# Inkling 2 Small vs RouterPlus (slim)

> Inkling 2 Small scores 52.1 (D) to RouterPlus's 50.3 (D) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/inkling-2-small-vs-routerplus.md (~6,350 tokens) · this version ~3,280 tokens · JSON https://www.anchorterminal.com/compare/inkling-2-small-vs-routerplus.json · canonical https://www.anchorterminal.com/compare/inkling-2-small-vs-routerplus
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-06
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Inkling 2 Small scores 52.1 (D) on agent readiness against RouterPlus's 50.3 (D), and leads in 3 of 7 scored categories. RouterPlus leads on reliability, agent ergonomics and payments & pricing. Both do llm inference.

- Inkling 2 Small: D 52.1, rank #899 of 1354 · https://www.anchorterminal.com/tools/inkling-2-small.min.md
- RouterPlus: D 50.3, rank #962 of 1354 · https://www.anchorterminal.com/tools/routerplus.min.md
- Inkling 2 Small, good for Developers who want a capable multimodal open-family model through an OpenAI-compatible API today, or to fine-tune it on Tinker, and who can live with a beta surface until the weights are published. Ahead on Schema & documentation, 70 against 59; Maintenance & community, 75 against 44; Transparency & trust, 64 against 41.
- RouterPlus, good for Teams that call Claude, GPT and open-weight models from one key and want the cost of every call in the response, with their own provider keys where they have them. Ahead on Reliability, 42 against 30; Agent ergonomics, 71 against 62; Payments & pricing, 40 against 20.

| Category | Inkling 2 Small | RouterPlus |
| --- | --- | --- |
| Reliability (16%) | 30 | 42 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 70 | 59 |
| Agent ergonomics (13%) | 62 | 71 |
| Security & auth (14%) | 57 | 59 |
| Payments & pricing (10%) | 20 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 75 | 44 |
| Transparency & trust (7%) | 64 | 41 |

| Fact (where they differ) | Inkling 2 Small | RouterPlus |
| --- | --- | --- |
| Kind | Model API | Model router |
| Vendor | Thinking Machines Lab | RouterPlus |
| Hosted endpoint | `https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1` | `https://api.routerplus.com/v1` |
| Transports |  | HTTP |
| Licence | Proprietary for now, used through Tinker under the Tinker Terms of Use and Thinking Machines' Model Acceptable Use Policy, per the model card. Thinking Machines says it will publish the weights under Apache 2.0 the week after launch, once outside safety testing is done | Closed service. No terms of service for the gateway were found on routerplus.com or app.routerplus.com on 13 October 2026. The only terms on the site govern the capacity request form and name EVO HQ Inc, a Delaware corporation (https://routerplus.com/capacity/terms/). |
| Last release | 2026-11-05 | none |
| Terms last updated | not read yet | no document linked |
| Privacy policy last updated | not read yet | no document linked |

Why the edge:
- Maintenance & community, Inkling 2 Small +31: Inkling 2 Small 75 (Model reading. Released 5 November 2026 (30). Churn and notice in place of release counts: Inkling, Inkling-Small (30 July) and Inkling 2 Small in about four months, and a deprecations page with dated retirements and a promise to 'aim to give advance notice' by email, with no stated period, per the tinker listing (10 of 20). A public changelog and a support address and Discord, per the tinker listing (10 of 15). Current official SDKs, Tinker's Python SDK and the OpenAI-compatible endpoint (15). SDK and cookbook CI, per the tinker listing (10). 30 + 10 + 10 + 15 + 10 = 75.); RouterPlus 44 (Router, read on the model lines. No changelog or release notes found. The blog, re-read on 4 November 2026, dates the launch of ScaleDown's extract-1 and summarize-1 on chat completions and classify-1 on the decisions API to 13 October 2026, and the catalogue now lists 105 chat models against 19 on 13 October, so the API changed within the last 30 days (30). The docs also date a console change on 17 October 2026 (keys can be copied again), which isn't counted, since it changes the console and not the API. Models carry a `deprecation_date` that delists them automatically, with no notice period stated (3 of 12). `POST /v1/signup` and the magic-link route were removed and Optimize is paused, none with a date we could find (3 of 8). No public changelog. Support is reached through the console and an email address, and wasn't tested (3 of 15). No public issue tracker for the gateway (0 of 10). No official SDK. The docs rely on the OpenAI and Anthropic SDKs and give client setups (5 of 15). No package or public repository to check (0 of 10).)
- Transparency & trust, Inkling 2 Small +23: Inkling 2 Small 64 (Editorial half. Closed for now under the Tinker Terms of Use and the Model Acceptable Use Policy, per the model card, with Apache 2.0 weights promised the week after launch (15). Terms commit not to use Customer Content for training, keep it only as needed, with a DPA and deletion on request; the privacy notice wasn't re-read, per the tinker listing (15). Dated deprecation notices with no stated period (15). The DPA annex names Google Cloud, Cloudflare, WorkOS and OpenAI with service and location (15). 15 + 15 + 15 + 15 = 60.); RouterPlus 41 (Closed service with no terms of service found. The only terms on the site govern the capacity request form, under EVO HQ Inc (0 of 30). The data policy page is detailed, lists what is stored and why, and gives a 30-day period for request logs and each provider's retention flag. Its 4 November 2026 text, which logs request content by default, no longer agrees with the homepage FAQ; that contradiction is charged once as a misleading claim under negative events, not on this line. There is no privacy policy, no DPA and no retention period for account data such as email addresses (14 of 30, held). Model retirement by `deprecation_date` is documented with no notice period, and no dated deprecation notices were found (4 of 20). The docs name Clerk, Resend and an AWS bucket, and say RouterPlus's own GPUs run in the United States. The form's terms name Supabase, Cloudflare and Resend. No complete subprocessor list or gateway hosting location was found (8 of 20).)
- Payments & pricing, RouterPlus +20: Inkling 2 Small 20 (Published rubric. No payment protocol (0). Per-million-token prices for serverless inference and training published without a login on 6 November (20). No free tier listed, and the quickstart asks for payment details before training, per the tinker listing (0). Sign-up is a browser flow (0). 0 + 20 + 0 + 0 = 20.); RouterPlus 40 (No machine payment protocol found in llms-full.txt. Calls draw on a prepaid balance (0). Per-token prices for every model are public in the docs catalogue and on the model pages with no login, re-read on 4 November 2026 (20). Signup adds no free credit, but inference through the caller's own provider keys carries no RouterPlus charge and needs no credit, the reading Cloudflare AI Gateway's dossier took for the same arrangement. We did not sign up to confirm that no card is asked for (20). A person signs up in the browser through Clerk with email verification, and the programmatic signup route was removed (0).)
- Reliability, RouterPlus +12: Inkling 2 Small 30 (Model reading, for the surface it's called on, Tinker's serverless inference and OpenAI-compatible API. No status page found, per the tinker listing's checks of 1 October and 4 November (0), so no readable incident history (5). The only published limit is the in-flight sample cap of 2,000, per the tinker listing's 1 October check; the OpenAI-compatible page gives no numbers and says higher or more stable throughput needs the waitlist (10). The SDK retries sampling with stable request IDs, per the tinker listing's reading of the SDK repository; the OpenAI-compatible page has no retry guidance (15). No SLA found (0). Serverless inference is 'currently in beta' on the models and pricing page and the OpenAI-compatible API is labelled Beta, read 6 November (0). 0 + 5 + 10 + 15 + 0 + 0 = 30.); RouterPlus 42 (Hosted reading. No status page found. Model pages show each provider's uptime over the last 24 hours and no incident history, and status.routerplus.com failed at our proxy again on 4 November 2026 (0). No readable incident history (5). The limits page, re-read on 4 November 2026, gives 20 requests a minute until the organisation's first purchase, then 300 per console key and 60 for the managed Playground key, with token-per-minute and in-flight limits per organisation and key (15). Rate-limit 429s carry `retry-after` from 1 to 59 seconds and `metadata.retry_at`, the errors page gives a retry or no-retry rule for each error class, and the docs say a retry is a new billed request because there is no idempotency key. That is safe-retry guidance without keys on the billed call, the value this run settled for routers such as ramp-router (12, 15 before). The homepage says "Production-grade SLAs", but no SLA terms were found, and the only terms on the site say a stated response time is not a service level (0). The chat and messages surfaces carry no beta label. The Responses API is a preview for non-OpenAI models and Optimize is paused, neither of which is the main surface (10). 0 + 5 + 15 + 12 + 0 + 10 = 42.)
- Schema & documentation, Inkling 2 Small +11: Inkling 2 Small 70 (Model reading. No OpenAPI file of its own; the OpenAI-compatible chat and completions endpoints and the typed Python SDK are the contract, as the tinker listing reads it (15). llms.txt on the docs host, per the tinker listing's 1 October check (10). The model card states intended use (agentic and tool-use systems, coding assistants, chatbots, RAG), inputs, outputs and limitations, and the launch post its benchmarks (16 of 20). Model IDs, context lengths and the reasoning_effort values (none to xhigh, or 0.0 to 0.99) are documented; the tool-call format and structured output aren't, for this model (8 of 15). A Python example and an HTTP 400 for models without reasoning_effort, with no error page (6 of 15). A dated Tinker changelog and a model deprecations page, per the tinker listing (15). 15 + 10 + 16 + 8 + 6 + 15 = 70.); RouterPlus 59 (Router, scored on the API lines. No OpenAPI or other machine-readable contract for the gateway was found. It follows the OpenAI and Anthropic wire formats, which this checklist doesn't credit to a reseller, the same reading as Antseed (0 of 25). llms.txt, llms-full.txt and a Markdown copy of every page (10). Each route page says what it is for, what isn't available, and which route to use for which model, and the agent integration guide lists what not to build on (18 of 20). Request fields follow the upstream formats, and the wire compatibility page tables which fields pass, translate, drop or fail with a typed 400 (12 of 15). Curl, Python and TypeScript examples on every page, and an error reference with a class, status and remedy for each error (15). Routes are versioned under /v1 and the wire compatibility page says changing it needs a recorded decision, but no changelog or dated release notes were found, re-read on 4 November 2026 (4 of 15).)
- Agent ergonomics, RouterPlus +9: Inkling 2 Small 62 (Model reading (tool use, structured output, caching, context, batch, SDKs). A 256K served context, max_tokens and a priced cache at $0.03 per million; tool use isn't documented for this model (15 of 25). Output-size controls through max_tokens, reasoning_effort and separate_reasoning (15 of 20). One documented error, the 400 for unsupported reasoning_effort (5 of 20). Stable request IDs make SDK sampling retries safe, per the tinker listing (15 of 20). OpenAI's SDKs work against the endpoint, with Tinker's Python SDK besides, and reasoning defaults to 0.9 (12 of 15). 15 + 15 + 5 + 15 + 12 = 62.); RouterPlus 71 (Router, read on the model lines (tool use, structured output, caching, context, batch, SDKs, errors). Tools pass through on both surfaces, and Anthropic server tools such as web search work for Claude models on `/v1/messages`. Behaviour depends on the model (15 of 20). `response_format` works for GPT ids and the open models (re-read on 4 November 2026), and the docs tell callers to get JSON from Claude through a single tool, so structured output still rests on the provider (8 of 15, held). Cached-input and cache-write prices per model, a session id that keeps provider caches warm, and `cache_control` on the Anthropic surface (13 of 15). The catalogue's largest contexts are 1,050,000 tokens on GPT-6.1 Sol and 1,000,000 on Claude Sonnet 5.5, a judgement call since a router has no default model (15). No batch route (0 of 10). No SDK of its own. The OpenAI and Anthropic SDKs work with a changed base URL, and the docs give setups for ten coding tools (5 of 10). A stable `error_type` in every body and header, an origin header, the limit that refused a request, and `x-tm-dropped-params` naming every dropped field (15).)