Ling 3.1 Flash from InclusionAI arrives on Vercel's AI Gateway, free until October 13
Vercel has added Ling 3.1 Flash from InclusionAI to its AI Gateway. The model is free to use through October 13, 2026, according to Vercel.
- Vercel added InclusionAI's Ling 3.1 Flash to AI Gateway, free through October 13, 2026.
- The hybrid reasoning model has 560B total parameters, 25B active per token, and a 262K-token context window on AI Gateway.
- It targets coding, multi-step analysis, and tool-using agents, including long documents and extended task histories.
- The standard ID begins billing after the promotion, while the -free ID stops serving.
What Ling 3.1 Flash offers
Ling 3.1 Flash is a hybrid reasoning language model with 560B total parameters and 25B active per token. On AI Gateway it has a 262K-token context window.
According to the announcement, the model is designed for coding, multi-step analysis, and agents that use tools. Vercel specifically names workflows involving long documents, code, and extended task histories as target uses.
Two model IDs, two behaviors at the end of the promotion
Developers can call the model through AI Gateway with one of two names: inclusionai/ling-3.1-flash or inclusionai/ling-3.1-flash-free. The difference matters once the free period ends.
- The standard model ID is free during the promotion and begins billing when it ends.
- The -free model ID stops serving instead of billing when the promotion ends.
The second option gives teams a way to test the model without any risk of unexpected charges. Vercel's example uses the AI SDK's streamText function with the -free ID and a prompt asking the model to triage open issues in a repository and group them by theme.
Using it in coding agents and the playground
To use Ling 3.1 Flash in a coding agent, Vercel points users to the AI Gateway coding agents guide and says to select inclusionai/ling-3.1-flash as the model. The model can also be tried in the AI Gateway model playground, and it is listed in the model catalog.
AI Gateway provides one API for calling models, tracking usage and cost, and configuring routing, retries, and failover. Users can authenticate with an AI Gateway API key or bring their own provider key.
What it means for developers
For developers already routing requests through AI Gateway, the addition makes a large model aimed at agentic and long-context coding work available behind the same API they use for other models. The free promotion lowered the cost of evaluating it, and the choice between the two model IDs let teams decide whether usage should convert to paid billing or simply stop when the offer ended. The source does not provide pricing for the standard model or benchmark results.
Vercel: Ling 3.1 Flash is now available on AI Gateway
