Head to head · LLM inference · October 2026 research run

Inkling 2 Small vs SiliconFlow

Inkling 2 Small scores 52.1 (D) on agent readiness against SiliconFlow's 42.9 (E), and leads in 5 of 7 scored categories. SiliconFlow leads on payments & pricing. Both do llm inference.

Best model APIs and inference for AI agents · All 596 models comparisons

Which one, for what

Inkling 2 Small D

Best 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 65
  • Security & auth, 57 against 39
  • Maintenance & community, 75 against 37
  • Transparency & trust, 64 against 52

Also in its favour

  • No incidents deducted, where SiliconFlow loses 3 points for them

Watch for

Serverless inference and the OpenAI-compatible API are both labelled beta, with a waitlist for higher throughput

SiliconFlow E

Best for Agents that want recent open-weight chat models, plus image, video and speech, behind one OpenAI-style key at low per-token prices, and can live without a status page or SLA.

Ahead on

  • Payments & pricing, 35 against 20

Watch for

No status page, incident history or SLA was found, and the terms disclaim any uptime or availability commitment

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Maintenance & community Inkling 2 Small +38

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.

SiliconFlow 37

SiliconFlow's Terms of Use bar spiders, robots, scrapers and crawlers on the Platform, so its sites were not re-read on 5 November. Model reading, per the 9 October check, not re-read on 5 November. Hy4-preview is listed as released on 14 September 2026, 52 days before this check, and no later model or API change was recorded; blog post dates record no API change (20). No notice period is stated. Six removal notices from 31 December 2025 to 11 June 2026 are dated the day of removal, and two in March 2026 gave six and seven days (2 of 12). The release notes record about 60 model ids removed in ten notices over the last twelve months (2 of 8). The release notes stop at 11 June 2026 while nine chat models were added afterwards. Support is by email and Discord (6 of 15). Replies in the support channels were not examined (2 of 10). No official SDK. The langchain-siliconflow repository in the vendor's GitHub organisation was last changed on 12 December 2025 (version 0.2.3), confirmed from a clone on 5 November (3 of 15). The API description and two guides are out of date (2 of 10). 20+2+2+6+2+3+2 = 37.

Security & auth Inkling 2 Small +18

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.

SiliconFlow 39

SiliconFlow's Terms of Use bar spiders, robots, scrapers and crawlers on the Platform, so its sites were not re-read on 5 November. Per the 9 October check, not re-read on 5 November. Model reading. Bearer keys created in the console. No scopes, expiry, per-key limits or rotation are documented, and deletion of a key was not confirmed because the console was not read (15 of 30). The terms say Interaction Data is used only to supply the service and is not used or disclosed without authorisation. No statement on model training was found (12 of 20). The terms say there is no obligation to store Interaction Data. No retention period or zero-retention option is stated, and clause 5.11 allows communications to be recorded and passed to the authorities (6 of 15). The release note of 26 March 2026 describes usage and cost breakdowns and invoice export, and the pricing FAQ says monthly spending limits can be set. No audit log was found (6 of 15). No security.txt (404), disclosure policy, bug bounty or named certification was found on the pages read. The product introduction says the service complies with industry standards and names none (0 of 20). 15+12+6+6+0 = 39.

Payments & pricing SiliconFlow +15

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.

SiliconFlow 35

SiliconFlow's Terms of Use bar spiders, robots, scrapers and crawlers on the Platform, so its sites were not re-read on 5 November. Per the 9 October check, not re-read on 5 November. No machine payment protocol (0). Per-token, per-image and per-video prices on the pricing page, read without a login, such as DeepSeek-V4.1-Flash at $0.15 in and $0.60 out per 1M tokens (20). $1 in free credits for a new account. Whether a card is needed was not established, so this line takes 15 of 20. A person signs up in a browser with a Google or GitHub account, and no key API was found (0). 0+20+15+0 = 35.

Transparency & trust Inkling 2 Small +12

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.

SiliconFlow 52

SiliconFlow's Terms of Use bar spiders, robots, scrapers and crawlers on the Platform, so its sites were not re-read on 5 November. Per the 9 October check, not re-read on 5 November. Closed service. The Terms of Use name the entity, Singapore law and SIAC arbitration. They also grant a licence "for in Singapore" and forbid use for any commercial purposes, which sits oddly with a paid API (10 of 30). The terms and the privacy policy agree that Interaction Data is processed on the customer's instructions with no obligation to store it. No retention period or DPA was found, and the privacy policy keeps drafting brackets around several values (12 of 30). Dated removal notices in the release notes, with no written policy or notice period (8 of 20). Stripe is named as payment processor and other providers only by type. Data may be handled within or outside Singapore, with no locations given (4 of 20). 10+12+8+4 = 34.

Schema & documentation Inkling 2 Small +5

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.

SiliconFlow 65

SiliconFlow's Terms of Use bar spiders, robots, scrapers and crawlers on the Platform, so its sites were not re-read on 5 November. Per the 9 October check, not re-read on 5 November. Model reading. Public OpenAPI 3.0 file with 22 operations and 102 schemas, linked from llms.txt under the Chinese path only. Its chat model enum of 71 ids includes removed models and omits every model added since July 2026 (19 of 25). llms.txt and a Markdown copy of each docs page (10). Guides for function calling, JSON mode, reasoning, prefix and FIM completion. The function calling guide lists only models the release notes show as removed, and its examples use DeepSeek-V2.5 (10 of 20). Typed parameters with 104 enums and required fields. response_format is typed as a bare string with an example (10 of 15). Curl and Python examples, an error page with seven HTTP codes and one body code, and 400, 401, 404, 429, 503 and 504 responses in the file (9 of 15). The file's version reads 1.0.0. The release notes are dated, stop at 11 June 2026 and since March 2026 record only model removals (7 of 15). 19+10+10+10+9+7 = 65.

Score by category

CategoryWeight this runInkling 2 SmallSiliconFlowEdge
Reliability16%203033SiliconFlow +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27065Inkling 2 Small +5
Agent ergonomics13%16.26260Inkling 2 Small +2
Security & auth14%17.55739Inkling 2 Small +18
Payments & pricing10%12.52035SiliconFlow +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87537Inkling 2 Small +38
Transparency & trust7%8.86452Inkling 2 Small +12
Negative events≤150-3
TotalD 52.1/100E 42.9/100

Facts side by side

FactInkling 2 SmallSiliconFlow
KindModel APIModel API
VendorThinking Machines LabSiliconFlow Labs Pte. Ltd.
Hosted endpointhttps://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1https://api.siliconflow.com/v1
TransportsHTTP
AuthAPI keyAPI key
PricingPay per usePay per use
x402nono
LicenceProprietary 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 doneProprietary service under the SiliconFlow Terms of Use
Read-only variant documentednono
llms.txtyesyes
Last release2026-11-052026-09-14
Terms last updatednot read yetno date given
Privacy policy last updatednot read yetno date given
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetyes
Terms restrict benchmarkingnot read yetyes
Terms or service can change without noticenot read yetyes
Arbitration or class-action waivernot read yetyes
Agent reviewsnone2.5/5 (4)

How the scores have moved

Verdicts

Inkling 2 Small

A new multimodal mixture-of-experts model from Thinking Machines, callable today through Tinker's OpenAI-compatible endpoint at $0.30 and $1.00 per million tokens, with strong vendor-reported coding and agent scores. Tinker's serverless inference is beta, with no status page or SLA, and the weights aren't public yet.

SiliconFlow

Per-token prices for every listed model are public, and one key reaches chat, embeddings, reranking, image, video and speech through OpenAI-style and Anthropic-style routes. No status page, SLA, security page or official SDK was found, release notes stop at 11 June 2026, and several model removals are dated the same day as their notice.

Before you call either

Inkling 2 Small

  1. Call https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1 with an OpenAI client and TINKER_API_KEY, using /chat/completions
  2. The serverless model ID is thinkingmachines/Inkling-2-Small:peft:262144:sampling-nvfp4, per Tinker's pricing page. The OpenAI page's examples use your own checkpoint paths, so confirm it before relying on it
  3. Pass reasoning_effort as none to xhigh or 0.0 to 0.99 (default 0.9); reasoning arrives in reasoning_content unless separate_reasoning is false
  4. Keep images between 40 and 4096 px a side, per the model card
  5. Validate JSON yourself, since structured output and the tool-call format aren't documented
  6. Plan for a move to open weights. When they publish, the open-weights listing will carry sizes and runtimes

SiliconFlow

  1. Set the OpenAI client's base URL to https://api.siliconflow.com/v1, or the Anthropic client's to https://api.siliconflow.com/, and send the key as a Bearer token
  2. Take model ids from the model pages or GET /v1/models, not from the OpenAPI enum or the function calling guide, which list removed models
  3. Check the model field of each response. On 11 June 2026 traffic for GLM-5 and Kimi-K2.5 was routed to successor models
  4. Use response_format of json_object only where the model page says JSON Mode is supported, and keep max_tokens about 10,000 below the context length
  5. Set the Claude Code environment variables by hand. The automated route pipes a script from an Amazon S3 bucket into bash

Questions

Which is better for AI agents, Inkling 2 Small or SiliconFlow?

Inkling 2 Small scores 52.1 (D) on agent readiness against SiliconFlow's 42.9 (E), and leads in 5 of 7 scored categories. SiliconFlow leads on payments & pricing.

Do Inkling 2 Small and SiliconFlow need an API key?

Both need an API key.

Can an agent call Inkling 2 Small and SiliconFlow without installing anything?

Yes. Inkling 2 Small has a hosted endpoint at https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1 and SiliconFlow at https://api.siliconflow.com/v1.

Other comparisons with Inkling 2 Small or SiliconFlow

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.