{ "data": { "a": { "slug": "ramp-router", "name": "Router.com (Ramp Router)", "vendor": "Ramp", "vendorUrl": "https://router.com", "kind": "router", "category": "inference", "summary": "Router.com (Ramp Router) is Ramp's LLM gateway. One API key reaches OpenAI, Anthropic, xAI and open-weight models through OpenAI Responses, Chat Completions and Anthropic Messages endpoints, with fallbacks, Flex-tier routing, shadow testing and benchmark aliases.", "url": "https://www.anchorterminal.com/tools/ramp-router", "markdownUrl": "https://www.anchorterminal.com/tools/ramp-router.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/ramp-router.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/ramp-router.json", "dns": "ramp-router.grade.anchorterminal.com", "repo": "https://github.com/ramp-public/ramp-cli", "license": "Closed service under the Router Terms of Service (last updated 31 August 2026). The Ramp CLI that configures coding agents for Router is MIT.", "transports": [ "http" ], "remoteUrl": "https://api.router.com/v1", "packages": [ { "registry": "npm", "name": "@ramp/router" } ], "auth": "api-key", "authNotes": "A Router API key, sent as `Authorization: Bearer` or `X-Api-Key`. A person signs up in the browser with Sign in with Ramp, or by email or Google with a business email address on a business domain (Gmail, Outlook, iCloud, Proton and similar are refused); other people can ask router@ramp.com for manual onboarding. Keys are created on the dashboard's API keys page and shown once, or by the Ramp CLI after browser approval. Each key can carry a lifetime or periodic spend cap and be locked, unlocked or revoked (https://docs.router.com/api/endpoint.md, https://docs.router.com/resources/signup-eligibility.md).", "pricing": "usage", "pricingNotes": "Routing is free through 2026, and models are billed at list price per 1M tokens from account credit. Router.com says the first $26 of credits are free. Requests served with the caller's own provider keys carry no Router charge, unless they fall back to Router's shared key. No routing price after 2026 was found. Per-model prices are public at https://router.com/models and https://docs.router.com/supported-models.md.", "priceSummary": "0% fee", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs at https://docs.router.com (all 41 Markdown pages read on 27 October 2026). Calls draw on account credit, and a 402 means the account has no available credit.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 1667, "pypiWeekly": null, "asOf": "2026-10-27" }, "docsUrl": "https://docs.router.com", "llmsTxt": "https://docs.router.com/llms.txt", "capabilities": [ "inference.router", "inference.llm", "inference.decision" ], "tags": [ "hosted", "router", "closed-source", "usage-priced", "prepaid", "free-credit", "llms-txt", "openai-compatible", "anthropic-compatible", "streaming", "prompt-caching", "cli", "new" ], "lastRelease": "2026-10-27", "graded": true, "anchor": { "graded": true, "score": 54.3, "grade": "C", "agentReady": false, "rank": 838, "ranked": true, "rankOf": 1260, "categoryRank": 22, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 77, "maintenance": 59, "payments": 40, "reliability": 25, "schema": 58, "security": 66, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-27" }, "negative": 0, "verdict": "Detailed Markdown docs with typed error codes, per-model capability data and routing an agent can set per request. No OpenAPI document, status page, changelog or published rate limits were found. Signup needs a US business email in a browser, and Ramp records prompts and outputs for a year by default unless switched off.", "bestFor": "Teams in the US that want one key for OpenAI, Anthropic, xAI and open-weight models, with routing to cheaper tiers and per-request cost, and can switch off content recording.", "strengths": [ "llms.txt and a Markdown copy of every docs page, with a field table for each endpoint and an error reference with an action per code", "`GET /v1/models` returns limits, tool, structured-output, caching and reasoning support, and per-provider prices for each model", "Fallback lists of up to 15 provider, model and tier candidates, with timeouts that bound each attempt", "Every response names the serving provider, and Responses calls return `usage.cost` in USD", "Routing is free through 2026, BYOK requests carry no Router charge, and the first $26 of credits are free" ], "weaknesses": [ "Ramp-side content recording is on by default and keeps prompts, outputs and tool calls for one year", "No OpenAPI document, status page, changelog, SLA or published rate limits were found", "Signup needs a US business email domain or Sign in with Ramp, in a browser", "No batch, embeddings or files routes, and Chat Completions lacks fallback lists and cost", "No routing price after 31 December 2026 was found" ], "agentNotes": [ "Switch off content recording in Settings before sending private data. It is on by default and keeps prompts and outputs for a year", "Read model ids from `GET /v1/models` at runtime. Ids are account-specific, an unknown one is a 404, and Gemini ids need your own Google key", "Use `POST /v1/responses` with a `models` list for fallbacks. Router stops falling back once a stream has started", "Set `fallback_timeout` and `provider_timeout`, or `allow_flex_tier: false`, when latency matters. Flex routing is on by default", "Treat both `401 invalid_api_key` and `401 api_key_deactivated` as a possibly locked key, and stop retrying on `402`" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 54.3 } ], "editorialScores": { "ergonomics": 77, "maintenance": 59, "payments": 40, "reliability": 25, "schema": 58, "security": 66, "transparency": 50 }, "provenanceScore": 77, "checked": { "categories": { "ergonomics": "2026-10-27", "maintenance": "2026-10-27", "payments": "2026-10-27", "reliability": "2026-10-27", "schema": "2026-10-27", "security": "2026-10-27", "transparency": "2026-10-27" }, "last": "2026-10-27", "lastMoved": "2026-10-30", "oldest": "2026-10-27", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "curl -fsSL https://router.com/install.sh | sh # Ramp CLI, configures Claude Code, Codex, OpenCode, Pi, Hermes or Conductor", "http": "curl https://api.router.com/v1/responses \\\n -H \"Authorization: Bearer $RAMP_ROUTER_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"models\":[\"openai:gpt-5.4-mini\",\"fireworks:accounts/fireworks/models/kimi-k3\"],\"input\":\"Reply with one word: pong.\",\"max_output_tokens\":16}'" }, "letme": { "capability": "https://letme.dev/inference.router", "tool": "https://letme.dev/ramp-router" }, "area": "models", "unitPrices": [ { "item": "Routing fee", "unit": "pct", "usd": 0, "note": "Free through 2026. Models are billed at list price" }, { "item": "Claude Opus 5.5 input", "unit": "1m-tokens", "usd": 4, "note": "claude-opus-5-5, 1,000,000-token context" }, { "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, 1,050,000-token context" }, { "item": "GPT-6.1 Sol output", "unit": "1m-tokens", "usd": 10 }, { "item": "Kimi K3 input", "unit": "1m-tokens", "usd": 3, "note": "kimi-k3, served by Fireworks or Baseten" }, { "item": "Kimi K3 output", "unit": "1m-tokens", "usd": 15 } ], "provenance": { "legalEntity": "Ramp Business Corporation", "domain": "router.com", "domainRegistered": "1995-07-26", "endpointOnVendorDomain": true, "terms": "https://ramp.com/legal/developer-terms/developer-terms/router-terms-of-service", "privacy": "https://ramp.com/legal/privacy-terms/privacy-terms/router-privacy-notice", "statusPage": "", "changelog": "", "securityTxt": "valid", "checked": "2026-10-27", "notes": [ "The Router Terms of Service (last updated 31 August 2026) name Ramp Business Corporation, 28 W. 23rd Street, Floor 2, New York, NY 10010. The legal pages render with JavaScript, and the documents were read from the legal site's own script files.", "The Router Privacy Notice URL linked from router.com and the docs answers 301 to Ramp's general privacy policy. The notice itself, last updated 19 August 2026, exists only in the legal site's script bundle.", "No status page found. status.router.com does not resolve, router.com/status answers 404, and no status link appears in the docs or on router.com.", "No changelog found. The docs sitemap has none, and /changelog.md on docs.router.com returns the docs app shell. The Ramp CLI's tagged releases are the only dated release record.", "router.com/.well-known/security.txt gives security-external@ramp.com as the contact and expires on 18 March 2027.", "RDAP gives router.com a registration date of 26 July 1995 and Cloudflare, Inc. as registrar, so the domain predates Ramp. The earlier API host router-api.ramp.com still answers." ], "score": 77 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/ramp-router.json", "live": { "slug": "ramp-router", "probe": { "target": "https://api.router.com/v1", "method": "get", "lastAt": "2026-11-02T00:56:17.952810063Z", "lastOk": true, "lastStatus": 401, "lastMs": 356, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 346, "p95ms24h": 476, "samples24h": 249, "samples30d": 1261, "days": [ { "date": "2026-10-27", "probes": 3, "ok": 3 }, { "date": "2026-10-28", "probes": 250, "ok": 250 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 10, "ok": 10 } ] }, "versions": [ { "registry": "github", "name": "ramp-public/ramp-cli", "version": "v0.2.89", "released": "2026-10-30", "seenAt": "2026-11-01T17:28:19.283543356Z" }, { "registry": "npm", "name": "@ramp/router", "version": "0.2.89", "seenAt": "2026-11-01T17:28:18.236978965Z" } ], "githubStars": 52, "npmWeekly": 3718, "securityTxt": { "url": "https://router.com/.well-known/security.txt", "state": "valid", "expires": "2027-03-18T19:00:00.000Z", "checkedAt": "2026-11-01T15:43:11.610675019Z" }, "llmsTxt": { "url": "https://docs.router.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-01T15:14:48.834604282Z" }, "domain": { "domain": "router.com", "registered": "1995-07-26", "source": "https://rdap.verisign.com/com/v1/domain/router.com", "checkedAt": "2026-11-01T14:14:03.12738718Z" }, "pages": [ { "url": "https://ramp.com/legal/privacy-terms/privacy-terms/router-privacy-notice", "kind": "privacy", "status": 200, "checkedAt": "2026-11-01T06:51:06.561962996Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e3b0c44298fc" }, { "url": "https://ramp.com/legal/developer-terms/developer-terms/router-terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-01T06:51:02.528336918Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e3b0c44298fc" } ], "updatedAt": "2026-11-02T00:56:17.952810063Z" } }, "answer": "Tencent Cloud TokenHub scores 59.5 (C) on agent readiness against Router.com (Ramp Router)'s 54.3 (C), and leads in 5 of 7 scored categories. Router.com (Ramp Router) leads on payments \u0026 pricing and transparency \u0026 trust.", "b": { "slug": "tencent-tokenhub", "name": "Tencent Cloud TokenHub", "vendor": "Tencent Cloud", "vendorUrl": "https://cloud.tencent.com", "kind": "router", "category": "inference", "summary": "Tencent Cloud TokenHub is a hosted model gateway serving Tencent's Hy models and third-party models such as DeepSeek, Kimi, GLM and MiniMax through OpenAI-compatible and Anthropic-compatible endpoints in Guangzhou and Singapore, with per-key scopes and quotas.", "url": "https://www.anchorterminal.com/tools/tencent-tokenhub", "markdownUrl": "https://www.anchorterminal.com/tools/tencent-tokenhub.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/tencent-tokenhub.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/tencent-tokenhub.json", "dns": "tencent-tokenhub.grade.anchorterminal.com", "repo": "https://github.com/TencentCloud/THCLI", "license": "Proprietary service under the TokenHub Terms of Service, the TokenHub SLA and the Tencent Cloud Service Agreement, with a special note for third-party deployed models. The `tencent-tokenhub-cli` package is Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://tokenhub.tencentmaas.com/v1", "packages": [ { "registry": "npm", "name": "tencent-tokenhub-cli" } ], "auth": "api-key", "authNotes": "Bearer API key from the TokenHub console, or `x-api-key` on the Anthropic-style `/v1/messages`. Keys are long-lived, belong to one region (Guangzhou or Singapore), can be limited to chosen models and inference services, up to 200 IP ranges and token quotas, and can be disabled or deleted. They can also be created through the CreateApiKey control-plane call with signed Tencent Cloud credentials, or by `thcli auth login`. The account needs real-name verification first.", "pricing": "usage", "pricingNotes": "Pay per token in CNY, billed hourly. Hy4 preview costs 6 CNY in, 18 CNY out and 0.3 CNY cached per 1M tokens, Hy3 1, 4 and 0.25 CNY. DeepSeek models double at weekday peak hours. Batch is half price for Hy3 and Hy4 preview. Each account gets 1M free tokens per language model for a year, in a campaign to 31 December 2026. Token Plan subscriptions run from 28 to 599 CNY a month (https://cloud.tencent.com/document/product/1823/130055, checked 2026-11-01).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs table of contents, the billing pages or the API usage page. Payment is from a Tencent Cloud account balance, billed hourly (checked 2026-11-01).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 204, "pypiWeekly": null, "asOf": "2026-11-01" }, "docsUrl": "https://cloud.tencent.com/document/product/1823/130058", "rateLimitsUrl": "https://cloud.tencent.com/document/product/1823/136028", "llmsTxt": "https://cloud.tencent.com/document/product/1823/llms.txt", "capabilities": [ "inference.router", "inference.llm", "inference.open-weights", "embed.text", "embed.multimodal", "image.generate", "video.generate", "speech.tts", "speech.stt", "audio.music", "translate.text", "web.search", "obs.gateway" ], "tags": [ "hosted", "router", "usage-based", "free-credit", "openai-compatible", "anthropic-compatible", "llms-txt", "cli", "sla", "batch", "bug-bounty", "no-status-page", "regional-endpoints", "singapore", "chinese", "subscription" ], "lastRelease": "2026-10-24", "graded": true, "anchor": { "graded": true, "score": 59.5, "grade": "C", "agentReady": false, "rank": 646, "ranked": true, "rankOf": 1260, "categoryRank": 18, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 83, "maintenance": 73, "payments": 35, "reliability": 46, "schema": 73, "security": 71, "transparency": 54 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -3, "negativeNotes": [ "2026-10-17. -3, a breaking change without notice. DeepSeek-V4.1-Flash (directly supplied) was moved to its 1017 version under the same model ids and prices on 17 October 2026, and the notice came two days later (https://cloud.tencent.com/announce/detail/2516). Callers pinned to the id got a different model's behaviour with no warning. One term at the floor: the API didn't change. The founder's decision, 1 November 2026." ], "verdict": "Keys can be limited to chosen models, source IPs and token quotas, errors name their source and code, and a 99.5% SLA covers paid use of models Tencent runs. Sign-up needs a Tencent Cloud account with real-name verification, prices are in CNY, no public status page was found, and 18 model retirement notices ran from April to October 2026.", "bestFor": "Teams in or near Tencent Cloud that want one key and bill for Tencent's Hy models and Chinese open-weight models (DeepSeek, Kimi, GLM, MiniMax, Qwen, MiMo) with per-key limits and CNY billing.", "strengths": [ "API keys can be limited to chosen models and inference services, up to 200 source IP ranges, and daily, monthly or total token quotas", "One base URL answers OpenAI Chat Completions, OpenAI Responses and Anthropic Messages calls, and `GET /v1/models` marks models due to retire as `pre-offline`", "Error bodies carry a six-digit code, English and Chinese messages, the source (client, gateway or upstream) and a request ID, and 429s can carry `Retry-After`", "A published SLA promises 99.5% monthly availability with voucher credits of 10 to 50 per cent of the month's fee, for paid use of models Tencent runs", "Per-call audit logs (request ID, key, client IP, status, tokens, latency) can be delivered to the customer's own Tencent Cloud CLS log service" ], "weaknesses": [ "Sign-up needs a Tencent Cloud account with real-name verification. The international site answered with a bot check, so access from outside China was not established", "No public status page was found. A four-hour outage of DeepSeek's directly supplied models on 15 October 2026 appears only as a compensation notice", "18 model retirement notices from 21 April to 22 October 2026. Those read gave 21 to 33 days, and eligible callers are switched to a successor at its price", "DeepSeek's directly supplied models send inputs to DeepSeek under its own terms, and the TokenHub SLA does not cover them", "Per-model RPM and TPM limits for chat models are shown in the console and the quota API, not in the public docs" ], "agentNotes": [ "Use `https://tokenhub.tencentmaas.com/v1` with keys made for Guangzhou and `https://tokenhub-intl.tencentmaas.com/v1` with keys made for Singapore. Keys do not work across the two", "Send the key as `Authorization: Bearer` on the OpenAI paths and as `x-api-key` on `/v1/messages`", "Parse `error.code` as a string or a number, since 429 codes can come back as integers, and wait for `Retry-After` before retrying", "Take model ids from `GET /v1/models` and watch for `pre-offline`. The quickstart's `deepseek-v3` example is not in the current model list", "Expect DeepSeek prices to double on weekdays from 9am to noon and 2pm to 6pm Beijing time, when the peak rate applies" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 59.5 } ], "editorialScores": { "ergonomics": 83, "maintenance": 73, "payments": 35, "reliability": 46, "schema": 73, "security": 71, "transparency": 59 }, "provenanceScore": 49, "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", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm i -g tencent-tokenhub-cli", "http": "curl https://tokenhub.tencentmaas.com/v1/models \\\n -H \"Authorization: Bearer $TOKENHUB_API_KEY\"", "claudeCode": "{\n \"env\": {\n \"ANTHROPIC_BASE_URL\": \"https://tokenhub.tencentmaas.com\",\n \"ANTHROPIC_AUTH_TOKEN\": \"YOUR_API_KEY\",\n \"ANTHROPIC_MODEL\": \"hy3\"\n }\n}" }, "letme": { "capability": "https://letme.dev/inference.router", "tool": "https://letme.dev/tencent-tokenhub" }, "area": "models", "provenance": { "legalEntity": "Tencent Cloud Computing (Beijing) Co., Ltd. (腾讯云计算（北京）有限责任公司)", "domain": "tencentmaas.com", "domainRegistered": "2026-03-13", "endpointOnVendorDomain": false, "terms": "https://cloud.tencent.com/document/product/301/129852", "privacy": "https://privacy.qq.com/document/preview/91d5fd3c98ce4468ae462ac59233bba2", "statusPage": "", "changelog": "https://cloud.tencent.com/document/product/1823/130675", "securityTxt": "none", "checked": "2026-11-01", "notes": [ "The TokenHub Terms of Service (effective 14 September 2026), the SLA (effective 23 April 2026) and the special note on third-party deployed models (effective 14 September 2026) name 腾讯云计算（北京）有限责任公司. The docs footer also names 深圳市腾讯计算机系统有限公司 as ICP licence holder.", "The TokenHub privacy policy is linked from the docs to privacy.qq.com, which renders only with JavaScript, so it was not read. privacy.qq.com has no robots.txt (404).", "No public status page was found. status.cloud.tencent.com did not answer, and the Tencent Cloud health dashboard documentation answered with a bot check.", "security.txt answered 404 on cloud.tencent.com, www.tencent.com and tokenhub.tencentmaas.com. Tencent's bug bounty policy at en.security.tencent.com lists Tencent Cloud in scope.", "RDAP at Verisign gives tencentmaas.com a registration date of 13 March 2026 with no registrant. The API answers at tokenhub.tencentmaas.com and tokenhub-intl.tencentmaas.com, named in Tencent Cloud's API usage page.", "cloud.tencent.com allows these docs in robots.txt. Its pages answered some requests with a JavaScript bot check, which was not passed. The pages were read when a later plain request returned them. www.tencentcloud.com answered robots.txt with a bot check, so the international site was not read." ], "score": 49 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/tencent-tokenhub.json", "live": { "slug": "tencent-tokenhub", "probe": { "target": "https://tokenhub.tencentmaas.com/v1", "method": "get", "lastAt": "2026-11-02T00:56:24.101434531Z", "lastOk": true, "lastStatus": 404, "lastMs": 795, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 826, "p95ms24h": 1067, "samples24h": 28, "samples30d": 28, "days": [ { "date": "2026-11-01", "probes": 18, "ok": 18 }, { "date": "2026-11-02", "probes": 10, "ok": 10 } ] }, "updatedAt": "2026-11-02T00:56:24.101434531Z" } }, "edges": [ { "by": 21, "category": "reliability", "leads": "tencent-tokenhub", "name": "Reliability", "reasons": { "a": "Hosted reading. No status page found. status.router.com does not resolve, router.com/status answers 404, and neither the docs nor router.com link one (0). No readable incident history (5). No request or token rate limits are published. The docs say limits vary by model and list only technical limits, a 100 MiB body, 15 candidates and 100 keys per user (0). The errors page passes through provider `retry-after` and `retry-after-ms`, tells clients to respect them, gives a retry or fallback action for every 4xx and 5xx code, and says a failed fallback candidate is not retried (15). No SLA found. The Router Terms provide the service as is, and Ramp's product schedule says Router documentation creates no service level (0). The public API carries no beta label in the docs, but Ramp's product schedule for its customers heads the Router section 'Early Access' and the docs llms.txt says to treat 'beta pricing, limits' as subject to change (5 of 10).", "b": "Hosted reading. No public status page was found. status.cloud.tencent.com did not answer and the Tencent Cloud health dashboard documentation answered with a bot check (0). With no page there is no incident record to read (5 of 30). The announcements carry one incident, DeepSeek's directly supplied models unavailable from 9:06 to 13:04 Beijing time on 15 October 2026 after a fault at DeepSeek, compensated with vouchers. Rate limits are per model, shown in the console and returned by DescribeModelQuota. The public docs give numbers only for batch jobs (20 created a minute, 10 active), image models (5 concurrent) and DeepSeek V4 Flash and Pro (2,500 and 500 concurrent), with the rules for self-serve increases (8 of 15). Six 429 codes separate RPM, TPM, TPD, concurrency and upstream capacity, 429s may carry `Retry-After` and the docs advise exponential backoff. No idempotency guidance, though inference calls are not writes (13 of 15). The TokenHub SLA promises 99.5% monthly availability with vouchers of 10, 25 or 50 per cent of the month's fee. It excludes free use and third-party deployed models such as DeepSeek's directly supplied ones (10). Generally available since 7 April 2026, with some models marked preview (10)." }, "scores": { "a": 25, "b": 46 } }, { "by": 15, "category": "schema", "leads": "tencent-tokenhub", "name": "Schema \u0026 documentation", "reasons": { "a": "Router, scored on the API lines. No OpenAPI or other machine-readable contract found. /openapi.json on docs.router.com returns the docs app shell. The API follows the OpenAI and Anthropic wire formats, which this checklist doesn't credit to a router, the same reading as RouterPlus (0 of 25). llms.txt and a Markdown copy of every page at the same path with `.md` (10). Pages say which endpoint to prefer and why, what isn't served (embeddings, files, batches), which Chat Completions controls return 501, and which workload suits which job (17 of 20). Router-only fields are tabled with types and bounds, the route selector rules are stated (`model` or `models` but never both, 1 to 15 candidates), over-limit timeouts are a 400 naming the maximum, and the model list documents a typed `router` object with a `schema_version`. Request bodies otherwise follow the upstream formats (12 of 15). curl, OpenAI SDK, Anthropic SDK, LangChain, Vercel AI SDK, LlamaIndex and Pydantic AI examples, and an error reference with a status, code and action for each case (15). Paths sit under `/v1` and the model object is versioned, but no API changelog or dated release notes were found (4 of 15).", "b": "Router, scored on the API lines. No OpenAPI file for the inference routes. Field pages document the OpenAI Chat Completions, OpenAI Responses and Anthropic Messages formats as TokenHub implements them, and the control plane is a Tencent Cloud API 3.0 service (version 2026-03-22) with typed parameters, API Explorer and SDKs (12 of 25). An llms.txt at cloud.tencent.com/document/product/1823/llms.txt links a Markdown copy of each docs page (10). The docs say which models support thinking, tools, structured output and caching, how TokenHub departs from each standard protocol, and which DeepSeek model suits which job. The quickstart's examples still use `deepseek-v3`, which is not in the model list, and Qwen3.5 stays in the list with a past shutdown date (13 of 20). Protocol pages list each field with type, required flag and default, and control-plane parameters carry enums and required flags (10 of 15). Examples in curl, Python, Node.js, Java and Go, and an error page listing 30 codes with HTTP status, cause and fix (14 of 15). Paths carry `/v1`, release notes are dated monthly from 7 April to 24 October 2026, and the control-plane API has a dated history of 26 releases to 18 September 2026 (14 of 15)." }, "scores": { "a": 58, "b": 73 } }, { "by": 14, "category": "maintenance", "leads": "tencent-tokenhub", "name": "Maintenance \u0026 community", "reasons": { "a": "Router, read on the model lines for a closed service. The Provider Terms Schedule was updated on 26 October 2026, and the Ramp CLI that ships the `router` commands released v0.2.82 on 27 October (30). Models carry a `deprecated` status and the docs list deprecated and retired models, but no notice period is stated, and the Baseten retirement note gives no date and says requests aren't redirected (4 of 12). Provider-specific Baseten ids and several Fireworks models were retired without dates. The API host moved from router-api.ramp.com to api.router.com, and the old host still answers (3 of 8). No public API changelog. Support is a dashboard button and router@ramp.com, not tested (5 of 15). ramp-cli issue replies were not read, because GitHub's API wasn't available to this session (3 of 10). No API SDK. The Ramp CLI (MIT, npm @ramp/router and @ramp/cli at 0.2.82, Homebrew) sets up agents and keys (7 of 15). The CLI repository has CI, build, npm and router-integration workflows and a tests folder, with 41 commit days since 29 July. CI results were not checked (7 of 10).", "b": "Closed service, read on the model lines. The newest release note is dated 24 October 2026 and the price page was updated on 31 October (30). The four retirement notices read gave 21 to 33 days, and eligible callers are switched to a successor at its price. No minimum notice period is written, and DeepSeek-V4.1-Flash (directly supplied) was moved to the 1017 version under the same ids on 17 October 2026 in a notice dated two days later (7 of 12). 18 retirement notices from 21 April to 22 October 2026, 12 of them since 3 August (3 of 8). Dated release notes and announcements, ticket and phone support around the clock and a Q\u0026A community (13 of 15). Replies on the THCLI repository were not sampled (3 of 10). Tencent Cloud SDK 3.0 in several languages covers the control plane and `tencent-tokenhub-cli` 1.0.2 was published on 30 October 2026. No inference SDK of its own (12 of 15). The CLI has four releases since 15 September 2026, lists no runtime dependencies and needs Node.js 18 or later. CI not checked (5 of 10)." }, "scores": { "a": 59, "b": 73 } }, { "by": 10, "category": "transparency", "leads": "ramp-router", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service under the Router Terms of Service of 31 August 2026, which bar reselling access and building a competing service. The CLI is MIT (16 of 30). The docs FAQ states the one-year default recording, the opt-out and the PII step. The Router Privacy Notice of 19 August 2026 says an account 'can be configured' not to retain content, without naming the default or the one-year period, and every link to it answers 301 to Ramp's general privacy policy. The superseded pilot terms kept data a year and allowed training on de-identified versions (16 of 30). No deprecation policy found. The Terms let Ramp add or remove models at any time, and model retirements in the docs carry no dates (5 of 20). The Provider Terms Schedule names each provider with its training and retention terms, and the FAQ says all models run on US infrastructure. No Router subprocessor list was found (13 of 20).", "b": "Closed service under the TokenHub Terms of Service (effective 14 September 2026), the SLA (23 April 2026), a special note on third-party deployed models and the Tencent Cloud Service Agreement, naming Tencent Cloud Computing (Beijing) Co., Ltd. The CLI is Apache-2.0 (18 of 30). The terms and the FAQ agree that inputs are processed on the customer's instructions and not used for training, and clause 2.14 limits retention to what the service needs without periods. The TokenHub privacy policy on privacy.qq.com renders only with JavaScript and was not read (15 of 30). Dated retirement notices, shutdown dates in the model list, a `pre-offline` status in `/v1/models` and a `DiscontinuedAt` field in the control API. Clause 6.3 refunds paid, unused tokens when a third-party model is removed. No minimum notice period is written (13 of 20). Clause 2.13 places processing generally in mainland China for the China site and in Singapore for the international site, and the third-party model list names DeepSeek's Hangzhou company with a link to its terms. No subprocessor list was found (13 of 20)." }, "scores": { "a": 64, "b": 54 } }, { "by": 6, "category": "ergonomics", "leads": "tencent-tokenhub", "name": "Agent ergonomics", "reasons": { "a": "Router, read on the model lines (tool use, structured output, caching, context, batch, SDKs, errors). Tools pass through on Responses, Messages and Chat Completions, and `GET /v1/models` reports `tools.supported` and `parallel` per model, with `null` where Router doesn't know. Behaviour depends on the model (16 of 20). The docs say JSON Schema output is expected to work across providers subject to model support, and each model carries a `structured_outputs` flag. A request the provider can't represent is a 501 (12 of 15). Cache read and write prices per model, a `prompt_cache_key` session lease of 5 or 30 minutes that keeps a session on the provider with a warm cache, and `cache_control` on Messages (14 of 15). Contexts up to 1,050,000 tokens on GPT-6.1 Sol and 1,048,576 on Kimi K3, a judgement call since a router has no default model (15). No batch route; the docs say Router doesn't serve batches (0 of 10). No SDK of its own. The OpenAI and Anthropic SDKs work with a changed base URL, framework setups are documented, and the MIT Ramp CLI configures six coding agents (5 of 10). Typed codes for every error, a `limit` object naming the cap and who set it, an all-candidates-failed summary, request and trace ids on every response and the serving provider in a header (15).", "b": "Router, read on the model lines. Function calling is marked on most chat models in the model list, with behaviour depending on the model routed (14 of 20). Structured output is marked per model and missing on the MiniMax and Qwen models, and an unsupported `response_format` returns code 400006 (12 of 15). Cache-hit prices are published per model, Kimi K3.1 Pro lists five-minute and one-hour cache writes, and a guide covers `prompt_cache_key` and the `X-Session-ID` header for instance affinity (14 of 15). Most listed chat models have contexts of one million tokens, a judgement call since a router has no default model (15). Batch at half price covers only Hy3 and Hy4 preview, reads and writes JSONL in the customer's own COS bucket and is documented for the Guangzhou endpoint (5 of 10). No TokenHub inference SDK. The OpenAI and Anthropic SDKs work with a changed base URL, and Tencent Cloud SDK 3.0 and the `thcli` CLI cover the control plane (8 of 10). Errors return a code, English and Chinese messages, the source, the upstream code and status and a request ID, and stream errors arrive as SSE error frames (15 of 15)." }, "scores": { "a": 77, "b": 83 } }, { "by": 5, "category": "security", "leads": "tencent-tokenhub", "name": "Security \u0026 auth", "reasons": { "a": "Router, read on the model lines. Router keys are shown once, can expire, carry lifetime or periodic spend caps, can be locked, unlocked or revoked, and each key has its own model set and default workload. No permission scopes or programmatic rotation were found (24 of 30). The docs FAQ says Ramp-side content recording is on by default and keeps inputs, outputs and tool calls for one year for debugging, semantic analysis and product improvement, with detected personal data removed before product use. The Provider Terms Schedule marks six providers as not training on Router traffic and TypeSafe as 'Not prohibited' (6 of 20). Recording can be switched off account-wide, propagating asynchronously and without deleting existing archives, and flagged content may still be kept up to 30 days. The schedule lists zero data retention for Ramp-provided connections, except up to 30 days for OpenAI GPT-5.5 and later and for Claude Fable 5 and 5.1 (10 of 15). Logs show model, provider, status, tokens, cost, latency, fallback candidates, credential source and routing decisions per request, with usage export to S3 for Router Admins (14 of 15). A valid security.txt on router.com points to Ramp's security address. Ramp's SOC 2 and ISO 27001 reports, per the ramp listing's 8 October check, were not shown to cover Router, which is a separate product under its own terms. No bug bounty found (12 of 20).", "b": "Router, read on the model lines. Bearer keys can be limited to chosen models and inference services, up to 200 source IP ranges and daily, monthly or total token quotas, can be disabled or deleted, and can be created in code through CreateApiKey with signed Tencent Cloud credentials. Keys are long-lived with no expiry setting or built-in rotation (26 of 30). Clause 2.17 of the terms says inputs are not used to train Tencent Cloud's own models, and the FAQ says data is not used for training. Inputs to third-party deployed models (DeepSeek's directly supplied ones) go to DeepSeek under its terms (14 of 20). Clause 2.14 keeps data only as long as the service needs, with no periods stated. When a customer asks for generated content without AI labels, Tencent Cloud keeps logs of who received it for at least six months. No zero-retention option was found (7 of 15). Per-call audit logs (request ID, key, client IP, status, tokens, latency) and optional full call logs go to the customer's CLS, billed separately, with usage by key and a monitoring dashboard (14 of 15). No security.txt on cloud.tencent.com, www.tencent.com or tokenhub.tencentmaas.com (404). Tencent's bug bounty through TSRC lists Tencent Cloud in scope. No certification for TokenHub was checked (10 of 20)." }, "scores": { "a": 66, "b": 71 } } ], "facts": [ { "a": "Model router", "b": "Model router", "name": "Kind" }, { "a": "Ramp", "b": "Tencent Cloud", "name": "Vendor" }, { "a": "https://api.router.com/v1", "b": "https://tokenhub.tencentmaas.com/v1", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Closed service under the Router Terms of Service (last updated 31 August 2026). The Ramp CLI that configures coding agents for Router is MIT.", "b": "Proprietary service under the TokenHub Terms of Service, the TokenHub SLA and the Tencent Cloud Service Agreement, with a special note for third-party deployed models. The `tencent-tokenhub-cli` package is Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-27", "b": "2026-10-24", "name": "Last release" }, { "a": "couldn't be read", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "couldn't be read", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "couldn't be read", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "couldn't be read", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "couldn't be read", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "couldn't be read", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "couldn't be read", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "1.7k npm/wk", "b": "204 npm/wk", "name": "Popularity" } ], "faq": [ { "answer": "Tencent Cloud TokenHub scores 59.5 (C) on agent readiness against Router.com (Ramp Router)'s 54.3 (C), and leads in 5 of 7 scored categories. Router.com (Ramp Router) leads on payments \u0026 pricing and transparency \u0026 trust.", "question": "Which is better for AI agents, Router.com (Ramp Router) or Tencent Cloud TokenHub?" }, { "answer": "Both need an API key.", "question": "Do Router.com (Ramp Router) and Tencent Cloud TokenHub need an API key?" }, { "answer": "Yes. Router.com (Ramp Router) has a hosted endpoint at https://api.router.com/v1 and Tencent Cloud TokenHub at https://tokenhub.tencentmaas.com/v1.", "question": "Can an agent call Router.com (Ramp Router) and Tencent Cloud TokenHub without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 40 against 35", "Transparency \u0026 trust, 64 against 54" ], "also": [ "No incidents deducted, where Tencent Cloud TokenHub loses 3 points for them" ], "goodFor": "Teams in the US that want one key for OpenAI, Anthropic, xAI and open-weight models, with routing to cheaper tiers and per-request cost, and can switch off content recording.", "slug": "ramp-router", "watchFor": "Ramp-side content recording is on by default and keeps prompts, outputs and tool calls for one year" }, { "aheadOn": [ "Reliability, 46 against 25", "Schema \u0026 documentation, 73 against 58", "Agent ergonomics, 83 against 77", "Security \u0026 auth, 71 against 66", "Maintenance \u0026 community, 73 against 59" ], "also": null, "goodFor": "Teams in or near Tencent Cloud that want one key and bill for Tencent's Hy models and Chinese open-weight models (DeepSeek, Kimi, GLM, MiniMax, Qwen, MiMo) with per-key limits and CNY billing.", "slug": "tencent-tokenhub", "watchFor": "Sign-up needs a Tencent Cloud account with real-name verification. The international site answered with a bot check, so access from outside China was not established" } ], "history": { "ramp-router": [ { "causes": [ "method" ], "date": "2026-10-30", "delta": -0.2, "from": 54.5, "fromGrade": "C", "to": 54.3, "toGrade": "C" } ], "tencent-tokenhub": null }, "job": { "capability": "inference.router", "name": "Model routing" }, "others": [ { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-ramp-router.json", "title": "Claude API vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-tencent-tokenhub.json", "title": "Claude API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-ramp-router.json", "title": "BlockRun.AI vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-tencent-tokenhub.json", "title": "BlockRun.AI vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-ramp-router.json", "title": "Cerebras Inference vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-tencent-tokenhub.json", "title": "Cerebras Inference vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-tencent-tokenhub" }, { "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-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-workers-ai-vs-ramp-router.json", "title": "Cloudflare Workers AI vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-tencent-tokenhub.json", "title": "Cloudflare Workers AI vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-ramp-router.json", "title": "Cohere Chat API (Command models) vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-tencent-tokenhub.json", "title": "Cohere Chat API (Command models) vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/deepinfra-vs-ramp-router.json", "title": "DeepInfra vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/deepinfra-vs-tencent-tokenhub.json", "title": "DeepInfra vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-ramp-router.json", "title": "DeepSeek API vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-tencent-tokenhub.json", "title": "DeepSeek API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-ramp-router.json", "title": "Glimpse vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-tencent-tokenhub.json", "title": "Glimpse vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-ramp-router.json", "title": "Fireworks AI Inference vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-tencent-tokenhub.json", "title": "Fireworks AI Inference vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/gemini-api-vs-ramp-router.json", "title": "Gemini Developer API vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/gemini-api-vs-tencent-tokenhub.json", "title": "Gemini Developer API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/groq-vs-ramp-router.json", "title": "GroqCloud vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/groq-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/groq-vs-tencent-tokenhub.json", "title": "GroqCloud vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/groq-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-ramp-router.json", "title": "Jais 3 vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/jais-3-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/jais-3-vs-tencent-tokenhub.json", "title": "Jais 3 vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/jais-3-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-ramp-router.json", "title": "Meta Model API vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub.json", "title": "Meta Model API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/minimax-api-vs-ramp-router.json", "title": "MiniMax API vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/minimax-api-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/minimax-api-vs-tencent-tokenhub.json", "title": "MiniMax API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/minimax-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-ramp-router.json", "title": "Mistral AI API vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/mistral-api-vs-tencent-tokenhub.json", "title": "Mistral AI API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/mistral-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-ramp-router.json", "title": "Muse Spark Open vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-tencent-tokenhub.json", "title": "Muse Spark Open vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-ramp-router.json", "title": "Nemotron 3.5 Super VL vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/novita-ai-vs-ramp-router.json", "title": "Novita AI vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/novita-ai-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/novita-ai-vs-tencent-tokenhub.json", "title": "Novita AI vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/novita-ai-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/openai-api-vs-ramp-router.json", "title": "OpenAI API vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/openai-api-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/openai-api-vs-tencent-tokenhub.json", "title": "OpenAI API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/openai-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/openrouter-vs-ramp-router.json", "title": "OpenRouter vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/openrouter-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/openrouter-vs-tencent-tokenhub.json", "title": "OpenRouter vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/openrouter-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/prism-inference-vs-ramp-router.json", "title": "Prism Inference vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/prism-inference-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/ramp-router-vs-reflection-beam.json", "title": "Router.com (Ramp Router) vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/ramp-router-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/ramp-router-vs-sambanova.json", "title": "Router.com (Ramp Router) vs SambaCloud", "url": "https://www.anchorterminal.com/compare/ramp-router-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/ramp-router-vs-siliconflow.json", "title": "Router.com (Ramp Router) vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/ramp-router-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/ramp-router-vs-simplismart.json", "title": "Router.com (Ramp Router) vs Simplismart", "url": "https://www.anchorterminal.com/compare/ramp-router-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/ramp-router-vs-stepfun-api.json", "title": "Router.com (Ramp Router) vs StepFun API", "url": "https://www.anchorterminal.com/compare/ramp-router-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/ramp-router-vs-together-inference.json", "title": "Router.com (Ramp Router) vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/ramp-router-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/reflection-beam-vs-tencent-tokenhub.json", "title": "Beam 1.0 vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/reflection-beam-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/sambanova-vs-tencent-tokenhub.json", "title": "SambaCloud vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/sambanova-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/siliconflow-vs-tencent-tokenhub.json", "title": "SiliconFlow vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/siliconflow-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/simplismart-vs-tencent-tokenhub.json", "title": "Simplismart vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/simplismart-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/stepfun-api-vs-tencent-tokenhub.json", "title": "StepFun API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/stepfun-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/tencent-tokenhub-vs-together-inference.json", "title": "Tencent Cloud TokenHub vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/tencent-tokenhub-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-tencent-tokenhub.json", "title": "Nemotron 3.5 Super VL vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/prism-inference-vs-tencent-tokenhub.json", "title": "Prism Inference vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/prism-inference-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-ramp-router.json", "title": "Antseed vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/antseed-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-tencent-tokenhub.json", "title": "Antseed vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/antseed-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/ramp-router-vs-routerplus.json", "title": "Router.com (Ramp Router) vs RouterPlus", "url": "https://www.anchorterminal.com/compare/ramp-router-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/ramp-router-vs-vercel-ai-gateway.json", "title": "Router.com (Ramp Router) vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/ramp-router-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/routerplus-vs-tencent-tokenhub.json", "title": "RouterPlus vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/routerplus-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/tencent-tokenhub-vs-vercel-ai-gateway.json", "title": "Tencent Cloud TokenHub vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/tencent-tokenhub-vs-vercel-ai-gateway" } ], "panel": null, "scores": [ { "by": 21, "edge": "tencent-tokenhub", "key": "reliability", "name": "Reliability", "ramp-router": 25, "tencent-tokenhub": 46, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 15, "edge": "tencent-tokenhub", "key": "schema", "name": "Schema \u0026 documentation", "ramp-router": 58, "tencent-tokenhub": 73, "weight": 13 }, { "by": 6, "edge": "tencent-tokenhub", "key": "ergonomics", "name": "Agent ergonomics", "ramp-router": 77, "tencent-tokenhub": 83, "weight": 13 }, { "by": 5, "edge": "tencent-tokenhub", "key": "security", "name": "Security \u0026 auth", "ramp-router": 66, "tencent-tokenhub": 71, "weight": 14 }, { "by": 5, "edge": "ramp-router", "key": "payments", "name": "Payments \u0026 pricing", "ramp-router": 40, "tencent-tokenhub": 35, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 14, "edge": "tencent-tokenhub", "key": "maintenance", "name": "Maintenance \u0026 community", "ramp-router": 59, "tencent-tokenhub": 73, "weight": 7 }, { "by": 10, "edge": "ramp-router", "key": "transparency", "name": "Transparency \u0026 trust", "ramp-router": 64, "tencent-tokenhub": 54, "weight": 7 } ], "summary": "Tencent Cloud TokenHub scores 59.5 (C) on agent readiness against Router.com (Ramp Router)'s 54.3 (C), and leads in 5 of 7 scored categories. Router.com (Ramp Router) leads on payments \u0026 pricing and transparency \u0026 trust. Both do model routing.", "tasks": null, "tutorials": [], "verdicts": { "ramp-router": "Detailed Markdown docs with typed error codes, per-model capability data and routing an agent can set per request. No OpenAPI document, status page, changelog or published rate limits were found. Signup needs a US business email in a browser, and Ramp records prompts and outputs for a year by default unless switched off.", "tencent-tokenhub": "Keys can be limited to chosen models, source IPs and token quotas, errors name their source and code, and a 99.5% SLA covers paid use of models Tencent runs. Sign-up needs a Tencent Cloud account with real-name verification, prices are in CNY, no public status page was found, and 18 model retirement notices ran from April to October 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/ramp-router-vs-tencent-tokenhub", "json": "https://www.anchorterminal.com/compare/ramp-router-vs-tencent-tokenhub.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/ramp-router-vs-tencent-tokenhub.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/ramp-router-vs-tencent-tokenhub.min.md" }, "markdown": "Tencent Cloud TokenHub scores 59.5 (C) on agent readiness against Router.com (Ramp Router)'s 54.3 (C), and leads in 5 of 7 scored categories. Router.com (Ramp Router) leads on payments \u0026 pricing and transparency \u0026 trust. Both do model routing.\n\n- Router.com (Ramp Router): grade C, 54.3/100, rank #838 of 1260. Markdown https://www.anchorterminal.com/tools/ramp-router.md · JSON https://www.anchorterminal.com/api/v1/tools/ramp-router.json\n- Tencent Cloud TokenHub: grade C, 59.5/100, rank #646 of 1260. Markdown https://www.anchorterminal.com/tools/tencent-tokenhub.md · JSON https://www.anchorterminal.com/api/v1/tools/tencent-tokenhub.json\n- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 529 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### Router.com (Ramp Router) (C)\n\nGood for: Teams in the US that want one key for OpenAI, Anthropic, xAI and open-weight models, with routing to cheaper tiers and per-request cost, and can switch off content recording.\n\nAhead on:\n- Payments \u0026 pricing, 40 against 35\n- Transparency \u0026 trust, 64 against 54\n\nAlso in its favour:\n- No incidents deducted, where Tencent Cloud TokenHub loses 3 points for them\n\nWatch for: Ramp-side content recording is on by default and keeps prompts, outputs and tool calls for one year\n\n### Tencent Cloud TokenHub (C)\n\nGood for: Teams in or near Tencent Cloud that want one key and bill for Tencent's Hy models and Chinese open-weight models (DeepSeek, Kimi, GLM, MiniMax, Qwen, MiMo) with per-key limits and CNY billing.\n\nAhead on:\n- Reliability, 46 against 25\n- Schema \u0026 documentation, 73 against 58\n- Agent ergonomics, 83 against 77\n- Security \u0026 auth, 71 against 66\n- Maintenance \u0026 community, 73 against 59\n\nWatch for: Sign-up needs a Tencent Cloud account with real-name verification. The international site answered with a bot check, so access from outside China was not established\n\n\n## Why the edge\n\n### Reliability: Tencent Cloud TokenHub +21\n\n- Router.com (Ramp Router) (25): Hosted reading. No status page found. status.router.com does not resolve, router.com/status answers 404, and neither the docs nor router.com link one (0). No readable incident history (5). No request or token rate limits are published. The docs say limits vary by model and list only technical limits, a 100 MiB body, 15 candidates and 100 keys per user (0). The errors page passes through provider `retry-after` and `retry-after-ms`, tells clients to respect them, gives a retry or fallback action for every 4xx and 5xx code, and says a failed fallback candidate is not retried (15). No SLA found. The Router Terms provide the service as is, and Ramp's product schedule says Router documentation creates no service level (0). The public API carries no beta label in the docs, but Ramp's product schedule for its customers heads the Router section 'Early Access' and the docs llms.txt says to treat 'beta pricing, limits' as subject to change (5 of 10).\n- Tencent Cloud TokenHub (46): Hosted reading. No public status page was found. status.cloud.tencent.com did not answer and the Tencent Cloud health dashboard documentation answered with a bot check (0). With no page there is no incident record to read (5 of 30). The announcements carry one incident, DeepSeek's directly supplied models unavailable from 9:06 to 13:04 Beijing time on 15 October 2026 after a fault at DeepSeek, compensated with vouchers. Rate limits are per model, shown in the console and returned by DescribeModelQuota. The public docs give numbers only for batch jobs (20 created a minute, 10 active), image models (5 concurrent) and DeepSeek V4 Flash and Pro (2,500 and 500 concurrent), with the rules for self-serve increases (8 of 15). Six 429 codes separate RPM, TPM, TPD, concurrency and upstream capacity, 429s may carry `Retry-After` and the docs advise exponential backoff. No idempotency guidance, though inference calls are not writes (13 of 15). The TokenHub SLA promises 99.5% monthly availability with vouchers of 10, 25 or 50 per cent of the month's fee. It excludes free use and third-party deployed models such as DeepSeek's directly supplied ones (10). Generally available since 7 April 2026, with some models marked preview (10).\n\n### Schema \u0026 documentation: Tencent Cloud TokenHub +15\n\n- Router.com (Ramp Router) (58): Router, scored on the API lines. No OpenAPI or other machine-readable contract found. /openapi.json on docs.router.com returns the docs app shell. The API follows the OpenAI and Anthropic wire formats, which this checklist doesn't credit to a router, the same reading as RouterPlus (0 of 25). llms.txt and a Markdown copy of every page at the same path with `.md` (10). Pages say which endpoint to prefer and why, what isn't served (embeddings, files, batches), which Chat Completions controls return 501, and which workload suits which job (17 of 20). Router-only fields are tabled with types and bounds, the route selector rules are stated (`model` or `models` but never both, 1 to 15 candidates), over-limit timeouts are a 400 naming the maximum, and the model list documents a typed `router` object with a `schema_version`. Request bodies otherwise follow the upstream formats (12 of 15). curl, OpenAI SDK, Anthropic SDK, LangChain, Vercel AI SDK, LlamaIndex and Pydantic AI examples, and an error reference with a status, code and action for each case (15). Paths sit under `/v1` and the model object is versioned, but no API changelog or dated release notes were found (4 of 15).\n- Tencent Cloud TokenHub (73): Router, scored on the API lines. No OpenAPI file for the inference routes. Field pages document the OpenAI Chat Completions, OpenAI Responses and Anthropic Messages formats as TokenHub implements them, and the control plane is a Tencent Cloud API 3.0 service (version 2026-03-22) with typed parameters, API Explorer and SDKs (12 of 25). An llms.txt at cloud.tencent.com/document/product/1823/llms.txt links a Markdown copy of each docs page (10). The docs say which models support thinking, tools, structured output and caching, how TokenHub departs from each standard protocol, and which DeepSeek model suits which job. The quickstart's examples still use `deepseek-v3`, which is not in the model list, and Qwen3.5 stays in the list with a past shutdown date (13 of 20). Protocol pages list each field with type, required flag and default, and control-plane parameters carry enums and required flags (10 of 15). Examples in curl, Python, Node.js, Java and Go, and an error page listing 30 codes with HTTP status, cause and fix (14 of 15). Paths carry `/v1`, release notes are dated monthly from 7 April to 24 October 2026, and the control-plane API has a dated history of 26 releases to 18 September 2026 (14 of 15).\n\n### Maintenance \u0026 community: Tencent Cloud TokenHub +14\n\n- Router.com (Ramp Router) (59): Router, read on the model lines for a closed service. The Provider Terms Schedule was updated on 26 October 2026, and the Ramp CLI that ships the `router` commands released v0.2.82 on 27 October (30). Models carry a `deprecated` status and the docs list deprecated and retired models, but no notice period is stated, and the Baseten retirement note gives no date and says requests aren't redirected (4 of 12). Provider-specific Baseten ids and several Fireworks models were retired without dates. The API host moved from router-api.ramp.com to api.router.com, and the old host still answers (3 of 8). No public API changelog. Support is a dashboard button and router@ramp.com, not tested (5 of 15). ramp-cli issue replies were not read, because GitHub's API wasn't available to this session (3 of 10). No API SDK. The Ramp CLI (MIT, npm @ramp/router and @ramp/cli at 0.2.82, Homebrew) sets up agents and keys (7 of 15). The CLI repository has CI, build, npm and router-integration workflows and a tests folder, with 41 commit days since 29 July. CI results were not checked (7 of 10).\n- Tencent Cloud TokenHub (73): Closed service, read on the model lines. The newest release note is dated 24 October 2026 and the price page was updated on 31 October (30). The four retirement notices read gave 21 to 33 days, and eligible callers are switched to a successor at its price. No minimum notice period is written, and DeepSeek-V4.1-Flash (directly supplied) was moved to the 1017 version under the same ids on 17 October 2026 in a notice dated two days later (7 of 12). 18 retirement notices from 21 April to 22 October 2026, 12 of them since 3 August (3 of 8). Dated release notes and announcements, ticket and phone support around the clock and a Q\u0026A community (13 of 15). Replies on the THCLI repository were not sampled (3 of 10). Tencent Cloud SDK 3.0 in several languages covers the control plane and `tencent-tokenhub-cli` 1.0.2 was published on 30 October 2026. No inference SDK of its own (12 of 15). The CLI has four releases since 15 September 2026, lists no runtime dependencies and needs Node.js 18 or later. CI not checked (5 of 10).\n\n### Transparency \u0026 trust: Router.com (Ramp Router) +10\n\n- Router.com (Ramp Router) (64): Closed service under the Router Terms of Service of 31 August 2026, which bar reselling access and building a competing service. The CLI is MIT (16 of 30). The docs FAQ states the one-year default recording, the opt-out and the PII step. The Router Privacy Notice of 19 August 2026 says an account 'can be configured' not to retain content, without naming the default or the one-year period, and every link to it answers 301 to Ramp's general privacy policy. The superseded pilot terms kept data a year and allowed training on de-identified versions (16 of 30). No deprecation policy found. The Terms let Ramp add or remove models at any time, and model retirements in the docs carry no dates (5 of 20). The Provider Terms Schedule names each provider with its training and retention terms, and the FAQ says all models run on US infrastructure. No Router subprocessor list was found (13 of 20).\n- Tencent Cloud TokenHub (54): Closed service under the TokenHub Terms of Service (effective 14 September 2026), the SLA (23 April 2026), a special note on third-party deployed models and the Tencent Cloud Service Agreement, naming Tencent Cloud Computing (Beijing) Co., Ltd. The CLI is Apache-2.0 (18 of 30). The terms and the FAQ agree that inputs are processed on the customer's instructions and not used for training, and clause 2.14 limits retention to what the service needs without periods. The TokenHub privacy policy on privacy.qq.com renders only with JavaScript and was not read (15 of 30). Dated retirement notices, shutdown dates in the model list, a `pre-offline` status in `/v1/models` and a `DiscontinuedAt` field in the control API. Clause 6.3 refunds paid, unused tokens when a third-party model is removed. No minimum notice period is written (13 of 20). Clause 2.13 places processing generally in mainland China for the China site and in Singapore for the international site, and the third-party model list names DeepSeek's Hangzhou company with a link to its terms. No subprocessor list was found (13 of 20).\n\n### Agent ergonomics: Tencent Cloud TokenHub +6\n\n- Router.com (Ramp Router) (77): Router, read on the model lines (tool use, structured output, caching, context, batch, SDKs, errors). Tools pass through on Responses, Messages and Chat Completions, and `GET /v1/models` reports `tools.supported` and `parallel` per model, with `null` where Router doesn't know. Behaviour depends on the model (16 of 20). The docs say JSON Schema output is expected to work across providers subject to model support, and each model carries a `structured_outputs` flag. A request the provider can't represent is a 501 (12 of 15). Cache read and write prices per model, a `prompt_cache_key` session lease of 5 or 30 minutes that keeps a session on the provider with a warm cache, and `cache_control` on Messages (14 of 15). Contexts up to 1,050,000 tokens on GPT-6.1 Sol and 1,048,576 on Kimi K3, a judgement call since a router has no default model (15). No batch route; the docs say Router doesn't serve batches (0 of 10). No SDK of its own. The OpenAI and Anthropic SDKs work with a changed base URL, framework setups are documented, and the MIT Ramp CLI configures six coding agents (5 of 10). Typed codes for every error, a `limit` object naming the cap and who set it, an all-candidates-failed summary, request and trace ids on every response and the serving provider in a header (15).\n- Tencent Cloud TokenHub (83): Router, read on the model lines. Function calling is marked on most chat models in the model list, with behaviour depending on the model routed (14 of 20). Structured output is marked per model and missing on the MiniMax and Qwen models, and an unsupported `response_format` returns code 400006 (12 of 15). Cache-hit prices are published per model, Kimi K3.1 Pro lists five-minute and one-hour cache writes, and a guide covers `prompt_cache_key` and the `X-Session-ID` header for instance affinity (14 of 15). Most listed chat models have contexts of one million tokens, a judgement call since a router has no default model (15). Batch at half price covers only Hy3 and Hy4 preview, reads and writes JSONL in the customer's own COS bucket and is documented for the Guangzhou endpoint (5 of 10). No TokenHub inference SDK. The OpenAI and Anthropic SDKs work with a changed base URL, and Tencent Cloud SDK 3.0 and the `thcli` CLI cover the control plane (8 of 10). Errors return a code, English and Chinese messages, the source, the upstream code and status and a request ID, and stream errors arrive as SSE error frames (15 of 15).\n\n### Security \u0026 auth: Tencent Cloud TokenHub +5\n\n- Router.com (Ramp Router) (66): Router, read on the model lines. Router keys are shown once, can expire, carry lifetime or periodic spend caps, can be locked, unlocked or revoked, and each key has its own model set and default workload. No permission scopes or programmatic rotation were found (24 of 30). The docs FAQ says Ramp-side content recording is on by default and keeps inputs, outputs and tool calls for one year for debugging, semantic analysis and product improvement, with detected personal data removed before product use. The Provider Terms Schedule marks six providers as not training on Router traffic and TypeSafe as 'Not prohibited' (6 of 20). Recording can be switched off account-wide, propagating asynchronously and without deleting existing archives, and flagged content may still be kept up to 30 days. The schedule lists zero data retention for Ramp-provided connections, except up to 30 days for OpenAI GPT-5.5 and later and for Claude Fable 5 and 5.1 (10 of 15). Logs show model, provider, status, tokens, cost, latency, fallback candidates, credential source and routing decisions per request, with usage export to S3 for Router Admins (14 of 15). A valid security.txt on router.com points to Ramp's security address. Ramp's SOC 2 and ISO 27001 reports, per the ramp listing's 8 October check, were not shown to cover Router, which is a separate product under its own terms. No bug bounty found (12 of 20).\n- Tencent Cloud TokenHub (71): Router, read on the model lines. Bearer keys can be limited to chosen models and inference services, up to 200 source IP ranges and daily, monthly or total token quotas, can be disabled or deleted, and can be created in code through CreateApiKey with signed Tencent Cloud credentials. Keys are long-lived with no expiry setting or built-in rotation (26 of 30). Clause 2.17 of the terms says inputs are not used to train Tencent Cloud's own models, and the FAQ says data is not used for training. Inputs to third-party deployed models (DeepSeek's directly supplied ones) go to DeepSeek under its terms (14 of 20). Clause 2.14 keeps data only as long as the service needs, with no periods stated. When a customer asks for generated content without AI labels, Tencent Cloud keeps logs of who received it for at least six months. No zero-retention option was found (7 of 15). Per-call audit logs (request ID, key, client IP, status, tokens, latency) and optional full call logs go to the customer's CLS, billed separately, with usage by key and a monitoring dashboard (14 of 15). No security.txt on cloud.tencent.com, www.tencent.com or tokenhub.tencentmaas.com (404). Tencent's bug bounty through TSRC lists Tencent Cloud in scope. No certification for TokenHub was checked (10 of 20).\n\n## Score by category\n\n| Category | Weight | Router.com (Ramp Router) | Tencent Cloud TokenHub | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 25 | 46 | Tencent Cloud TokenHub +21 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 58 | 73 | Tencent Cloud TokenHub +15 |\n| Agent ergonomics | 13% (16.2 this run) | 77 | 83 | Tencent Cloud TokenHub +6 |\n| Security \u0026 auth | 14% (17.5 this run) | 66 | 71 | Tencent Cloud TokenHub +5 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 35 | Router.com (Ramp Router) +5 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 59 | 73 | Tencent Cloud TokenHub +14 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 64 | 54 | Router.com (Ramp Router) +10 |\n| Negative events | ≤15 | 0 | -3 | |\n| **Total** | | **54.3 · C** | **59.5 · C** | |\n\n## Facts side by side\n\n| Fact | Router.com (Ramp Router) | Tencent Cloud TokenHub |\n| --- | --- | --- |\n| Kind | Model router | Model router |\n| Vendor | Ramp | Tencent Cloud |\n| Hosted endpoint | `https://api.router.com/v1` | `https://tokenhub.tencentmaas.com/v1` |\n| Transports | HTTP | HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | Closed service under the Router Terms of Service (last updated 31 August 2026). The Ramp CLI that configures coding agents for Router is MIT. | Proprietary service under the TokenHub Terms of Service, the TokenHub SLA and the Tencent Cloud Service Agreement, with a special note for third-party deployed models. The `tencent-tokenhub-cli` package is Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-27 | 2026-10-24 |\n| Terms last updated | couldn't be read | couldn't be read |\n| Privacy policy last updated | couldn't be read | couldn't be read |\n| Customer content may train models | couldn't be read | couldn't be read |\n| Terms restrict automated access | couldn't be read | couldn't be read |\n| Terms restrict benchmarking | couldn't be read | couldn't be read |\n| Terms or service can change without notice | couldn't be read | couldn't be read |\n| Arbitration or class-action waiver | couldn't be read | couldn't be read |\n| Popularity | 1.7k npm/wk | 204 npm/wk |\n\n## How the scores have moved\n\n### Router.com (Ramp Router)\n\n- -0.2 on 30 October 2026: checklist\n\n### Tencent Cloud TokenHub\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Router.com (Ramp Router).** Detailed Markdown docs with typed error codes, per-model capability data and routing an agent can set per request. No OpenAPI document, status page, changelog or published rate limits were found. Signup needs a US business email in a browser, and Ramp records prompts and outputs for a year by default unless switched off.\n\n**Tencent Cloud TokenHub.** Keys can be limited to chosen models, source IPs and token quotas, errors name their source and code, and a 99.5% SLA covers paid use of models Tencent runs. Sign-up needs a Tencent Cloud account with real-name verification, prices are in CNY, no public status page was found, and 18 model retirement notices ran from April to October 2026.\n\n## Before you call either\n\n### Router.com (Ramp Router)\n\n1. Switch off content recording in Settings before sending private data. It is on by default and keeps prompts and outputs for a year\n2. Read model ids from `GET /v1/models` at runtime. Ids are account-specific, an unknown one is a 404, and Gemini ids need your own Google key\n3. Use `POST /v1/responses` with a `models` list for fallbacks. Router stops falling back once a stream has started\n4. Set `fallback_timeout` and `provider_timeout`, or `allow_flex_tier: false`, when latency matters. Flex routing is on by default\n5. Treat both `401 invalid_api_key` and `401 api_key_deactivated` as a possibly locked key, and stop retrying on `402`\n\n### Tencent Cloud TokenHub\n\n1. Use `https://tokenhub.tencentmaas.com/v1` with keys made for Guangzhou and `https://tokenhub-intl.tencentmaas.com/v1` with keys made for Singapore. Keys do not work across the two\n2. Send the key as `Authorization: Bearer` on the OpenAI paths and as `x-api-key` on `/v1/messages`\n3. Parse `error.code` as a string or a number, since 429 codes can come back as integers, and wait for `Retry-After` before retrying\n4. Take model ids from `GET /v1/models` and watch for `pre-offline`. The quickstart's `deepseek-v3` example is not in the current model list\n5. Expect DeepSeek prices to double on weekdays from 9am to noon and 2pm to 6pm Beijing time, when the peak rate applies\n\n## Questions\n\n### Which is better for AI agents, Router.com (Ramp Router) or Tencent Cloud TokenHub?\n\nTencent Cloud TokenHub scores 59.5 (C) on agent readiness against Router.com (Ramp Router)'s 54.3 (C), and leads in 5 of 7 scored categories. Router.com (Ramp Router) leads on payments \u0026 pricing and transparency \u0026 trust.\n\n### Do Router.com (Ramp Router) and Tencent Cloud TokenHub need an API key?\n\nBoth need an API key.\n\n### Can an agent call Router.com (Ramp Router) and Tencent Cloud TokenHub without installing anything?\n\nYes. Router.com (Ramp Router) has a hosted endpoint at https://api.router.com/v1 and Tencent Cloud TokenHub at https://tokenhub.tencentmaas.com/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/ramp-router-vs-tencent-tokenhub.json, and with the fewest tokens: https://www.anchorterminal.com/compare/ramp-router-vs-tencent-tokenhub.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"ramp-router\", \"b\": \"tencent-tokenhub\"}`. From a terminal: `anchor compare ramp-router tencent-tokenhub`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/ramp-router.json and https://www.anchorterminal.com/api/v1/tools/tencent-tokenhub.json\n\n## Other comparisons with Router.com (Ramp Router) or Tencent Cloud TokenHub\n\n- [Claude API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/anthropic-api-vs-ramp-router.md)\n- [Claude API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/anthropic-api-vs-tencent-tokenhub.md)\n- [BlockRun.AI vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/blockrun-ai-vs-ramp-router.md)\n- [BlockRun.AI vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/blockrun-ai-vs-tencent-tokenhub.md)\n- [Cerebras Inference vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/cerebras-inference-vs-ramp-router.md)\n- [Cerebras Inference vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/cerebras-inference-vs-tencent-tokenhub.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 Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-tencent-tokenhub.md)\n- [Cloudflare Workers AI vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-ramp-router.md)\n- [Cloudflare Workers AI vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-tencent-tokenhub.md)\n- [Cohere Chat API (Command models) vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/cohere-chat-vs-ramp-router.md)\n- [Cohere Chat API (Command models) vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/cohere-chat-vs-tencent-tokenhub.md)\n- [DeepInfra vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/deepinfra-vs-ramp-router.md)\n- [DeepInfra vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/deepinfra-vs-tencent-tokenhub.md)\n- [DeepSeek API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/deepseek-api-vs-ramp-router.md)\n- [DeepSeek API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/deepseek-api-vs-tencent-tokenhub.md)\n- [Glimpse vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/elorian-glimpse-vs-ramp-router.md)\n- [Glimpse vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/elorian-glimpse-vs-tencent-tokenhub.md)\n- [Fireworks AI Inference vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/fireworks-inference-vs-ramp-router.md)\n- [Fireworks AI Inference vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/fireworks-inference-vs-tencent-tokenhub.md)\n- [Gemini Developer API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/gemini-api-vs-ramp-router.md)\n- [Gemini Developer API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/gemini-api-vs-tencent-tokenhub.md)\n- [GroqCloud vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/groq-vs-ramp-router.md)\n- [GroqCloud vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/groq-vs-tencent-tokenhub.md)\n- [Jais 3 vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/jais-3-vs-ramp-router.md)\n- [Jais 3 vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/jais-3-vs-tencent-tokenhub.md)\n- [Meta Model API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/meta-model-api-vs-ramp-router.md)\n- [Meta Model API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/meta-model-api-vs-tencent-tokenhub.md)\n- [MiniMax API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/minimax-api-vs-ramp-router.md)\n- [MiniMax API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/minimax-api-vs-tencent-tokenhub.md)\n- [Mistral AI API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/mistral-api-vs-ramp-router.md)\n- [Mistral AI API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/mistral-api-vs-tencent-tokenhub.md)\n- [Muse Spark Open vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/muse-spark-open-vs-ramp-router.md)\n- [Muse Spark Open vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/muse-spark-open-vs-tencent-tokenhub.md)\n- [Nemotron 3.5 Super VL vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-ramp-router.md)\n- [Novita AI vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/novita-ai-vs-ramp-router.md)\n- [Novita AI vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/novita-ai-vs-tencent-tokenhub.md)\n- [OpenAI API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/openai-api-vs-ramp-router.md)\n- [OpenAI API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/openai-api-vs-tencent-tokenhub.md)\n- [OpenRouter vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/openrouter-vs-ramp-router.md)\n- [OpenRouter vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/openrouter-vs-tencent-tokenhub.md)\n- [Prism Inference vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/prism-inference-vs-ramp-router.md)\n- [Router.com (Ramp Router) vs Beam 1.0](https://www.anchorterminal.com/compare/ramp-router-vs-reflection-beam.md)\n- [Router.com (Ramp Router) vs SambaCloud](https://www.anchorterminal.com/compare/ramp-router-vs-sambanova.md)\n- [Router.com (Ramp Router) vs SiliconFlow](https://www.anchorterminal.com/compare/ramp-router-vs-siliconflow.md)\n- [Router.com (Ramp Router) vs Simplismart](https://www.anchorterminal.com/compare/ramp-router-vs-simplismart.md)\n- [Router.com (Ramp Router) vs StepFun API](https://www.anchorterminal.com/compare/ramp-router-vs-stepfun-api.md)\n- [Router.com (Ramp Router) vs Together AI Inference](https://www.anchorterminal.com/compare/ramp-router-vs-together-inference.md)\n- [Beam 1.0 vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/reflection-beam-vs-tencent-tokenhub.md)\n- [SambaCloud vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/sambanova-vs-tencent-tokenhub.md)\n- [SiliconFlow vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/siliconflow-vs-tencent-tokenhub.md)\n- [Simplismart vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/simplismart-vs-tencent-tokenhub.md)\n- [StepFun API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/stepfun-api-vs-tencent-tokenhub.md)\n- [Tencent Cloud TokenHub vs Together AI Inference](https://www.anchorterminal.com/compare/tencent-tokenhub-vs-together-inference.md)\n- [Nemotron 3.5 Super VL vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-tencent-tokenhub.md)\n- [Prism Inference vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/prism-inference-vs-tencent-tokenhub.md)\n- [Antseed vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/antseed-vs-ramp-router.md)\n- [Antseed vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/antseed-vs-tencent-tokenhub.md)\n- [Router.com (Ramp Router) vs RouterPlus](https://www.anchorterminal.com/compare/ramp-router-vs-routerplus.md)\n- [Router.com (Ramp Router) vs Vercel AI Gateway](https://www.anchorterminal.com/compare/ramp-router-vs-vercel-ai-gateway.md)\n- [RouterPlus vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/routerplus-vs-tencent-tokenhub.md)\n- [Tencent Cloud TokenHub vs Vercel AI Gateway](https://www.anchorterminal.com/compare/tencent-tokenhub-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": "2026-11-02", "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": "Router.com (Ramp Router) vs Tencent Cloud TokenHub", "url": "" } ], "description": "Tencent Cloud TokenHub scores 59.5 (C) to Router.com's 54.3 (C) for model routing. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Router.com (Ramp Router) C 54.3", "Tencent Cloud TokenHub C 59.5", "scores" ], "h1": "Router.com (Ramp Router) vs Tencent Cloud TokenHub", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/ramp-router-vs-tencent-tokenhub", "published": "2026-10-01", "section": "tools", "title": "Router.com vs Tencent Cloud TokenHub for AI agents (2026)", "toc": null, "updated": "2026-11-01", "url": "https://www.anchorterminal.com/compare/ramp-router-vs-tencent-tokenhub" }, "tokens": { "markdown": 7650, "slim": 4330 }, "version": 1 }