# Router.com (Ramp Router) > 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. - Canonical: https://www.anchorterminal.com/tools/ramp-router - Pricing: https://www.anchorterminal.com/tools/ramp-router#pricing - Reviews: https://www.anchorterminal.com/tools/ramp-router#reviews - Markdown: https://www.anchorterminal.com/tools/ramp-router.md (~9,150 tokens) - Slim: https://www.anchorterminal.com/tools/ramp-router.min.md (~1,930 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/ramp-router.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key) - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) - Updated: 2026-10-28 ## Overview **Grade C · 54.5/100 · rank #798 of 1218 · #21 in Model APIs & inference · not agent-ready · confidence medium** ## Assessment 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. ## Facts | Field | Value | | --- | --- | | Vendor | Ramp (https://router.com) | | Kind | Model router | | Category | Model APIs & inference (https://www.anchorterminal.com/categories/inference) | | Transport | HTTP | | Endpoint | `https://api.router.com/v1` | | Auth | API key · 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 | Pay per use (0% fee) · 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. | | x402 | No · 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. | | 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. | | Packages | npm: `@ramp/router` | | Source | https://github.com/ramp-public/ramp-cli | | Docs | https://docs.router.com | | llms.txt | https://docs.router.com/llms.txt | | Last release | 2026-10-27 | | npm downloads / week | 1,667 | | Surface graded | The gateway at https://api.router.com/v1, read from its docs, model pages, legal terms and site on 27 October 2026. No account was created and no call was made. An unauthenticated `GET /v1/models` answered 401 `invalid_api_key`. app.router.com is disallowed by robots.txt and was not read | | Endpoints | `GET /v1/models`, `POST /v1/responses`, `POST /v1/chat/completions`, `POST /v1/messages`, `POST /v1/messages/count_tokens`, `POST /v1/decisions` (limited availability) and `POST /v1/systemone` (TypeSafe Jev) | | Not available | Embeddings, files and batches. Chat Completions has no `models` fallback list, timeouts or `usage.cost`, and answers 501 for `logprobs`, `n` above 1, `seed`, `logit_bias` and legacy functions. Messages has no `models` list and no `usage.cost` | | Routing | Fallback lists of up to 15 `provider:model[:tier]` candidates on Responses. Cost-efficient Flex routing on by default, cross-provider routing by cost or throughput, Switchyard (NVIDIA NeMo) for coding agents, Jev Auto Routing (limited availability), benchmark aliases and shadow models, grouped in saved workloads | | Rate limits | No request or token limits published. The docs say rate limits vary by model. Technical limits are a 100 MiB request body, 15 candidates and 100 keys per user | | Errors | OpenAI or Anthropic error envelopes with a `code` per case, a `limit` object naming the spend cap and who set it, `x-request-id` and `x-trace-id` on every response, and `X-Router-Provider` naming the provider that answered. Provider `retry-after` headers are passed through | | Bring your own key | OpenAI, Anthropic, Google Gemini (required for Gemini), Fireworks, xAI, Baseten and Sail Research keys, and Amazon Bedrock through an AWS connection. Shared-key fallback is on by default and billed normally. Claude organisation billing is in limited availability | | Data handling | Ramp-side content recording on by default, kept for one year, switched off account-wide in Settings with asynchronous propagation and no deletion of existing archives. Flagged content may be kept up to 30 days even when storage is off. Shadow models need recording on | | Connectors | Beta. The Ramp CLI connects Claude Code, Codex and OpenCode to an MCP endpoint at https://api.router.com/v1/mcp for apps such as Slack, GitHub, Google Drive and Linear. Setup needs Sign in with Ramp and browser approval on every run, and some tools can write | | Company | Ramp Business Corporation, 28 West 23rd Street, New York, per the Router Terms of Service. A Router account is separate from a Ramp spend-management account | | 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 | | JSON | https://www.anchorterminal.com/api/v1/tools/ramp-router.json | ## Score breakdown (methodology v0.7, October 2026 research run) Assessed 2026-10-27 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 25 | 5.0 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 58 | 9.4 | | Agent ergonomics | 13% | 16.2 | 77 | 12.5 | | Security & auth | 14% | 17.5 | 66 | 11.6 | | Payments & pricing | 10% | 12.5 | 40 | 5.0 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 59 | 5.2 | | Transparency & trust (editorial 50, provenance 83) | 7% | 8.8 | 67 | 5.9 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **54.5 → C** | ### Why each score - Reliability 25 (checked 2026-10-27): 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). - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 58 (checked 2026-10-27): 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). - Agent ergonomics 77 (checked 2026-10-27): 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). - Security & auth 66 (checked 2026-10-27): 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). - Payments & pricing 40 (checked 2026-10-27): No x402, MPP or L402 in any of the 41 docs pages. Calls draw on account credit (0). Per-token prices for every model are public at router.com/models and in the supported-models page without a login (20). Router.com says routing is free through 2026 and the first $26 of credits are free, and BYOK requests carry no Router charge. We did not sign up to confirm that no card is asked for (20). A person signs up in the browser with a US business email or Sign in with Ramp, and the CLI creates keys only after browser approval (0). - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 59 (checked 2026-10-27): 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). - Transparency & trust 67 (checked 2026-10-27): 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). Fix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (16 items): https://www.anchorterminal.com/fixes/ramp-router.md (JSON https://www.anchorterminal.com/fixes/ramp-router.json) ### What we couldn't check - unchecked: the dashboard at app.router.com, which robots.txt disallows, so the signup form, settings defaults and whether a card is asked for were not seen - unchecked: replies on the ramp-cli GitHub issue tracker and CI results, because GitHub's API wasn't available to this session - No routing price after 31 December 2026 was found - The launch post says Router is open 'to everyone', while the Router Terms and router.com limit it to business users in the United States with a business email domain. Recorded, not deducted - Router.com says models are 'all US-hosted with options for ZDR', while BYOK Gemini defaults to the `global` Vertex location and Bedrock global profiles can route across all commercial AWS regions. Shared-key routes are stated as US-only - The Router Privacy Notice is linked from router.com and the docs, but its URLs answer 301 to Ramp's general privacy policy, so a reader following the link doesn't see the Router notice - Whether Ramp's SOC 2 and ISO 27001 reports cover Router, which runs under separate terms ### Sources - launch post, 19 August 2026, free routing through 2026: (seen 2026-10-27) - homepage, $26 credits, provider list, cost claims: (seen 2026-10-27) - router.com FAQ, US eligibility, free through 2026: (seen 2026-10-27) - docs llms.txt index: (seen 2026-10-27) - endpoint, authentication, error shapes: (seen 2026-10-27) - errors and limits, retry-after, technical limits: (seen 2026-10-27) - Responses and Messages, Router-only fields, usage.cost: (seen 2026-10-27) - list models, router object: (seen 2026-10-27) - docs FAQ, content recording default and one-year retention: (seen 2026-10-27) - signup eligibility, business email: (seen 2026-10-27) - supported and deprecated models with prices: (seen 2026-10-27) - fallbacks, billing of truncated attempts: (seen 2026-10-27) - bring your own key, shared-key fallback: (seen 2026-10-27) - monitor and debug, logs: (seen 2026-10-27) - connectors (beta): (seen 2026-10-27) - Router Terms of Service, 31 August 2026 (read from the legal site's script): (seen 2026-10-27) - Router Privacy Notice, 19 August 2026 (link answers 301; read from the legal site's script): (seen 2026-10-27) - Provider Terms Schedule, 26 October 2026: (seen 2026-10-27) - Ramp product schedule, Router (Early Access) section: (seen 2026-10-27) - Ramp CLI source, tags and workflows: (seen 2026-10-27) - npm @ramp/router latest and weekly downloads: (seen 2026-10-27) - security.txt: (seen 2026-10-27) - RDAP for router.com: (seen 2026-10-27) ## Score history Every move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/ramp-router/history.json - 2026-10-27: graded 54.5 C (methodology 0.7) ## Who's behind it (provenance 83/100, checked 2026-10-27) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | Ramp Business Corporation | 20/20 | | Domain age | router.com, registered 1995-07-26 (31 years) | 15/15 | | Endpoint on the vendor's domain | api.router.com | 15/15 | | Terms of service | published | 10/10 | | Privacy policy | published | 10/10 | | Status page | not found | 0/10 | | Changelog | not found | 0/10 | | security.txt | valid | 10/10 | | People named | 4 named with their role, 3 with a public profile | 10/10 | | Support route | a support address, help pages, a community | 5/5 | 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. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service** (https://ramp.com/legal/developer-terms/developer-terms/router-terms-of-service), not read yet. **Privacy policy** (https://ramp.com/legal/privacy-terms/privacy-terms/router-privacy-notice), not read yet. ## Humans behind the project (researched 2026-10-27 from public pages, not part of the grade) ### Key people - Eric Glyman, Co-founder and Co-CEO, Ramp. LinkedIn: https://www.linkedin.com/in/eglyman. X: https://x.com/eglyman - Karim Atiyeh, Co-founder and Co-CEO, Ramp. LinkedIn: https://www.linkedin.com/in/karimatiyeh. X: https://x.com/karimatiyeh - Veeral Patel, Head of Applied AI, Ramp, leading the team behind Ramp Router. LinkedIn: https://www.linkedin.com/in/patelveeral/. X: https://x.com/vral - Rahul Sengottuvelu, CTO, Ramp - Note: founders from their author pages on ramp.com, which give eric glyman and karim atiyeh as co-founder & co-ceo, and the 25 june 2026 post that calls karim atiyeh eric glyman's co-founder. no first-hand page read lists ramp's full founding group, so the roster may be incomplete. veeral patel's author page says he leads the team behind ramp router, and he wrote the launch post. rahul sengottuvelu is quoted as cto, ramp on router.com and named cto in the 25 june post. linkedin and x accounts are the ones the ramp.com author pages link (eric glyman's x is linked as twitter.com/eglyman). rahul sengottuvelu has no author page in ramp's author sitemap, so no accounts are given for him. data/humans/ramp.json names no people. - Ramp Business Corporation: LinkedIn https://www.linkedin.com/company/ramp X https://x.com/tryramp GitHub https://github.com/ramp-public ### Getting support - Support email: router@ramp.com - Help: https://docs.router.com/resources/support-and-feedback - Help: https://docs.router.com/resources/faq - Community (Ramp CLI issues on GitHub): https://github.com/ramp-public/ramp-cli/issues - Sources: https://ramp.com/authors/eric-glyman, https://ramp.com/authors/karim-atiyeh, https://ramp.com/authors/veeral-patel, https://ramp.com/blog/welcoming-my-co-founder-karim-as-co-ceo-of-ramp, https://ramp.com/blog/router-launch, https://router.com/, https://docs.router.com/resources/support-and-feedback.md, https://docs.router.com/resources/faq.md, https://router.com/.well-known/security.txt, https://github.com/ramp-public/ramp-cli ## Live (updated 2026-10-28 01:25 UTC) - Right now: up, HTTP 401, 326 ms, checked 2026-10-28 01:25 UTC (get on `https://api.router.com/v1`, asks for auth) - Uptime 24h 100.0% (18 probes) · 30 days 100.0% (18 probes) · p50 329 ms · p95 429 ms - Always current: https://www.anchorterminal.com/api/v1/live/ramp-router.json ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Prices | Item | Price | Unit | Note | | --- | --- | --- | --- | | Routing fee | 0% | percentage fee | Free through 2026. Models are billed at list price | | Claude Opus 5.5 input | $4 | per 1M tokens | claude-opus-5-5, 1,000,000-token context | | Claude Opus 5.5 output | $20 | per 1M tokens | | | GPT-6.1 Sol input | $2 | per 1M tokens | gpt-6.1-sol, 1,050,000-token context | | GPT-6.1 Sol output | $10 | per 1M tokens | | | Kimi K3 input | $3 | per 1M tokens | kimi-k3, served by Fireworks or Baseten | | Kimi K3 output | $15 | per 1M tokens | | Across all listings: https://www.anchorterminal.com/prices/index.md ## 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 ## Before you call it (notes for agents) 1. Switch off content recording in Settings before sending private data. It is on by default and keeps prompts and outputs for a year 2. 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 3. Use `POST /v1/responses` with a `models` list for fallbacks. Router stops falling back once a stream has started 4. Set `fallback_timeout` and `provider_timeout`, or `allow_flex_tier: false`, when latency matters. Flex routing is on by default 5. Treat both `401 invalid_api_key` and `401 api_key_deactivated` as a possibly locked key, and stop retrying on `402` ## Connect Install: ```bash curl -fsSL https://router.com/install.sh | sh # Ramp CLI, configures Claude Code, Codex, OpenCode, Pi, Hermes or Conductor ``` First request: ```bash curl https://api.router.com/v1/responses \ -H "Authorization: Bearer $RAMP_ROUTER_API_KEY" \ -H "Content-Type: application/json" \ -d '{"models":["openai:gpt-5.4-mini","fireworks:accounts/fireworks/models/kimi-k3"],"input":"Reply with one word: pong.","max_output_tokens":16}' ``` ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | Vercel AI Gateway | B | 66.8 | 315 | inference.router, inference.llm, inference.decision | no | https://www.anchorterminal.com/tools/vercel-ai-gateway.md | | RouterPlus | D | 51.3 | 898 | inference.router, inference.llm, inference.decision | no | https://www.anchorterminal.com/tools/routerplus.md | | OpenRouter | B | 68.6 | 239 | inference.llm, inference.router | no | https://www.anchorterminal.com/tools/openrouter.md | | Cloudflare AI Gateway | B | 66.9 | 304 | inference.llm, inference.router | no | https://www.anchorterminal.com/tools/cloudflare-ai-gateway.md | | Granite Switch 4.1 | C | 59.4 | 629 | inference.decision, inference.llm | no | https://www.anchorterminal.com/tools/granite-switch.md | | Ollama | C | 56.6 | 732 | inference.llm, inference.decision | no | https://www.anchorterminal.com/tools/ollama.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - Ramp opened Router.com to everyone on 19 August 2026 with free routing through 2026, $26 of model credits and 50% off GPT-5.6 Sol until 18 September (source: ) - Before that it ran as a design-partner pilot with a waitlist and $100 of credits for up to 500 applicants, under offer terms dated 27 July 2026 and superseded on 19 August (Ramp Router Design Partner Pilot Offer Terms, read from ramp.com/legal) - The docs FAQ says Ramp-side content recording is on by default. Inputs, outputs and tool calls are kept for one year for debugging, semantic analysis and product improvement, with detected personal data removed before product use. It can be switched off account-wide in Settings (source: ) - Router.com says it is for individual developers and teams in the U.S., and the Router Terms limit use to business users in the United States and locations Ramp approves (source: ) - The supported-models table listed 93 entries from 13 model makers on 27 October 2026. Gemini models need the caller's own Google key (source: ) - Ramp's Provider Terms Schedule (last updated 26 October 2026) marks OpenAI, Anthropic, Baseten, Fireworks, xAI and Meta as not training on Router inputs or outputs and TypeSafe as 'Not prohibited' (source: ) - The Router Privacy Notice links on router.com and in the docs answer 301 to Ramp's general privacy policy. The notice itself (last updated 19 August 2026) was read from the legal site's script bundle - Router.com claims routing cuts inference costs by 40% on average and that Router cut Ramp's own LLM costs by 30%. These are Ramp's figures (source: ) - #21 of 31 in Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md - All 466 models comparisons: https://www.anchorterminal.com/compare/inference/index.md ## Compare - [Claude API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/anthropic-api-vs-ramp-router.md): BB 77.3 vs C 54.5 - [BlockRun.AI vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/blockrun-ai-vs-ramp-router.md): BB 72.4 vs C 54.5 - [Cerebras Inference vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/cerebras-inference-vs-ramp-router.md): B 68.6 vs C 54.5 - [Cloudflare AI Gateway vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-ramp-router.md): B 66.9 vs C 54.5 - [Cloudflare Workers AI vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-ramp-router.md): B 68.3 vs C 54.5 - [Cohere Chat API (Command models) vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/cohere-chat-vs-ramp-router.md): B 64.7 vs C 54.5 - [DeepInfra vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/deepinfra-vs-ramp-router.md): B 63.1 vs C 54.5 - [DeepSeek API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/deepseek-api-vs-ramp-router.md): E 45.8 vs C 54.5 - [Glimpse vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/elorian-glimpse-vs-ramp-router.md): D 49 vs C 54.5 - [Fireworks AI Inference vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/fireworks-inference-vs-ramp-router.md): BB 73.5 vs C 54.5 - [Gemini Developer API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/gemini-api-vs-ramp-router.md): B 65.5 vs C 54.5 - [GroqCloud vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/groq-vs-ramp-router.md): BB 74.5 vs C 54.5 - [Jais 3 vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/jais-3-vs-ramp-router.md): D 52.1 vs C 54.5 - [Meta Model API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/meta-model-api-vs-ramp-router.md): D 52.5 vs C 54.5 - [MiniMax API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/minimax-api-vs-ramp-router.md): C 55.2 vs C 54.5 - [Mistral AI API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/mistral-api-vs-ramp-router.md): BB 71.2 vs C 54.5 - [Muse Spark Open vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/muse-spark-open-vs-ramp-router.md): D 53.5 vs C 54.5 - [Nemotron 3.5 Super VL vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-ramp-router.md): C 59 vs C 54.5 - [Novita AI vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/novita-ai-vs-ramp-router.md): D 53.5 vs C 54.5 - [OpenAI API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/openai-api-vs-ramp-router.md): A 82.9 vs C 54.5 - [OpenRouter vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/openrouter-vs-ramp-router.md): B 68.6 vs C 54.5 - [Prism Inference vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/prism-inference-vs-ramp-router.md): C 60.3 vs C 54.5 - [Router.com (Ramp Router) vs Beam 1.0](https://www.anchorterminal.com/compare/ramp-router-vs-reflection-beam.md): C 54.5 vs D 53.4 - [Router.com (Ramp Router) vs SambaCloud](https://www.anchorterminal.com/compare/ramp-router-vs-sambanova.md): C 54.5 vs B 66.5 - [Router.com (Ramp Router) vs SiliconFlow](https://www.anchorterminal.com/compare/ramp-router-vs-siliconflow.md): C 54.5 vs D 47 - [Router.com (Ramp Router) vs StepFun API](https://www.anchorterminal.com/compare/ramp-router-vs-stepfun-api.md): C 54.5 vs E 44.4 - [Router.com (Ramp Router) vs Together AI Inference](https://www.anchorterminal.com/compare/ramp-router-vs-together-inference.md): C 54.5 vs B 67.8 - [Antseed vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/antseed-vs-ramp-router.md): C 55.1 vs C 54.5 - [Router.com (Ramp Router) vs RouterPlus](https://www.anchorterminal.com/compare/ramp-router-vs-routerplus.md): C 54.5 vs D 51.3 - [Router.com (Ramp Router) vs Vercel AI Gateway](https://www.anchorterminal.com/compare/ramp-router-vs-vercel-ai-gateway.md): C 54.5 vs B 66.8 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on router.com or one of its subdomains, or the README of github.com/ramp-public/ramp-cli. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "ramp-router", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html Router.com (Ramp Router) on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Router.com (Ramp Router) on Anchor Terminal](https://www.anchorterminal.com/badges/ramp-router.svg)](https://www.anchorterminal.com/tools/ramp-router) ``` Plain link: ```html Router.com (Ramp Router) on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Router.com (Ramp Router) is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/ramp-router-dark.png - Light: https://www.anchorterminal.com/assets/share/ramp-router-light.png - Create a video and download its frames: https://www.anchorterminal.com/assets/listing-video/index.html?listing=ramp-router --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp