Skip to content
Inclusionai

Ling 3.0 Flash

Ling 3.0 Flash is a Mixture-of-Experts model from Inclusionai with 124B total parameters and about 5.1B active per token, built for token-efficient agentic inference. It supports a context window of 256K tokens and a max output of 256K tokens per request.

ReasoningTool UseImplicit Caching
Use with AI GatewayView docs
import { streamText } from 'ai'


const result = streamText({
  model: 'inclusionai/ling-3.0-flash-free',
  prompt: 'Why is the sky blue?'
})
Read docs
OverviewAPIAboutProvidersUptimeStatusSimilarFAQ

Copy link to headingFrequently Asked Questions

  • What architecture does Ling 3.0 Flash use?

    Ling 3.0 Flash uses a Mixture-of-Experts (MoE) design with 124B total parameters and about 5.1B active per token. Sparse activation means each request pays inference cost on the active subset rather than the full parameter count.

  • What is the context window for Ling 3.0 Flash?

    Ling 3.0 Flash supports a context window of 256K tokens and a max output of 256K tokens per request. That covers long agent transcripts, large document sets, and extended multi-turn sessions.

  • Does Ling 3.0 Flash support a thinking mode?

    Yes. Ling 3.0 Flash runs in thinking and non-thinking modes. Thinking mode adds reasoning tokens before the final answer, so budget output tokens for the requests where you enable it.

  • Why does the model identifier end in -free?

    The suffix marks a free listing on AI Gateway. Ling 3.0 Flash joined the catalog at no cost for three weeks after launch, through August 3, 2026. Check the pricing panel on this page for current rates.

  • What workloads did Inclusionai design Ling 3.0 Flash for?

    High-frequency agentic workflows, coding agents, document work, and long-context multi-turn interactions. Inclusionai prioritized token efficiency so agent runs complete more useful work inside tight token, latency, and serving-cost budgets.

  • Does Ling 3.0 Flash support tool calling?

    Yes. Ling 3.0 Flash is tagged for tool use in the AI Gateway catalog, so you can define tools through the AI SDK, the Chat Completions API, or another supported API format and let Ling 3.0 Flash call them across multi-step runs.

  • How does Ling 3.0 Flash compare to Ling 3.0 Tiny?

    Ling 3.0 Tiny is the smaller sibling, with 7.9B total parameters, about 1.3B active per token, a 256K context window, and up to 32K output tokens. Ling 3.0 Flash carries 124B total parameters and about 5.1B active, so it has more capacity for harder multi-step work.

  • How do I call Ling 3.0 Flash through AI Gateway?

    Use the model identifier inclusionai/ling-3.0-flash-free with the AI SDK, the Chat Completions API, the Responses API, the Messages API, or another supported API format. You authenticate with an AI Gateway API key, and no Inclusionai account is needed.

  • Does AI Gateway support Zero Data Retention for Ling 3.0 Flash?

    Zero Data Retention is not currently available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

  • Can Ling 3.0 Flash handle image or video inputs?

    No. Ling 3.0 Flash takes text in and returns text out. For visual inputs, pick a multimodal model from the AI Gateway catalog and keep Ling 3.0 Flash on the text path.