Skip to content

Inclusionai · Chat

Ling 3.0 Flash

Inclusionai 🇨🇳ChatOpen weights. One of its sources says the weights are publicly available.

Newer version: Ling 3.2 Flash. Our catalogue has no release date for Ling 3.2 Flash. We compared the version names in our catalogue.

From Llmgateway's listing:
InclusionAI's native hybrid-reasoning MoE model (124B total, 5.1B active) with strong agentic and coding performance.
llminfo IQ
125.6
Market median price
$0.09 blended / 1M
Max context
262K
Listings
24

Evidence and sources

inclusionAI is Ant Group’s AGI initiative (per its Hugging Face organisation card, huggingface.co/inclusionAI); the country cites Ant Group’s own site (Hangzhou).

🤗 inclusionAI/Ling-3.0-flashllminfo IQ 125.6, ranked among chat models. From 52 benchmarks. Plenty of data behind it.How llminfo IQ is computedGood value (64.2). Cheaper per task than its benchmark results predict. From 2 benchmarks with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 2 Aug 2026Maker HQ: CN (source)
All rankings: #75 on OpenRouter today #85 on OpenRouter this week #90 on OpenRouter this month #315 on NanoGPT recentlySources: DeepInfra data, Models.dev data, AI/ML API data, LLMGateway data, Hugging FacePrimary data from DeepInfra from Models.dev: weights availability from AI/ML API: primary mode from LLMGateway: description from Hugging Face: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 3 of the 9 peers that say either way have open weights.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 7 maker's prices; 3 market median prices.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured outputPrompt caching

Listings

 Nous Portalinclusionai/ling-3.0-flashSource: Nous Portal Inference Gateway data262K$0.021cache read $0.0042$0.063——
 OpenRouterInference by Novita AIinclusionai/ling-3.0-flashSource: OpenRouter data docs262K$0.021cache read $0.0042$0.0631131,168.5ms
 Vercelinclusionai/ling-3.0-flashSources: Models.dev data, Vercel AI Gateway data256K$0.021cache read $0.0042$0.063——
 Aihubmixling-3.0-flashSource: AIHubMix data docs262K$0.06cache read $0.012$0.18——
 Fastrouterinclusionai/ling-3.0-flashSource: FastRouter data131K$0.06cache read $0.012$0.18——
 FlowdotinclusionAI/Ling-3.0-flashSource: FlowDot data131K$0.06$0.18——
 Hugging FaceInference by DeepInfrainclusionAI/Ling-3.0-flashSource: Hugging Face Inference Providers data131K$0.06$0.18——
 Kiloinclusionai/ling-3.0-flashSources: Kilo AI Gateway data, Models.dev data262K$0.06cache read $0.012$0.18——
 LlmgatewayInference by DeepInfrainclusionAI/Ling-3.0-flashSource: LLMGateway dataNot published by the provider$0.06cache read $0.012$0.18——
 Zenmuxinclusionai/ling-3.0-flashSource: ZenMux data262K$0.06cache read $0.012$0.18——
Show all 22 listings

Showing 10 of 22: the cheapest per 1M input tokens from each provider.

Also sold by Bailing, DeepInfra, Llmgateway Providers, NanoGPT, Novita AI.

2 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Multilingual

Benchmark Nusantara17 related benchmarks · 17 results
Show 11 more resultsHide 11 results

Long context

Agentic

BFCL-V4Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
DracoSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GDPval-AASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MCP AtlasSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Source: OpenRouter benchmark exports · Oct 2026
23 Jul 2026 version · 90-day results
Across 2 providers lowest 73.8% median 73.9% highest 74%OpenRouter's automatic routing 68.7%
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
  • Novita
  • DeepInfra
  • OpenRouter's automatic routing

Coding

Math

Science

GPQA Diamond3 results
Source: OpenRouter benchmark exports · Oct 2026
23 Jul 2026 version · 90-day results
Across 2 providers lowest 76.1% median 76.6% highest 77%OpenRouter's automatic routing 74.9%
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
  • Novita
  • DeepInfra
  • OpenRouter's automatic routing

Human preference

Instruction following

IFBenchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Multi-IFSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Reasoning

Other

Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark · Data by LLM Stats · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · Benchmark Nusantara, ibahasa (M. Khoirul Huda), doi:10.5281/zenodo.21970463. Test results CC BY 4.0, attribution to ibahasa; aggregate results CSV only. (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted. · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence)

Also known as: deepinfra/inclusionai/ling-3.0-flash, deepinfra/ling-3.0-flash, inclusionai/ling-3.0-flash, inclusionai/ling-3.0-flash:thinking, ling-3.0-flash-free, novita/inclusionai/ling-3.0-flash, novita/inclusionai/ling-3.0-flash-fast, novita/ling-3.0-flash

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works