{
  "data": {
    "a": {
      "slug": "cloudflare-workers-ai",
      "name": "Cloudflare Workers AI",
      "vendor": "Cloudflare, Inc.",
      "vendorUrl": "https://www.cloudflare.com",
      "kind": "model",
      "category": "inference",
      "summary": "Workers AI is Cloudflare's serverless inference service for open-weight models, covering text generation, embeddings, images and speech. Agents call it through the Cloudflare REST API, OpenAI-compatible endpoints or a Workers binding.",
      "url": "https://www.anchorterminal.com/tools/cloudflare-workers-ai",
      "markdownUrl": "https://www.anchorterminal.com/tools/cloudflare-workers-ai.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/cloudflare-workers-ai.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/cloudflare-workers-ai.json",
      "repo": "https://github.com/cloudflare/api-schemas",
      "license": "Proprietary service under Cloudflare's Self-Serve Subscription Agreement. Each hosted model carries its own open-weight licence, linked from its model page. The `cloudflare` SDKs are Apache-2.0, `workers-ai-provider` is MIT and the OpenAPI repository is BSD-3-Clause",
      "transports": [
        "http"
      ],
      "remoteUrl": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai",
      "packages": [
        {
          "registry": "npm",
          "name": "workers-ai-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, with the Workers AI Read or Workers AI Edit permission on an account. Tokens can carry an expiry and an IP address filter. Inside a Worker the `AI` binding needs no token. The API reference also accepts the older global API key with an account email. Later tokens can be created through the API with an existing token.",
      "pricing": "freemium",
      "pricingNotes": "$0.011 per 1,000 neurons, shown per model as token, image or audio prices, for example Gemma 4 26B at $0.10 in and $0.30 out per 1M tokens. 10,000 neurons a day are free on the Workers Free and Paid plans, and going past that needs Workers Paid, from $5 a month. Seven frontier models need Workers Paid or prepaid AI Gateway credits. A Free plan account starts without a contract (https://developers.cloudflare.com/workers-ai/platform/pricing/, checked 2026-10-09).",
      "priceSummary": "from $0.0605 / 1M in",
      "where": "hosted",
      "x402": {
        "level": "partial",
        "evidence": "AI Gateway 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 per-model route `/ai/run/{model_name}` and the OpenAI-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": 379824,
        "pypiWeekly": null,
        "asOf": "2026-10-09"
      },
      "docsUrl": "https://developers.cloudflare.com/workers-ai/",
      "rateLimitsUrl": "https://developers.cloudflare.com/workers-ai/platform/limits/",
      "llmsTxt": "https://developers.cloudflare.com/workers-ai/llms.txt",
      "openapi": "https://raw.githubusercontent.com/cloudflare/api-schemas/main/openapi.json",
      "capabilities": [
        "inference.llm",
        "inference.open-weights",
        "embed.text",
        "rerank",
        "image.generate",
        "speech.stt",
        "speech.tts",
        "compute.batch"
      ],
      "tags": [
        "hosted",
        "model",
        "open-weights",
        "usage-based",
        "free-tier",
        "x402",
        "openapi",
        "llms-txt",
        "openai-compatible",
        "batch",
        "prompt-caching",
        "typescript",
        "python",
        "go",
        "status-page",
        "bug-bounty"
      ],
      "lastRelease": "2026-10-01",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 68.3,
        "grade": "B",
        "agentReady": false,
        "rank": 227,
        "ranked": true,
        "rankOf": 1010,
        "categoryRank": 7,
        "methodology": "0.4",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 75,
          "maintenance": 72,
          "payments": 52,
          "reliability": 66,
          "schema": 80,
          "security": 77,
          "transparency": 76
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-09"
        },
        "negative": -3,
        "negativeNotes": [
          "28 July 2026. Kimi K2.6, Kimi K2.7 Code and GLM-5.2 began returning 403 (code 5035) on the Workers Free plan on the day of the notice, with no advance warning found. Three points (https://developers.cloudflare.com/changelog/post/2026-07-28-models-require-workers-paid/)."
        ],
        "verdict": "Per-model prices, rate limits and JSON Schemas are public, 10,000 neurons a day are free, and x402 payment is in beta on `/ai/run` for four models. No SLA was found, three models moved to paid-only access on 28 July 2026 with no notice, and several docs pages still use a model retired in May.",
        "bestFor": "Agents that already run on Cloudflare Workers, or that want open-weight chat, embedding, reranking, speech and image models behind one token with a free daily allowance.",
        "strengths": [
          "Per-model token prices, cached-input prices and neuron rates are published without a login, with 10,000 neurons a day free on the Workers Free plan",
          "x402 payment (Machine Payments, beta since 30 September 2026) works on `POST /ai/run` for four open models",
          "Rate limits are published per task type, and a 429 separates a spent free allocation (3036) from capacity (3040)",
          "API tokens are limited to Workers AI permissions on an account, with optional expiry and IP address filtering",
          "DeepSeek V4 and GLM-5.3 run with a 1,048,576-token context, with prefix caching and discounted cached input"
        ],
        "weaknesses": [
          "No SLA for Workers AI was found in the docs or the agreements read",
          "Three models moved to paid-only access on 28 July 2026, the day of the notice, and Free plan calls to them return 403",
          "Eighteen models were retired on 30 May 2026 with 22 days' notice, and no minimum notice period is published",
          "The REST quick start, the OpenAI-compatibility page and the JSON Mode model list still name models on the 30 May 2026 retirement list",
          "The x402 route still needs a Cloudflare API token, a United States account and a card on file"
        ],
        "agentNotes": [
          "Check the model page before calling. Seven models need Workers Paid or AI Gateway credits and return 403 with code 5035 on the Free plan",
          "Read the internal code on a 429. 3036 means the day's 10,000 free neurons are spent until 00:00 UTC, 3040 means capacity, so retry later",
          "Set `options.rejectIfBusy` to fail fast, or add `?queueRequest=true` for the batch route when the answer can wait",
          "Send the same `x-session-affinity` value on every turn of a session to reach the prefix cache and the cached-input price",
          "Keep paid frontier models under 20 requests a minute per model, or 50 with prepaid AI Gateway credits"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "0.4",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 68.3
          }
        ],
        "editorialScores": {
          "ergonomics": 75,
          "maintenance": 72,
          "payments": 52,
          "reliability": 66,
          "schema": 80,
          "security": 77,
          "transparency": 56
        },
        "provenanceScore": 95
      },
      "connect": {
        "http": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run/@cf/google/gemma-4-26b-a4b-it \\\n  -X POST \\\n  -H \"Authorization: Bearer $CLOUDFLARE_AUTH_TOKEN\" \\\n  -d '{ \"messages\": [{ \"role\": \"system\", \"content\": \"You are a friendly assistant\" }, { \"role\": \"user\", \"content\": \"Why is pizza so good\" }]}'",
        "x402": "curl -iX POST \"https://api.cloudflare.com/client/v4/accounts/$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-workers-ai"
      },
      "sameCompany": [
        "cloudflare-ai-gateway",
        "cloudflare-sandbox-sdk",
        "cloudflare-web-search",
        "cloudflare-mcp",
        "cloudflare-email-service",
        "cloudflare-r2",
        "cloudflare-clef"
      ],
      "area": "models",
      "unitPrices": [
        {
          "item": "Whisper large v3 turbo, speech to text",
          "unit": "audio-minute",
          "usd": 0.0005,
          "note": "46.63 neurons"
        },
        {
          "item": "Deepgram Nova-3, speech to text",
          "unit": "audio-minute",
          "usd": 0.0052,
          "note": "472.73 neurons. $0.0092 over WebSocket"
        },
        {
          "item": "Deepgram Aura-1, text to speech",
          "unit": "1m-chars",
          "usd": 15,
          "note": "listed as $0.015 per 1,000 characters"
        },
        {
          "item": "Deepgram Aura-2, text to speech",
          "unit": "1m-chars",
          "usd": 30,
          "note": "listed as $0.030 per 1,000 characters, English and Spanish"
        }
      ],
      "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/changelog/product/workers-ai/",
        "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 Workers AI data usage page cites it and the Enterprise Subscription Agreement as the governing documents.",
          "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.",
          "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 to match the other Cloudflare listings.",
          "The endpoint is on api.cloudflare.com.",
          "The status page lists Workers AI as its own component, operational on 9 October 2026.",
          "RDAP for cloudflare.com gives a registration date of 2009-02-17.",
          "The Workers AI changelog page (https://developers.cloudflare.com/workers-ai/changelog/) stops at 16 June 2026, so the product changelog is recorded."
        ],
        "score": 95
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/cloudflare-workers-ai.json",
      "live": {
        "slug": "cloudflare-workers-ai",
        "probe": {
          "target": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai",
          "method": "get",
          "lastAt": "2026-10-14T01:19:38.215267006Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 13,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 19,
          "p95ms24h": 40,
          "samples24h": 248,
          "samples30d": 1088,
          "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": 14,
              "ok": 14
            }
          ]
        },
        "vendorStatus": {
          "page": "https://www.cloudflarestatus.com",
          "indicator": "major",
          "summary": "Partial System Outage",
          "checkedAt": "2026-10-14T01:21:19.093058828Z"
        },
        "versions": [
          {
            "registry": "npm",
            "name": "cloudflare",
            "version": "7.3.0",
            "seenAt": "2026-10-13T22:49:41.080423711Z"
          },
          {
            "registry": "npm",
            "name": "workers-ai-provider",
            "version": "4.0.0",
            "seenAt": "2026-10-13T22:49:40.306685498Z"
          },
          {
            "registry": "pypi",
            "name": "cloudflare",
            "version": "5.9.0",
            "released": "2026-10-03",
            "seenAt": "2026-10-13T22:49:42.327389695Z"
          }
        ],
        "githubStars": 194,
        "npmWeekly": 349168,
        "pypiWeekly": 463417,
        "securityTxt": {
          "url": "https://cloudflare.com/.well-known/security.txt",
          "state": "valid",
          "checkedAt": "2026-10-13T15:45:20.306139352Z"
        },
        "llmsTxt": {
          "url": "https://developers.cloudflare.com/workers-ai/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-10-13T14:11:20.363982076Z"
        },
        "domain": {
          "domain": "cloudflare.com",
          "registered": "2009-02-17",
          "source": "https://rdap.verisign.com/com/v1/domain/cloudflare.com",
          "checkedAt": "2026-10-11T13:20:21.49951473Z"
        },
        "pages": [
          {
            "url": "https://developers.cloudflare.com/changelog/product/workers-ai/",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-10-13T20:13:19.614772028Z",
            "changedAt": "2026-10-13T20:13:19.614772028Z",
            "fingerprint": "f6fafc2068f0"
          },
          {
            "url": "https://developers.cloudflare.com/changelog/post/2026-05-08-planned-model-deprecations/",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-10-13T20:13:11.614348222Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "456d5c31e53a"
          },
          {
            "url": "https://developers.cloudflare.com/changelog/post/2026-07-28-models-require-workers-paid/",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-10-13T20:13:13.579591378Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "23663c817503"
          }
        ],
        "updatedAt": "2026-10-14T01:21:19.093058828Z"
      }
    },
    "answer": "Cloudflare Workers AI scores 68.3 (B) on agent readiness against RouterPlus's 51.2 (D), and leads in every scored category.",
    "b": {
      "slug": "routerplus",
      "name": "RouterPlus",
      "vendor": "RouterPlus",
      "vendorUrl": "https://routerplus.com",
      "kind": "router",
      "category": "inference",
      "summary": "RouterPlus is an LLM gateway that puts Claude, GPT and decision models behind one API key and a prepaid balance, with OpenAI-compatible and Anthropic-compatible endpoints at the providers' list prices.",
      "url": "https://www.anchorterminal.com/tools/routerplus",
      "markdownUrl": "https://www.anchorterminal.com/tools/routerplus.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/routerplus.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/routerplus.json",
      "license": "Closed service. No terms of service for the gateway were found on routerplus.com or app.routerplus.com on 13 October 2026. The only terms on the site govern the capacity request form and name EVO HQ Inc, a Delaware corporation (https://routerplus.com/capacity/terms/).",
      "transports": [
        "http"
      ],
      "remoteUrl": "https://api.routerplus.com/v1",
      "packages": [],
      "auth": "api-key",
      "authNotes": "A `tm_vk_` virtual key, sent as `Authorization: Bearer` or `x-api-key` on every route. A person signs up in the browser through Clerk with email verification, and the first key is shown once after sign-in. More keys come from the console or from `POST /api/identity/keys` with a console session. The programmatic signup route `POST /v1/signup` was removed and returns 404 (https://app.routerplus.com/docs/authentication.md, https://app.routerplus.com/docs/api-signup.md).",
      "pricing": "usage",
      "pricingNotes": "Provider list prices per 1M tokens with no markup, paid from prepaid credits. Purchases start at $10, and RouterPlus matches the first $100 of purchases for eligible accounts. Signup adds no free credit. Inference through the caller's own provider keys (BYOK) carries no RouterPlus charge and needs no credit. Prices are public at https://app.routerplus.com/api/models.json (https://app.routerplus.com/docs/pricing.md).",
      "priceSummary": "0% fee",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in https://app.routerplus.com/llms-full.txt, checked 13 October 2026. Calls draw on a prepaid balance bought in the console's Billing page.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-13"
      },
      "docsUrl": "https://app.routerplus.com/docs/overview",
      "llmsTxt": "https://app.routerplus.com/llms.txt",
      "capabilities": [
        "inference.router",
        "inference.llm",
        "inference.decision",
        "image.generate"
      ],
      "tags": [
        "hosted",
        "router",
        "closed-source",
        "usage-priced",
        "prepaid",
        "llms-txt",
        "openai-compatible",
        "anthropic-compatible",
        "streaming"
      ],
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 51.2,
        "grade": "D",
        "agentReady": false,
        "rank": 777,
        "ranked": true,
        "rankOf": 1010,
        "categoryRank": 17,
        "methodology": "0.4",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 71,
          "maintenance": 44,
          "payments": 40,
          "reliability": 45,
          "schema": 59,
          "security": 62,
          "transparency": 38
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-13"
        },
        "negative": -2,
        "negativeNotes": [
          "Misleading claim, seen 13 October 2026. The banner on https://routerplus.com/ reads \"Try RouterPlus with free credits\" and links to the playground, while the quickstart (https://app.routerplus.com/docs/quickstart.md) says \"Signup does not add free credit\" and the playground bills the organisation's credits (https://app.routerplus.com/docs/playground.md). Only an invitation link adds credit. -2."
        ],
        "verdict": "The docs are written for agents, every model price is public, and each response carries its own cost. No terms of service, privacy policy, status page or changelog were found. Signup adds no free credit, and the chat catalogue is Claude and GPT only.",
        "bestFor": "Teams that call Claude and GPT models from one key and want the cost of every call in the response, with their own provider keys where they have them.",
        "strengths": [
          "llms.txt, llms-full.txt and a Markdown copy of every page, with an integration guide written for coding agents",
          "Every billed response carries `usage.cost` in USD, and `GET /v1/generation` lists each attempt behind a request",
          "Any chat model answers on both the OpenAI-compatible and Anthropic-compatible surfaces, with the format translated by the gateway",
          "Typed errors with a stable `error_type`, an origin header, and `retry-after` on rate-limit 429s",
          "The gateway stores no prompt or completion content for ordinary accounts, and BYOK inference carries no RouterPlus charge"
        ],
        "weaknesses": [
          "No terms of service, privacy policy, status page, changelog or security.txt found for the gateway",
          "The chat catalogue on 13 October 2026 was nine Claude and ten GPT models, all marked as retained by the provider with no ZDR",
          "Signup adds no free credit, purchases start at $10, and keys stay at 20 requests a minute until the first purchase",
          "No idempotency keys, no batch route and no embeddings, and the `zdr` and `regions` filters remove every marketplace route",
          "Optimize, the eval-based model search the homepage leads with, is paused"
        ],
        "agentNotes": [
          "Send `max_tokens` on every request. Without it the balance hold assumes up to 32,768 output tokens and can return `insufficient_quota` on a small balance",
          "Switch on `error_type`. Retry `rate_limit` after `retry-after`, and stop on `insufficient_quota`, which needs a person to add credit or raise a cap",
          "Don't add a retry loop on top of the SDK's. There is no idempotency key, so a retry that reaches a provider is billed again",
          "Copy model ids from `GET /v1/models` or /api/models.json. An unknown id is a 404 and the gateway never substitutes one",
          "Use `/v1/messages` for Claude when you need `thinking` or server tools, and `/v1/chat/completions` with `response_format` only for GPT ids"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "D",
            "methodology": "0.4",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 51.2
          }
        ],
        "editorialScores": {
          "ergonomics": 71,
          "maintenance": 44,
          "payments": 40,
          "reliability": 45,
          "schema": 59,
          "security": 62,
          "transparency": 26
        },
        "provenanceScore": 50
      },
      "connect": {
        "http": "curl -N https://api.routerplus.com/v1/chat/completions \\\n  -H \"Authorization: Bearer $TM_API_KEY\" \\\n  -H \"content-type: application/json\" \\\n  -d '{\"model\":\"claude-haiku-4-5\",\"stream\":true,\"max_tokens\":60,\"messages\":[{\"role\":\"user\",\"content\":\"hello\"}]}'"
      },
      "letme": {
        "capability": "https://letme.dev/inference.router",
        "tool": "https://letme.dev/routerplus"
      },
      "area": "models",
      "unitPrices": [
        {
          "item": "Markup on provider token prices",
          "unit": "pct",
          "usd": 0,
          "note": "Pass-through per the pricing docs. Credits are bought in $10 steps or more"
        },
        {
          "item": "Claude Opus 5.5 input",
          "unit": "1m-tokens",
          "usd": 4,
          "note": "claude-opus-5-5, served by Anthropic's API"
        },
        {
          "item": "Claude Opus 5.5 output",
          "unit": "1m-tokens",
          "usd": 20
        },
        {
          "item": "GPT-6.1 Sol input",
          "unit": "1m-tokens",
          "usd": 2,
          "note": "gpt-6.1-sol, served by OpenAI's API, 1,050,000-token context"
        },
        {
          "item": "GPT-6.1 Sol output",
          "unit": "1m-tokens",
          "usd": 10
        },
        {
          "item": "Anthropic web search server tool",
          "unit": "1k-requests",
          "usd": 10,
          "note": "$10 per 1,000 searches, Anthropic's price, on top of tokens"
        }
      ],
      "provenance": {
        "legalEntity": "EVO HQ Inc",
        "domain": "routerplus.com",
        "domainRegistered": "2014-04-15",
        "endpointOnVendorDomain": true,
        "terms": "",
        "privacy": "",
        "statusPage": "",
        "changelog": "",
        "securityTxt": "none",
        "checked": "2026-10-13",
        "notes": [
          "EVO HQ Inc, a Delaware corporation, is named only in the terms of the capacity request form at https://routerplus.com/capacity/terms/, which govern form submissions and not the gateway. The footer elsewhere reads © 2026 RouterPlus.",
          "No terms of service or privacy policy for the gateway were found. /terms, /privacy and /legal/terms answer 404 on both hosts, the signup page links neither, and the footer's Privacy and Security links open an email to founders@evo-hq.com. The docs' data policy page (https://app.routerplus.com/docs/data-policy.md) is the only data statement for the gateway.",
          "No status page. Model pages such as https://app.routerplus.com/models/claude-haiku-4-5 show per-provider uptime over the last 24 hours, with no incident history. A request to status.routerplus.com failed at our proxy with a 502, so whether it exists is unchecked.",
          "No changelog found. /changelog and /docs/changelog.md answer 404, and the blog's newest post is dated 13 August 2026.",
          "routerplus.com/.well-known/security.txt and app.routerplus.com/.well-known/security.txt answer 404.",
          "RDAP gives 15 April 2014 as the registration date of routerplus.com and 2 October 2026 as its last change, so the registration may predate the current owner."
        ],
        "score": 50
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/routerplus.json",
      "live": {
        "slug": "routerplus",
        "probe": {
          "target": "https://api.routerplus.com/v1",
          "method": "get",
          "lastAt": "2026-10-14T01:19:55.653579676Z",
          "lastOk": true,
          "lastStatus": 401,
          "lastMs": 638,
          "lastNote": "asks for credentials",
          "authRequired": true,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 645,
          "p95ms24h": 1293,
          "samples24h": 18,
          "samples30d": 18,
          "days": [
            {
              "date": "2026-10-13",
              "probes": 4,
              "ok": 4
            },
            {
              "date": "2026-10-14",
              "probes": 14,
              "ok": 14
            }
          ]
        },
        "updatedAt": "2026-10-14T01:19:55.653579676Z"
      }
    },
    "facts": [
      {
        "a": "Model API",
        "b": "Model router",
        "name": "Kind"
      },
      {
        "a": "Cloudflare, Inc.",
        "b": "RouterPlus",
        "name": "Vendor"
      },
      {
        "a": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai",
        "b": "https://api.routerplus.com/v1",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP",
        "b": "HTTP",
        "name": "Transports"
      },
      {
        "a": "API key",
        "b": "API key",
        "name": "Auth"
      },
      {
        "a": "Freemium",
        "b": "Pay per use",
        "name": "Pricing"
      },
      {
        "a": "payer tooling only",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Proprietary service under Cloudflare's Self-Serve Subscription Agreement. Each hosted model carries its own open-weight licence, linked from its model page. The `cloudflare` SDKs are Apache-2.0, `workers-ai-provider` is MIT and the OpenAPI repository is BSD-3-Clause",
        "b": "Closed service. No terms of service for the gateway were found on routerplus.com or app.routerplus.com on 13 October 2026. The only terms on the site govern the capacity request form and name EVO HQ Inc, a Delaware corporation (https://routerplus.com/capacity/terms/).",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "2026-10-01",
        "b": "none",
        "name": "Last release"
      },
      {
        "a": "2025-09-12",
        "b": "no document linked",
        "name": "Terms last updated"
      },
      {
        "a": "no date given",
        "b": "no document linked",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not found in the text",
        "b": "",
        "name": "Customer content may train models"
      },
      {
        "a": "yes",
        "b": "",
        "name": "Terms restrict automated access"
      },
      {
        "a": "not found in the text",
        "b": "",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "yes",
        "b": "",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "yes",
        "b": "",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "380k npm/wk",
        "b": "none",
        "name": "Popularity"
      }
    ],
    "faq": [
      {
        "answer": "Cloudflare Workers AI scores 68.3 (B) on agent readiness against RouterPlus's 51.2 (D), and leads in every scored category.",
        "question": "Which is better for AI agents, Cloudflare Workers AI or RouterPlus?"
      },
      {
        "answer": "Both need an API key.",
        "question": "Do Cloudflare Workers AI and RouterPlus need an API key?"
      },
      {
        "answer": "Yes. Cloudflare Workers AI has a hosted endpoint at https://api.cloudflare.com/client/v4/accounts/{account_id}/ai and RouterPlus at https://api.routerplus.com/v1.",
        "question": "Can an agent call Cloudflare Workers AI and RouterPlus without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 66 against 45",
          "Schema \u0026 documentation, 80 against 59",
          "Security \u0026 auth, 77 against 62",
          "Payments \u0026 pricing, 52 against 40",
          "Maintenance \u0026 community, 72 against 44",
          "Transparency \u0026 trust, 76 against 38"
        ],
        "also": null,
        "goodFor": "Agents that already run on Cloudflare Workers, or that want open-weight chat, embedding, reranking, speech and image models behind one token with a free daily allowance.",
        "slug": "cloudflare-workers-ai",
        "watchFor": "No SLA for Workers AI was found in the docs or the agreements read"
      },
      {
        "aheadOn": null,
        "also": null,
        "goodFor": "Teams that call Claude and GPT models from one key and want the cost of every call in the response, with their own provider keys where they have them.",
        "slug": "routerplus",
        "watchFor": "No terms of service, privacy policy, status page, changelog or security.txt found for the gateway"
      }
    ],
    "job": {
      "capability": "inference.llm",
      "name": "LLM inference"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-cloudflare-workers-ai.json",
        "title": "Claude API vs Cloudflare Workers AI",
        "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-cloudflare-workers-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-routerplus.json",
        "title": "Claude API vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antseed-vs-cloudflare-workers-ai.json",
        "title": "Antseed vs Cloudflare Workers AI",
        "url": "https://www.anchorterminal.com/compare/antseed-vs-cloudflare-workers-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-cloudflare-workers-ai.json",
        "title": "BlockRun.AI vs Cloudflare Workers AI",
        "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-cloudflare-workers-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-routerplus.json",
        "title": "BlockRun.AI vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-routerplus"
      },
      {
        "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-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-workers-ai-vs-cohere-chat.json",
        "title": "Cloudflare Workers AI vs Cohere Chat API (Command models)",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-cohere-chat"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-deepinfra.json",
        "title": "Cloudflare Workers AI vs DeepInfra",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-deepinfra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-deepseek-api.json",
        "title": "Cloudflare Workers AI vs DeepSeek API",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-deepseek-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-gemini-api.json",
        "title": "Cloudflare Workers AI vs Gemini Developer API",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-gemini-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-groq.json",
        "title": "Cloudflare Workers AI vs GroqCloud",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-groq"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-meta-model-api.json",
        "title": "Cloudflare Workers AI vs Meta Model API",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-meta-model-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-mistral-api.json",
        "title": "Cloudflare Workers AI vs Mistral AI API",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-mistral-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-novita-ai.json",
        "title": "Cloudflare Workers AI vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-novita-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-openai-api.json",
        "title": "Cloudflare Workers AI vs OpenAI API",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-openai-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-openrouter.json",
        "title": "Cloudflare Workers AI vs OpenRouter",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-openrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-prism-inference.json",
        "title": "Cloudflare Workers AI vs Prism Inference",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-prism-inference"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-sambanova.json",
        "title": "Cloudflare Workers AI vs SambaCloud",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-sambanova"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-siliconflow.json",
        "title": "Cloudflare Workers AI vs SiliconFlow",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-siliconflow"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-stepfun-api.json",
        "title": "Cloudflare Workers AI vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-routerplus.json",
        "title": "Cohere Chat API (Command models) vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepinfra-vs-routerplus.json",
        "title": "DeepInfra vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/deepinfra-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-routerplus.json",
        "title": "DeepSeek API vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-api-vs-routerplus.json",
        "title": "Gemini Developer API vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/gemini-api-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/groq-vs-routerplus.json",
        "title": "GroqCloud vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/groq-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-routerplus.json",
        "title": "Meta Model API vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/mistral-api-vs-routerplus.json",
        "title": "Mistral AI API vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/mistral-api-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-routerplus.json",
        "title": "Novita AI vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/openai-api-vs-routerplus.json",
        "title": "OpenAI API vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/openai-api-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/openrouter-vs-routerplus.json",
        "title": "OpenRouter vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/openrouter-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/prism-inference-vs-routerplus.json",
        "title": "Prism Inference vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/prism-inference-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/routerplus-vs-sambanova.json",
        "title": "RouterPlus vs SambaCloud",
        "url": "https://www.anchorterminal.com/compare/routerplus-vs-sambanova"
      },
      {
        "json": "https://www.anchorterminal.com/compare/routerplus-vs-siliconflow.json",
        "title": "RouterPlus vs SiliconFlow",
        "url": "https://www.anchorterminal.com/compare/routerplus-vs-siliconflow"
      },
      {
        "json": "https://www.anchorterminal.com/compare/routerplus-vs-stepfun-api.json",
        "title": "RouterPlus vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/routerplus-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antseed-vs-routerplus.json",
        "title": "Antseed vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/antseed-vs-routerplus"
      }
    ],
    "scores": [
      {
        "by": 21,
        "cloudflare-workers-ai": 66,
        "edge": "cloudflare-workers-ai",
        "key": "reliability",
        "name": "Reliability",
        "routerplus": 45,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 21,
        "cloudflare-workers-ai": 80,
        "edge": "cloudflare-workers-ai",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "routerplus": 59,
        "weight": 13
      },
      {
        "by": 4,
        "cloudflare-workers-ai": 75,
        "edge": "cloudflare-workers-ai",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "routerplus": 71,
        "weight": 13
      },
      {
        "by": 15,
        "cloudflare-workers-ai": 77,
        "edge": "cloudflare-workers-ai",
        "key": "security",
        "name": "Security \u0026 auth",
        "routerplus": 62,
        "weight": 14
      },
      {
        "by": 12,
        "cloudflare-workers-ai": 52,
        "edge": "cloudflare-workers-ai",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "routerplus": 40,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 28,
        "cloudflare-workers-ai": 72,
        "edge": "cloudflare-workers-ai",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "routerplus": 44,
        "weight": 7
      },
      {
        "by": 38,
        "cloudflare-workers-ai": 76,
        "edge": "cloudflare-workers-ai",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "routerplus": 38,
        "weight": 7
      }
    ],
    "summary": "Cloudflare Workers AI scores 68.3 (B) on agent readiness against RouterPlus's 51.2 (D), and leads in every scored category. Both do llm inference.",
    "verdicts": {
      "cloudflare-workers-ai": "Per-model prices, rate limits and JSON Schemas are public, 10,000 neurons a day are free, and x402 payment is in beta on `/ai/run` for four models. No SLA was found, three models moved to paid-only access on 28 July 2026 with no notice, and several docs pages still use a model retired in May.",
      "routerplus": "The docs are written for agents, every model price is public, and each response carries its own cost. No terms of service, privacy policy, status page or changelog were found. Signup adds no free credit, and the chat catalogue is Claude and GPT only."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-routerplus",
    "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-routerplus.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-routerplus.md",
    "slim": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-routerplus.min.md"
  },
  "markdown": "Cloudflare Workers AI scores 68.3 (B) on agent readiness against RouterPlus's 51.2 (D), and leads in every scored category. Both do llm inference.\n\n- Cloudflare Workers AI: grade B, 68.3/100, rank #227 of 1010. Markdown https://www.anchorterminal.com/tools/cloudflare-workers-ai.md · JSON https://www.anchorterminal.com/api/v1/tools/cloudflare-workers-ai.json\n- RouterPlus: grade D, 51.2/100, rank #777 of 1010. Markdown https://www.anchorterminal.com/tools/routerplus.md · JSON https://www.anchorterminal.com/api/v1/tools/routerplus.json\n- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 190 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### Cloudflare Workers AI (B)\n\nGood for: Agents that already run on Cloudflare Workers, or that want open-weight chat, embedding, reranking, speech and image models behind one token with a free daily allowance.\n\nAhead on:\n- Reliability, 66 against 45\n- Schema \u0026 documentation, 80 against 59\n- Security \u0026 auth, 77 against 62\n- Payments \u0026 pricing, 52 against 40\n- Maintenance \u0026 community, 72 against 44\n- Transparency \u0026 trust, 76 against 38\n\nWatch for: No SLA for Workers AI was found in the docs or the agreements read\n\n### RouterPlus (D)\n\nGood for: Teams that call Claude and GPT models from one key and want the cost of every call in the response, with their own provider keys where they have them.\n\nWatch for: No terms of service, privacy policy, status page, changelog or security.txt found for the gateway\n\n\n## Score by category\n\n| Category | Weight | Cloudflare Workers AI | RouterPlus | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 66 | 45 | Cloudflare Workers AI +21 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 80 | 59 | Cloudflare Workers AI +21 |\n| Agent ergonomics | 13% (16.2 this run) | 75 | 71 | Cloudflare Workers AI +4 |\n| Security \u0026 auth | 14% (17.5 this run) | 77 | 62 | Cloudflare Workers AI +15 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 52 | 40 | Cloudflare Workers AI +12 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 72 | 44 | Cloudflare Workers AI +28 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 76 | 38 | Cloudflare Workers AI +38 |\n| Negative events | ≤15 | -3 | -2 | |\n| **Total** | | **68.3 · B** | **51.2 · D** | |\n\n## Facts side by side\n\n| Fact | Cloudflare Workers AI | RouterPlus |\n| --- | --- | --- |\n| Kind | Model API | Model router |\n| Vendor | Cloudflare, Inc. | RouterPlus |\n| Hosted endpoint | `https://api.cloudflare.com/client/v4/accounts/{account_id}/ai` | `https://api.routerplus.com/v1` |\n| Transports | HTTP | HTTP |\n| Auth | API key | API key |\n| Pricing | Freemium | Pay per use |\n| x402 | payer tooling only | no |\n| Licence | Proprietary service under Cloudflare's Self-Serve Subscription Agreement. Each hosted model carries its own open-weight licence, linked from its model page. The `cloudflare` SDKs are Apache-2.0, `workers-ai-provider` is MIT and the OpenAPI repository is BSD-3-Clause | Closed service. No terms of service for the gateway were found on routerplus.com or app.routerplus.com on 13 October 2026. The only terms on the site govern the capacity request form and name EVO HQ Inc, a Delaware corporation (https://routerplus.com/capacity/terms/). |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-01 | none |\n| Terms last updated | 2025-09-12 | no document linked |\n| Privacy policy last updated | no date given | no document linked |\n| Customer content may train models | not found in the text |  |\n| Terms restrict automated access | yes |  |\n| Terms restrict benchmarking | not found in the text |  |\n| Terms or service can change without notice | yes |  |\n| Arbitration or class-action waiver | yes |  |\n| Popularity | 380k npm/wk | none |\n\n## Verdicts\n\n**Cloudflare Workers AI.** Per-model prices, rate limits and JSON Schemas are public, 10,000 neurons a day are free, and x402 payment is in beta on `/ai/run` for four models. No SLA was found, three models moved to paid-only access on 28 July 2026 with no notice, and several docs pages still use a model retired in May.\n\n**RouterPlus.** The docs are written for agents, every model price is public, and each response carries its own cost. No terms of service, privacy policy, status page or changelog were found. Signup adds no free credit, and the chat catalogue is Claude and GPT only.\n\n## Before you call either\n\n### Cloudflare Workers AI\n\n1. Check the model page before calling. Seven models need Workers Paid or AI Gateway credits and return 403 with code 5035 on the Free plan\n2. Read the internal code on a 429. 3036 means the day's 10,000 free neurons are spent until 00:00 UTC, 3040 means capacity, so retry later\n3. Set `options.rejectIfBusy` to fail fast, or add `?queueRequest=true` for the batch route when the answer can wait\n4. Send the same `x-session-affinity` value on every turn of a session to reach the prefix cache and the cached-input price\n5. Keep paid frontier models under 20 requests a minute per model, or 50 with prepaid AI Gateway credits\n\n### RouterPlus\n\n1. Send `max_tokens` on every request. Without it the balance hold assumes up to 32,768 output tokens and can return `insufficient_quota` on a small balance\n2. Switch on `error_type`. Retry `rate_limit` after `retry-after`, and stop on `insufficient_quota`, which needs a person to add credit or raise a cap\n3. Don't add a retry loop on top of the SDK's. There is no idempotency key, so a retry that reaches a provider is billed again\n4. Copy model ids from `GET /v1/models` or /api/models.json. An unknown id is a 404 and the gateway never substitutes one\n5. Use `/v1/messages` for Claude when you need `thinking` or server tools, and `/v1/chat/completions` with `response_format` only for GPT ids\n\n## Questions\n\n### Which is better for AI agents, Cloudflare Workers AI or RouterPlus?\n\nCloudflare Workers AI scores 68.3 (B) on agent readiness against RouterPlus's 51.2 (D), and leads in every scored category.\n\n### Do Cloudflare Workers AI and RouterPlus need an API key?\n\nBoth need an API key.\n\n### Can an agent call Cloudflare Workers AI and RouterPlus without installing anything?\n\nYes. Cloudflare Workers AI has a hosted endpoint at https://api.cloudflare.com/client/v4/accounts/{account_id}/ai and RouterPlus at https://api.routerplus.com/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-routerplus.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-routerplus.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cloudflare-workers-ai\", \"b\": \"routerplus\"}`. From a terminal: `anchor compare cloudflare-workers-ai routerplus`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cloudflare-workers-ai.json and https://www.anchorterminal.com/api/v1/tools/routerplus.json\n\n## Other comparisons with Cloudflare Workers AI or RouterPlus\n\n- [Claude API vs Cloudflare Workers AI](https://www.anchorterminal.com/compare/anthropic-api-vs-cloudflare-workers-ai.md)\n- [Claude API vs RouterPlus](https://www.anchorterminal.com/compare/anthropic-api-vs-routerplus.md)\n- [Antseed vs Cloudflare Workers AI](https://www.anchorterminal.com/compare/antseed-vs-cloudflare-workers-ai.md)\n- [BlockRun.AI vs Cloudflare Workers AI](https://www.anchorterminal.com/compare/blockrun-ai-vs-cloudflare-workers-ai.md)\n- [BlockRun.AI vs RouterPlus](https://www.anchorterminal.com/compare/blockrun-ai-vs-routerplus.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 RouterPlus](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-routerplus.md)\n- [Cloudflare Workers AI vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-cohere-chat.md)\n- [Cloudflare Workers AI vs DeepInfra](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-deepinfra.md)\n- [Cloudflare Workers AI vs DeepSeek API](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-deepseek-api.md)\n- [Cloudflare Workers AI vs Gemini Developer API](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-gemini-api.md)\n- [Cloudflare Workers AI vs GroqCloud](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-groq.md)\n- [Cloudflare Workers AI vs Meta Model API](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-meta-model-api.md)\n- [Cloudflare Workers AI vs Mistral AI API](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-mistral-api.md)\n- [Cloudflare Workers AI vs Novita AI](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-novita-ai.md)\n- [Cloudflare Workers AI vs OpenAI API](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-openai-api.md)\n- [Cloudflare Workers AI vs OpenRouter](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-openrouter.md)\n- [Cloudflare Workers AI vs Prism Inference](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-prism-inference.md)\n- [Cloudflare Workers AI vs SambaCloud](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-sambanova.md)\n- [Cloudflare Workers AI vs SiliconFlow](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-siliconflow.md)\n- [Cloudflare Workers AI vs StepFun API](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-stepfun-api.md)\n- [Cohere Chat API (Command models) vs RouterPlus](https://www.anchorterminal.com/compare/cohere-chat-vs-routerplus.md)\n- [DeepInfra vs RouterPlus](https://www.anchorterminal.com/compare/deepinfra-vs-routerplus.md)\n- [DeepSeek API vs RouterPlus](https://www.anchorterminal.com/compare/deepseek-api-vs-routerplus.md)\n- [Gemini Developer API vs RouterPlus](https://www.anchorterminal.com/compare/gemini-api-vs-routerplus.md)\n- [GroqCloud vs RouterPlus](https://www.anchorterminal.com/compare/groq-vs-routerplus.md)\n- [Meta Model API vs RouterPlus](https://www.anchorterminal.com/compare/meta-model-api-vs-routerplus.md)\n- [Mistral AI API vs RouterPlus](https://www.anchorterminal.com/compare/mistral-api-vs-routerplus.md)\n- [Novita AI vs RouterPlus](https://www.anchorterminal.com/compare/novita-ai-vs-routerplus.md)\n- [OpenAI API vs RouterPlus](https://www.anchorterminal.com/compare/openai-api-vs-routerplus.md)\n- [OpenRouter vs RouterPlus](https://www.anchorterminal.com/compare/openrouter-vs-routerplus.md)\n- [Prism Inference vs RouterPlus](https://www.anchorterminal.com/compare/prism-inference-vs-routerplus.md)\n- [RouterPlus vs SambaCloud](https://www.anchorterminal.com/compare/routerplus-vs-sambanova.md)\n- [RouterPlus vs SiliconFlow](https://www.anchorterminal.com/compare/routerplus-vs-siliconflow.md)\n- [RouterPlus vs StepFun API](https://www.anchorterminal.com/compare/routerplus-vs-stepfun-api.md)\n- [Antseed vs RouterPlus](https://www.anchorterminal.com/compare/antseed-vs-routerplus.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-14",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "Cloudflare Workers AI vs RouterPlus",
        "url": ""
      }
    ],
    "description": "Cloudflare Workers AI scores 68.3 (B) to RouterPlus's 51.2 (D) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Cloudflare Workers AI B 68.3",
      "RouterPlus D 51.2",
      "scores"
    ],
    "h1": "Cloudflare Workers AI vs RouterPlus",
    "image": "https://www.anchorterminal.com/assets/og/compare-cloudflare-workers-ai-vs-routerplus.png",
    "path": "/compare/cloudflare-workers-ai-vs-routerplus",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Cloudflare Workers AI vs RouterPlus for AI agents (2026)",
    "toc": null,
    "updated": "2026-10-13",
    "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-routerplus"
  },
  "tokens": {
    "markdown": 3000,
    "slim": 780
  },
  "version": 1
}