 of 7 scored categories. LiteLLM leads on schema \u0026 documentation, agent ergonomics, payments \u0026 pricing and maintenance \u0026 community. Both do model routing.\n\n- Cloudflare AI Gateway: grade B, 67.8/100, rank #301 of 1510. Markdown https://www.anchorterminal.com/tools/cloudflare-ai-gateway.md · JSON https://www.anchorterminal.com/api/v1/tools/cloudflare-ai-gateway.json\n- LiteLLM: grade B, 62.4/100, rank #559 of 1510. Markdown https://www.anchorterminal.com/tools/litellm.md · JSON https://www.anchorterminal.com/api/v1/tools/litellm.json\n- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 830 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### Cloudflare AI Gateway (B)\n\nGood for: Teams that already hold a Cloudflare account and want one token, one bill, logs, budgets and fallbacks in front of several model providers, or that want to keep their own provider keys behind a proxy with spend limits.\n\nAhead on:\n- Security \u0026 auth, 80 against 72\n- Transparency \u0026 trust, 74 against 63\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: API tokens are account-scoped. Any token with AI Gateway Run can send requests through every gateway in the account and spend its stored provider keys\n\n### LiteLLM (B)\n\nGood for: Teams that want one OpenAI-compatible endpoint over many providers on their own infrastructure, with per-key budgets, model allowlists and an MCP gateway.\n\nAhead on:\n- Schema \u0026 documentation, 91 against 75\n- Agent ergonomics, 79 against 73\n- Payments \u0026 pricing, 60 against 52\n- Maintenance \u0026 community, 82 against 75\n\nAlso in its favour:\n- Open source\n\nWatch for: litellm 1.82.7 and 1.82.8 on PyPI carried a credential stealer for about 40 minutes on 24 March 2026\n\n\n## Why the edge\n\n### Schema \u0026 documentation: LiteLLM +16\n\n- Cloudflare AI Gateway (75): Router, scored on the API lines. Cloudflare's public OpenAPI 3.0.3 document, updated 9 October 2026, has 36 paths and 67 operations under `/ai-gateway` and includes `POST /ai/run`. The `/ai/v1/chat/completions`, `/ai/v1/responses` and `/ai/v1/messages` routes and the `gateway.ai.cloudflare.com` endpoints are not in it (20 of 25). An AI Gateway `llms.txt` and a Markdown copy of every page (10). Every management operation has a description, and the usage pages say which endpoint to use for new work and which are deprecated (15 of 20). Gateway settings are typed with enums and required fields, while the `input` object of `/ai/run` is free-form and depends on the model (10 of 15). Curl, SDK and Worker examples on most pages. No table of gateway error codes was found. The troubleshooting page still tells callers to keep the Cloudflare token out of `Authorization`, which the authentication page contradicts for the REST API, and the changelog of 6 October links a BYOK address that differs from the docs index (9 of 15). A dated changelog with RSS. The API has no version of its own beyond `/client/v4`, and the move of new customers to Workers Logs on 24 September 2026 has no changelog entry (11 of 15).\n- LiteLLM (91): Every gateway serves Swagger at /, ReDoc at /redoc and the raw schema at /openapi.json, and the docs host a public Swagger explorer (25). llms.txt, llms-full.txt and a Markdown twin of every page via `.md` (10). Pages say what a feature is for and where its limits are, and the key-auth page explains how permissions are inherited and where they aren't, but the reference is very large for a model to navigate (16 of 20). OpenAI-shaped request schemas from Pydantic models, with `metadata`, `litellm_params` and config blocks left as free-form objects (10 of 15). A full error reference with the envelope, every status, response headers and how to tell gateway limits from provider limits, plus examples on every page (15). Release notes per version with dates, newest v1.108.0 and v1.106.7 on 4 November 2026 (15).\n\n### Transparency \u0026 trust: Cloudflare AI Gateway +11\n\n- Cloudflare AI Gateway (74): Closed service under the Self-Serve Subscription Agreement and service-specific terms with a section for Workers AI and AI Gateway. Each model page links the provider's terms, `ai-gateway-provider` is MIT and the OpenAPI repository is BSD-3-Clause (16 of 30). The service terms, the logging and Zero Data Retention pages, the DPA (version 6.4, 3 April 2026) and the privacy policy of 4 November 2025 were read. The privacy policy gives retention criteria, not periods. The terms take third-party models outside the DPA, while the sub-processor list names five model providers for AI Gateway, and the two are hard to square (17 of 30). No deprecation policy was found. Deprecated endpoints carry notices with no dates, and section 8 of the agreement lets Cloudflare modify or discontinue a service without notice (6 of 20). The sub-processor list, last updated 1 October 2025, names Google, Anthropic, OpenAI, xAI and Groq for AI Gateway with locations. The catalogue on 9 October 2026 also carries models from Alibaba, ByteDance, MiniMax and others that the list does not name (12 of 20). The terms, DPA, privacy policy and sub-processor list are per the 9 October check, not re-read on 1 November.\n- LiteLLM (63): MIT for everything outside enterprise/, which has its own licence (25 of 30). The data security page (updated 6 November 2026) and security.md agree that a self-hosted gateway sends no data or telemetry to BerriAI, and the gateway stores prompts and spend in the operator's own Postgres. We found no terms of service or privacy policy on litellm.ai for its site, trial or Enterprise licence (20 of 30). A version support policy since 29 June 2026 (four stable minor lines), deprecated pages labelled in the docs, and release notes with breaking-change bullets (15 of 20). Usage telemetry, new in v1.107.0, is off by default, lists every field it can send and goes only to a table or endpoint the operator sets. A main-branch commit of 23 October 2026 made the Admin UI chat post a hashed user id to chat-telemetry.litellm.ai, and it was removed on 24 October before any tagged release contained it, so it isn't deducted. The start-up fetch of the price map from GitHub is documented with an opt-out (17 of 20).\n\n### Security \u0026 auth: Cloudflare AI Gateway +8\n\n- Cloudflare AI Gateway (80): Router, read on the model lines. Cloudflare API tokens are revocable, split into AI Gateway Read, Run and Edit and Workers AI Read, and take an expiry and an IP address filter. They cannot be limited to one gateway, so a Run token can spend the provider keys stored on every gateway in the account. The OpenAPI document also lists the older API key with account email (24 of 30). The service-specific terms of 28 September 2026 say Cloudflare does not use Customer Content to train generative AI tools. The same section says the DPA and Information Security Exhibit do not apply to third-party models reached through AI Gateway, so training and retention there rest on each provider's terms (13 of 20). Prompts and responses are logged by default. Two headers switch off the whole log or the payload per request, Zero Data Retention routing exists for Unified Billing on marked models, and new customers' logs are kept 3 or 7 days while Legacy Logs persist until deleted (11 of 15). Per-request logs carry prompt, response, tokens, cost and user agent, account audit logs record gateway creation, update and deletion, and Logpush and OpenTelemetry export exist (14 of 15). security.txt, re-read on 1 November, names a HackerOne programme and a disclosure policy, with no Expires field. Cloudflare's ISO certifications page, read on 1 November, says it is certified to ISO 27001 (since 2019, now 27001:2022), ISO 27018 and ISO 27701, with a scope of the Cloudflare global cloud platform, which doesn't name AI Gateway. 2 held back for the missing Expires field, which RFC 9116 requires, as cloudflare-r2, cloudflare-workers-ai, cloudflare-sandbox-sdk and cloudflare-email-service read the same evidence (18 of 20, 13 before, when certifications went unread). Guardrails and DLP scanning are available per gateway and are not scored on these lines. 24 + 13 + 11 + 14 + 18 = 80.\n- LiteLLM (72): Read with the tool checklist for self-hosted software. Virtual keys are hashed, revocable and blockable, with model, route, MCP server, budget, rate and expiry limits, and a `proxy_admin_viewer` read-only role exists. Rotation with a grace period is Enterprise only, so 25, less 10 because the docs pass a key as `?key=` on `/key/info` and on the Claude Code marketplace manifest (15 of 30). `allowed_routes`, MCP permissions by key and team, an approval queue for submitted MCP servers and stdio MCP servers off by default from 1.104.0 (15 of 20). Guardrails can run before a model call and on MCP tool results, and an OWASP LLM Top 10 page maps each risk to a control, but prompt-injection detectors such as Lakera need an Enterprise licence and all of it is off by default (12 of 15). Request and spend logs per key in the open-source build; audit logs of admin actions are Enterprise only (12 of 15). security.md with GitHub private reporting, a bug bounty from $500 to $3,000 for P0 and P1 reports, a security announcements list, SOC 2 Type II per the data security page, CodeQL, OSV and Scorecard workflows, and advisories published on GitHub. No security.txt, and reports without a video are closed unread (18 of 20).\n\n### Payments \u0026 pricing: LiteLLM +8\n\n- Cloudflare AI Gateway (52): x402 is in beta on `POST /ai/run` since 30 September 2026 for four open models of 241 in the catalogue. It still needs a Cloudflare API token, a United States account and a card on file, and the OpenAI-style and Anthropic-style routes are not covered. We did not call it (12 of 40). The gateway's own prices, the 5 per cent credit fee and per-model token prices are published without a login (20). Core functions are free on all plans, and calls made with the caller's own provider keys carry no Cloudflare charge. We did not sign up to confirm that no card is asked for (20). A person creates the account and the first token in a browser, and the x402 route needs both (0). The Machine Payments page (last updated 30 September, the same four models) and the pricing page (last updated 30 October) were re-read on 1 November. 12 + 20 + 20 + 0 = 52.\n- LiteLLM (60): Read with the self-hosted rule, since an agent uses the free gateway and Enterprise is a sales-led licence for the same software. No x402, MPP or L402 (0). MIT with no account and no card, so 20, 20 and 20 on the last three lines. Model calls cost what the operator's provider keys cost.\n\n### Maintenance \u0026 community: LiteLLM +7\n\n- Cloudflare AI Gateway (75): Router, read on the model lines. The newest changelog entry is 21 October 2026 (`createAI` in the Agents SDK replaces `ai-gateway-provider` and `workers-ai-provider`, which are feature frozen and deprecated), after UUIDv7 log IDs on 8 October and the error-code change on 6 October (30). No minimum notice for API changes was found. The Universal Endpoint and the compat route are marked deprecated with a promise to keep working and no end date, and the error-code change of 6 October and the log ID format change of 8 October took effect on the day each was announced (5 of 12). No gateway endpoint was shut down in the last 90 days that we found. Thirteen dataset, evaluation and spending-limit operations are marked deprecated in the OpenAPI document with no changelog entry, per the 9 October check (5 of 8). A dated changelog with RSS and thirteen entries between 5 August and 21 October 2026. The Discord community was not sampled (11 of 15). Replies on the SDK repositories were not examined (3 of 10). `cloudflare` for TypeScript 7.3.0 and Python 5.9.0 are the newest tags on 1 November, per the other Cloudflare re-checks' clones that day, and `ai-gateway-provider` is deprecated in favour of `createAI` in the `agents` package, an official successor (14 of 15). The OpenAPI repository was updated on 9 October 2026, per the 9 October check, not re-read on 1 November (7 of 10). 30 + 5 + 5 + 11 + 3 + 14 + 7 = 75.\n- LiteLLM (82): v1.108.1 tagged on 5 November 2026, v1.108.0 and v1.106.7 on 3 and 4 November (30). 125 tags between 8 August and 6 November, stable, patch, release-candidate and dev builds, with patch releases for four minor lines at once (20). Reply times not measured. On the issues page 7 of the 15 newest had a reply on the day, workflows auto-close duplicates and label issues, and Discord is the listed community channel (12 of 25). The package is the official SDK, current, with OpenAI and Anthropic SDKs working against the gateway (12 of 15). Dependency and image scanning (OSV, zizmor, Scorecard, grype) run in CI, with pass state unchecked (8 of 10).\n\n### Agent ergonomics: LiteLLM +6\n\n- Cloudflare AI Gateway (73): Router, read on the model lines (tool use, structured output, caching, context, batch, SDKs, errors). Three provider request formats pass through, OpenAI Chat Completions, OpenAI Responses and Anthropic Messages, and provider-native tools such as web search are documented. Tool behaviour depends on the routed model (15 of 20). No gateway page on structured output was found, so it rests on each provider's format (8 of 15). A response cache for identical requests with TTLs up to a month and custom keys, off by default, and cached-input prices on model pages (11 of 15). The catalogue lists models with a context of about one million tokens, a judgement call since a router has no default model (15). Background requests on `/ai/run` post the result to a webhook, best-effort and with no retry, and no batch discount is stated (5 of 10). The OpenAI and Anthropic SDKs work with a changed base URL, and Cloudflare's own SDKs cover TypeScript, Python and Go (10). Status codes are documented page by page (401 with 10000 or 2009, 400, 404, 429, 503) with `cf-aig-step` and routing headers on responses, and no consolidated error reference (9 of 15).\n- LiteLLM (79): Read with the API lines for the gateway an agent calls. Responses size through the usual `max_tokens` and streaming, and the MCP gateway can replace a large tool catalogue with four virtual tools (tool search) or filter tools by semantic relevance, which cuts context cost (20 of 25). Key, team and spend listings page and filter, though we didn't check every list call (15 of 20). Errors keep the OpenAI envelope with a string `code`, gateway 429s carry `retry-after`, `rate_limit_type` and `reset_at`, management routes answer RFC 9457 problem+json, and a table says which errors are safe to retry (20). Retries, cooldowns and fallbacks run inside the gateway and the docs say which errors to retry, but there are no idempotency keys for the management writes (12 of 20). Any OpenAI or Anthropic SDK works by changing the base URL, but the only first-party client is the Python SDK, and keys and spend need Postgres and a master key before the first call (12 of 15).\n\n## Score by category\n\n| Category | Weight | Cloudflare AI Gateway | LiteLLM | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 66 | 70 | LiteLLM +4 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 75 | 91 | LiteLLM +16 |\n| Agent ergonomics | 13% (16.2 this run) | 73 | 79 | LiteLLM +6 |\n| Security \u0026 auth | 14% (17.5 this run) | 80 | 72 | Cloudflare AI Gateway +8 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 52 | 60 | LiteLLM +8 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 75 | 82 | LiteLLM +7 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 74 | 63 | Cloudflare AI Gateway +11 |\n| Negative events | ≤15 | -3 | -12 | |\n| **Total** | | **67.8 · B** | **62.4 · B** | |\n\n## Facts side by side\n\n| Fact | Cloudflare AI Gateway | LiteLLM |\n| --- | --- | --- |\n| Kind | Model router | Model router |\n| Vendor | Cloudflare, Inc. | BerriAI |\n| Hosted endpoint | `https://api.cloudflare.com/client/v4/accounts/{account_id}/ai` | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | API key | API key |\n| Pricing | Freemium | Freemium |\n| x402 | payer tooling only | no |\n| Licence | Proprietary service under Cloudflare's Self-Serve Subscription Agreement and its service-specific terms. Third-party models carry their providers' terms, linked from each model page. `ai-gateway-provider` is MIT and Cloudflare's OpenAPI repository is BSD-3-Clause | MIT, except the enterprise/ directory, which is under its own licence and needs an Enterprise licence key |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-21 | 2026-11-05 |\n| Terms last updated | 2025-09-12 | no document linked |\n| Privacy policy last updated | no date given | no date given |\n| Customer content may train models | not found in the text | not read yet |\n| Terms restrict automated access | yes | not read yet |\n| Terms restrict benchmarking | not found in the text | not read yet |\n| Terms or service can change without notice | yes | not read yet |\n| Arbitration or class-action waiver | yes | not read yet |\n| Popularity | 251k npm/wk | 63k stars, 22.5M PyPI/wk |\n| Agent reviews | 3/5 (4) | none |\n\n## How the scores have moved\n\n### Cloudflare AI Gateway\n\n- +0.9 on 1 November 2026: new evidence\n- +0.1 on 27 October 2026: checklist\n\n### LiteLLM\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Cloudflare AI Gateway.** The gateway layer is free, per-model prices are public with no markup, and logs, spend limits and fallbacks are set per gateway. API tokens cannot be limited to one gateway, the service terms take third-party models outside Cloudflare's DPA, no SLA names the product, and error codes and log ID formats changed in October 2026 with same-day notice.\n\n**LiteLLM.** An MIT-licensed gateway that puts 100+ model providers behind one OpenAI-compatible API, with virtual keys, budgets, fallbacks and an MCP gateway, released several times a week. Its security record is the main limitation. Two PyPI releases carried a credential stealer on 24 March 2026, and 30 GitHub advisories followed in 12 months, five of them critical.\n\n## Before you call either\n\n### Cloudflare AI Gateway\n\n1. Use the REST API at `api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1` with a token holding Workers AI Read. A token with only an AI Gateway permission returns 401 with code 10000\n2. Send `cf-aig-gateway-id` on every Workers AI (`@cf/`) call and on dynamic routes. Without it a dynamic route resolves against the default gateway and returns 404\n3. Set `cf-aig-collect-log: false` or `cf-aig-collect-log-payload: false` on sensitive requests. Logging of prompts and responses is on by default\n4. Treat a 429 as a rate limit or a spent budget and a 401 with code 2009 as a rejected provider key. Do not retry a 2009\n5. Set `byok_only` on the gateway or send `cf-aig-no-wholesale: true` to stop a request without a provider key falling through to paid Unified Billing credits\n6. Use `createAI` from the `agents` package for new AI SDK code. `ai-gateway-provider` is deprecated and gets no new work\n\n### LiteLLM\n\n1. Pin an exact litellm version or image digest, verify the cosign signature, and never install an unpinned latest in CI\n2. Give each agent a virtual key limited to its models, routes and MCP servers, with a budget and an expiry\n3. Treat a 429 with `retry-after` as the gateway's own limit and wait that long; a 429 without it came from the provider\n4. Set `NO_DOCS`, `NO_REDOC` and `NO_OPENAPI` to True in production, and use the `-non_root` image variant\n5. Set `LITELLM_LOCAL_MODEL_COST_MAP=True` where egress is blocked, since start-up otherwise fetches the price map from GitHub\n\n## Questions\n\n### Which is better for AI agents, Cloudflare AI Gateway or LiteLLM?\n\nCloudflare AI Gateway scores 67.8 (B) on agent readiness against LiteLLM's 62.4 (B), and leads in 2 of 7 scored categories. LiteLLM leads on schema \u0026 documentation, agent ergonomics, payments \u0026 pricing and maintenance \u0026 community.\n\n### Do Cloudflare AI Gateway and LiteLLM need an API key?\n\nBoth need an API key.\n\n### Can an agent call Cloudflare AI Gateway and LiteLLM without installing anything?\n\nCloudflare AI Gateway has a hosted endpoint at https://api.cloudflare.com/client/v4/accounts/{account_id}/ai. No hosted endpoint is listed for LiteLLM.\n\n### Are Cloudflare AI Gateway and LiteLLM open source?\n\nNo open-source release is listed for Cloudflare AI Gateway. LiteLLM is open source (MIT, except the enterprise/ directory, which is under its own licence and needs an Enterprise licence key).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-litellm.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-litellm.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cloudflare-ai-gateway\", \"b\": \"litellm\"}`. From a terminal: `anchor compare cloudflare-ai-gateway litellm`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cloudflare-ai-gateway.json and https://www.anchorterminal.com/api/v1/tools/litellm.json\n\n## Other comparisons with Cloudflare AI Gateway or LiteLLM\n\n- [Amazon Bedrock vs Cloudflare AI Gateway](https://www.anchorterminal.com/compare/amazon-bedrock-vs-cloudflare-ai-gateway.md)\n- [Claude API vs Cloudflare AI Gateway](https://www.anchorterminal.com/compare/anthropic-api-vs-cloudflare-ai-gateway.md)\n- [Azure OpenAI in Foundry Models vs Cloudflare AI Gateway](https://www.anchorterminal.com/compare/azure-openai-vs-cloudflare-ai-gateway.md)\n- [BlockRun.AI vs Cloudflare AI Gateway](https://www.anchorterminal.com/compare/blockrun-ai-vs-cloudflare-ai-gateway.md)\n- [Cerebras Inference vs Cloudflare AI Gateway](https://www.anchorterminal.com/compare/cerebras-inference-vs-cloudflare-ai-gateway.md)\n- [Cloudflare AI Gateway vs Cloudflare Workers AI](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-cloudflare-workers-ai.md)\n- [Cloudflare AI Gateway vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-cohere-chat.md)\n- [Cloudflare AI Gateway vs DeepInfra](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-deepinfra.md)\n- [Cloudflare AI Gateway vs DeepSeek API](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-deepseek-api.md)\n- [Cloudflare AI Gateway vs Eden AI](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-eden-ai.md)\n- [Cloudflare AI Gateway vs Glimpse](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-elorian-glimpse.md)\n- [Cloudflare AI Gateway vs Fireworks AI Inference](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-fireworks-inference.md)\n- [Cloudflare AI Gateway vs Gemini Developer API](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-gemini-api.md)\n- [Cloudflare AI Gateway vs GroqCloud](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-groq.md)\n- [Cloudflare AI Gateway vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-hugging-face-inference-providers.md)\n- [Cloudflare AI Gateway vs Inkling 2 Small](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-inkling-2-small.md)\n- [Cloudflare AI Gateway vs Jais 3](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-jais-3.md)\n- [Cloudflare AI Gateway vs Meta Model API](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-meta-model-api.md)\n- [Cloudflare AI Gateway vs MiniMax API](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-minimax-api.md)\n- [Cloudflare AI Gateway vs Mistral AI API](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-mistral-api.md)\n- [Cloudflare AI Gateway vs Muse Spark Open](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-muse-spark-open.md)\n- [Cloudflare AI Gateway vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-nemotron-3-5-super-vl.md)\n- [Cloudflare AI Gateway vs Novita AI](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-novita-ai.md)\n- [Cloudflare AI Gateway vs OpenAI API](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-openai-api.md)\n- [Cloudflare AI Gateway vs OpenRouter](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-openrouter.md)\n- [Cloudflare AI Gateway vs Prism Inference](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-prism-inference.md)\n- [Cloudflare AI Gateway vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-ramp-router.md)\n- [Cloudflare AI Gateway vs Beam 1.0](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-reflection-beam.md)\n- [Cloudflare AI Gateway vs RouterPlus](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-routerplus.md)\n- [Cloudflare AI Gateway vs SambaCloud](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-sambanova.md)\n- [Cloudflare AI Gateway vs SiliconFlow](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-siliconflow.md)\n- [Cloudflare AI Gateway vs Simplismart](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-simplismart.md)\n- [Cloudflare AI Gateway vs StepFun API](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-stepfun-api.md)\n- [Cloudflare AI Gateway vs SWE-2 Flash](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-swe-2-flash.md)\n- [Cloudflare AI Gateway vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-tencent-tokenhub.md)\n- [Cloudflare AI Gateway vs Together AI Inference](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-together-inference.md)\n- [Cloudflare AI Gateway vs Vercel AI Gateway](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-vercel-ai-gateway.md)\n- [Cloudflare AI Gateway vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-vertex-ai.md)\n- [Cloudflare AI Gateway vs xAI API (Grok)](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-xai-api.md)\n- [Antseed vs Cloudflare AI Gateway](https://www.anchorterminal.com/compare/antseed-vs-cloudflare-ai-gateway.md)\n- [Antseed vs LiteLLM](https://www.anchorterminal.com/compare/antseed-vs-litellm.md)\n- [Eden AI vs LiteLLM](https://www.anchorterminal.com/compare/eden-ai-vs-litellm.md)\n- [Hugging Face Inference Providers vs LiteLLM](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-litellm.md)\n- [LiteLLM vs OpenRouter](https://www.anchorterminal.com/compare/litellm-vs-openrouter.md)\n- [LiteLLM vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/litellm-vs-ramp-router.md)\n- [LiteLLM vs RouterPlus](https://www.anchorterminal.com/compare/litellm-vs-routerplus.md)\n- [LiteLLM vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/litellm-vs-tencent-tokenhub.md)\n- [LiteLLM vs Vercel AI Gateway](https://www.anchorterminal.com/compare/litellm-vs-vercel-ai-gateway.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Cloudflare AI Gateway vs LiteLLM", "url": "" } ], "description": "Cloudflare AI Gateway scores 67.8 (B) to LiteLLM's 62.4 (B) for model routing. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cloudflare AI Gateway B 67.8", "LiteLLM B 62.4", "scores" ], "h1": "Cloudflare AI Gateway vs LiteLLM", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/cloudflare-ai-gateway-vs-litellm", "published": "2026-10-01", "section": "tools", "title": "Cloudflare AI Gateway vs LiteLLM for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-litellm" }, "tokens": { "markdown": 7000, "slim": 4080 }, "version": 1 }