Inkling 2 Small vs Simplismart

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.

Simplismart 17

Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). The LiveKit guide calls the LLM API fully OpenAI-compatible, but no page documents tools or tool_choice, and the OpenAPI files allow only system, user and assistant roles (3 of 20). No structured-output or JSON mode documented (0 of 15). No prompt caching documented for shared endpoints (0 of 15). Context lengths are not stated per model; output is capped at 4,096 tokens in the API files (3 of 15). No batch API for shared endpoints (0 of 10). Inference goes through the OpenAI client; the simplismart-sdk Python package and CLI manage repositories and deployments, not inference, and a community Pipecat package exists (5 of 10). Expired keys return a documented 401, and the SDK exposes status_code, message and payload, but no error codes or bodies are listed for the inference API (6 of 15). 3+0+0+3+0+5+6 = 17.

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.

Simplismart 29

Closed service. The terms, last updated 13 January 2023, name Verute Technologies Private Limited and Indian law but define the Service as the website, grant Simplismart a licence to use and redistribute posted Content, bar robots and automatic access, and rule out refunds. No API or platform terms were found (8 of 30). The privacy policy, effective 13 January 2023, is a website policy that says personal data is processed in India. It says nothing about prompts, outputs, logs or training, and no DPA, retention period or subprocessor list was found. A Simplismart article claims GDPR and HIPAA support (3 of 30). No deprecation policy or dated removals (0 of 20). Data goes to India per the privacy policy, and an article says workloads are kept in approved regions by scheduling policy. No subprocessor or hosting-provider list (3 of 20). 8+3+0+3 = 14.

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.

Simplismart 42

Model reading for a closed service. Muse Spark Open was added in beta on 19 October 2026, and the docs sitemap shows pages changed on 7 October (30). No deprecation policy or notice period found (0 of 12). One dated model addition in the 90 days to 28 October and no recorded removals; the pricing page still lists Llama 3.1 405B and DeepSeek-R1, which the API reference doesn't cover, so the live model set is unclear (2 of 8). No public changelog or community channel. Support is support@simplismart.ai and a contact form, not tested (4 of 15). SDK issue replies not read, because github.com gave no readable robots.txt (0 of 10). simplismart-sdk for Python, documented with a CLI, and the OpenAI client for inference. No TypeScript SDK, and the PyPI page answered with a browser challenge, so the version and date are unchecked (6 of 15). CI not checked (0 of 10). 30+0+2+4+0+6+0 = 42.

Inkling 2 Small 57

Platform readings are the tinker listing's. Revocable API keys from the console, with no per-key scopes found (20). Org, team and project permissions with no read-only role (5). The model returns its own completions, no third-party content (10). get_audit_log() for admins (15). security.txt with a reporting address and no stated acknowledgement time (7). For the model reading, Tinker's terms commit not to use Customer Content for training, recorded under transparency. 20 + 5 + 10 + 15 + 7 = 57.

Simplismart 35

Model reading. Named Bearer keys with an expiry chosen at creation, a 401 after expiry and immediate deletion. No scopes or per-key limits found, keys belong to the organisation, and the SDK uses a separate Playground token (20 of 30). No statement on training on API data in the terms, the privacy policy, the AI policy or the docs (0 of 20). No retention or zero-retention statement for prompts and outputs. The privacy policy covers the website only (0 of 15). The Usage page shows request counts and a per-request timeline per model, and an LLM metrics call returns token counts and timings per request id. A Simplismart article claims exportable audit trails, not documented (8 of 15). The homepage shows GDPR, ISO 27001 v2022 and AICPA SOC 2 badges, and a Simplismart article says it holds a SOC 2 Type 2 report, available on request. No trust centre was reachable, security.txt answered 404, and no disclosure policy or bug bounty was found (7 of 20). 20+0+0+8+7 = 35.

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.

Simplismart 51

Model reading. OpenAPI 3.1 files for seven LLMs and 3.0 or 3.1 files for Whisper, Flux, an LLM metrics call and training jobs. They cover a handful of the 150+ models, omit tools and response_format, show a streaming delta as the non-streaming response, and several name hosts on s9t.link instead of api.simplismart.live. The Llama 4 Maverick file gives llama3_1 as its only model id, and /api-reference/openapi.json is the Flux spec (12 of 25). llms.txt and a Markdown copy of each docs page (10). The docs say when to use shared or dedicated endpoints; model pages carry one-line descriptions (10 of 20). Roles are enums, temperature is bounded 0 to 2, max_tokens 1 to 4096, and messages and model are required (10 of 15). curl and OpenAI-client Python examples. Errors are bare 400, 401 and 500 descriptions, plus an SDK example of a 404 payload (7 of 15). No changelog. Every spec reads version 1.0.0 (2 of 15). 12+10+10+10+7+2 = 51.

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.

Simplismart 15

Hosted reading. No status page found. The docs and site link none, a search found none, and status.simplismart.ai could not be reached from our network (0). No readable incident history (5). No request or token rate limits are published for shared endpoints. The docs give GPU quotas for training, compilation and private deployments only, 1 H100 and 1 L40 on the Quotas page and 8 of each on the Organisation page (0). No 429 response, Retry-After header or retry guidance found; the OpenAPI files list only 400, 401 and 500 (0). No SLA document found. The homepage claims 99.99% uptime and a Simplismart post calls its autoscaling SLA-backed, but no terms state a commitment, and the terms provide the service as is (0). Shared endpoints carry no beta label, while Muse Spark Open is in beta (10). 0+5+0+0+0+10 = 15.