OpenRouter Lists InclusionAI's Ling 3.0 Flash Fin as a Free Route

OpenRouter now lists InclusionAI's Ling 3.0 Flash Fin under the exact route inclusionai/ling-3.0-flash-fin:free. The page shows zero pricing for prompt and completion tokens, while also warning that free endpoints are rate limited.

The route page labels the model as released on 27 August 2026. That is an OpenRouter catalogue date. We have not treated it as proof of a separate InclusionAI maker announcement, general-availability event, API launch or weights publication.

OpenRouter describes Ling 3.0 Flash Fin as a 124-billion-parameter mixture-of-experts model with about 5.1 billion active parameters per token. It accepts text and returns text, with a 262,144-token context window and a maximum output of 32,768 tokens.

The route metadata lists reasoning as supported and enabled by default, although it is not mandatory. Tools and function calling are listed as supported. Structured outputs, vision and other input types are not confirmed in the AIMI record, so they should not be assumed from the broader Ling family.

OpenRouter's provider metadata carries a created time of 15:58:10 UTC, or 17:58:10 SAST. AIMI first saw the route in OpenRouter's models endpoint at 16:16:31 UTC, or 18:16:31 SAST. The endpoint observation came 18 minutes and 21 seconds after the provider metadata time.

Earlier in the same SAST day, the verified DeepSeek V4 Pro GA event was recorded at 00:59:11. The Ling route observation followed 17 hours, 17 minutes and 20 seconds later. These are two different model events, and the timestamps do not establish that InclusionAI was responding to DeepSeek or that the providers coordinated their listings.

A route listing is useful availability evidence, but it is not a substitute for a maker release note. AIMI has no verified official InclusionAI announcement, API release timestamp or weights URL for Ling 3.0 Flash Fin in this batch. The model should therefore be described as available through OpenRouter, not as a separately verified new maker release.

The zero-price offer can change, and free endpoints are usually subject to traffic limits. The route has no recorded AIMI handshake yet, so the catalogue confirms the listing and metadata but not a successful generation test from this environment.

The route is a practical test surface for finance-oriented prompts, long documents and tool-enabled agent workflows. A 262K context window gives it room for large inputs, but context size alone does not tell you whether the model will produce reliable decisions or tool calls.

AZ Labs does not sell an InclusionAI subscription. The relevant product is the AZ Labs AI Gateway, which gives applications one integration point for model routing and provider changes. Test the exact route, prompts, tools, rate limits and review rules before using it for financial work or other high-impact decisions.