inclusionAI: Ling 3.0 Flash Sante (free) by Kilo Gateway

$10 off the fastest Kimi K3 and GLM 5.3$10 off the fastest Kimi K3 and GLM 5.3

Model details

inclusionAI: Ling 3.0 Flash Sante (free)

inclusionAI's Ling 3.0 Flash Sante is positioned within the Ling model family and appears as a zero-cost text offering on multi-model gateways. It sits alongside a sibling variant called Ling 3.0 Flash Fin in the free tier of aggregator listings, suggesting inclusionAI intends the Ling 3.0 Flash line as an accessible, lightweight option rather than a frontier-scale system. The "Sante" naming and free-tier placement indicate a focus on broad availability for experimentation and lightweight assistant workloads.

On Kilo Gateway, Ling 3.0 Flash Sante benefits from a routing layer that exposes more than 500 third-party models at cost with no markup, supporting both hosted and bring-your-own-key workflows. Kilo itself was founded in 2025 by a team including former GitLab co-founder Sid Sijbrandij and backed with $8 million in seed funding, framing the gateway as part of a broader push toward open, transparent AI tooling. For users, this translates into a practical fit: a free inclusionAI text model reachable through an open-source agent platform oriented around coding and general productivity workflows.

Kilo Gatewayinclusionai/ling-3.0-flash-sante:freeling

Open provider page Provider docs

Quick Info

Provider: Kilo Gateway
Model key: inclusionai/ling-3.0-flash-sante:free
Release date: Sep 4, 2026
Last updated: Sep 4, 2026
Input modalities
Output modalities
Capabilities

Cost

A provider subscription or plan supersedes token-based pricing for this model.

Limits

Output tokens: 32,768 tokens
Context window: 262,144 tokens

Latest news about inclusionAI: Ling 3.0 Flash Sante (free)

Kilo Gateway

CoverageRelease Notes

Vercel's AI Gateway changelog announces that InclusionAI's Ling 3.0 Flash Sante is now available on AI Gateway, free to use through October 4, 2026. The model is described as a health and medicine-focused version of Ling 3.0 Flash, implemented as a Mixture-of-Experts architecture with 124B total parameters, about 5.1B Two model IDs are documented: the standard `inclusionai/ling-3.0-flash-sante` continues serving and begins billing after October 4, while the free variant `inclusionai/ling-3.0-flash-sante-free` stops serving when the offer ends; free requests still appear in the spend dashboard with traces but carry no cost. Developer

Kilo Gateway

CoverageBenchmark

According to LM Market Cap's model directory page, InclusionAI's Ling 3.0 Flash Sante (free) was released on September 4, 2026, as a health and medicine-focused Mixture-of-Experts variant of Ling 3.0 Flash with 5.1B active parameters out of 124B total, a 262.1K token context window, and a 32.8K max output. The director The page also notes that Ling 3.0 Flash Sante fits into InclusionAI's recent shipping cadence, following Ling 3.0 Flash Fin and Ling 3.0 Flash Fin (free) on August 27, 2026, and the original Ling 3.0 Flash on July 23, 2026, indicating an active release cadence from the provider. While the directory flags the model as s