Skip to content
ModelCap

Ling 3.1 Flash

Official publisher releaseOpen weights

InclusionAI·#99 of 533 in the all-versions archive

Ling 3.1 Flash is a language model from InclusionAI. It ranks #99 of 533 in ModelCap's all-versions archive, with an Index score of 67.7, modeled from the publisher's launch results against measured models. Its score range of 52.5–82.9 spans positions #11–#194. It is listed at $0.045 per million input tokens and $0.135 per million output tokens from one provider. It reads up to 1M tokens of context, and its weights are openly downloadable.

Figures as of 19 Nov 2026, 05:16 UTC · download the public dataset · methodology

ModelCap Index · All-versions archive
67.7#99
Modeled from the publisher's launch results against measured models · range 52.5–82.9
Market Gravity
50.9
Secondary market signal

Superseded by Ling 3.1 flash 1019. It no longer holds a current-board position; its all-versions archive rank is #99.

Input
$0.045
per 1M tokens
Output
$0.135
per 1M tokens
Context
1M
tokens
Providers
1
endpoint

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Novita$0.045$0.1351M—100.0%

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

ProviderInputOutputContextTTFTThroughputFeatures
novita
live
$0.045$0.1351M1124 ms47.0 tok/stools

Reported evaluation leads (7)

Not independent measurement

Structured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. Rows marked as used were laddered against independently measured peers inside the launch-card channel of this model's modeled placement, with the replay-measured optimism haircut applied; the others played no part.

Dataset / taskMetricValueRevisionProvenance
benchflow/skillsbench
skillsbench_v1_1
—68.7
Unpinned
not published
Reported
Not used in launch estimate
cais/hle
hle
—37.44
Unpinned
not published
Reported
Not used in launch estimate
datacurve/deep-swe
deep_swe
—59.7
Unpinned
not published
Reported
Not used in launch estimate
harborframework/terminal-bench
terminalbench_4
—46.03
Unpinned
not published
Reported
Not used in launch estimate
harborframework/terminal-bench-2.1
terminalbench_2_1
—81.18
Unpinned
not published
Reported
Not used in launch estimate
ScaleAI/SWE-bench_Pro
SWE_Bench_Pro
—68.74
Unpinned
not published
Reported
Not used in launch estimate
SWE-bench/SWE-bench_Multilingual
swe_bench_multilingual_%_resolved
—88.5
Unpinned
not published
Reported
Not used in launch estimate

Other versions (5)

ModelCap Index · All-versions archive

Methodology
67.7
Modeled from the publisher's launch results against measured models
All-versions archive
#99 of 533
Score range
52.5–82.9
Rank range
#11–#194
Technical details
Public rank basis
Modeled · peer benchmarks (architecture)
Evidence label
Modeled · peer benchmarks · 5 reported rows against measured corpus ladders (73%); global-corpus-prior over 214 held-out anchors (27%); shrunk 5.9 toward the measured corpus
Index support
21.1% · limited
Identity binding
Exact catalogue product · inclusionai/inclusionai/ling-3.1-flash/fp8 · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata inclusionAI/Ling-3.1-flash@dde57b1c6a365aa0e0a33e15cecce0f2be96f5a3 (not the evaluation revision)
Index observations used
0
Qualified Index evidence point
67.7
How this position was produced · fused launch placement

No general-family board lists this model yet. Its point estimate is the precision-weighted mean of every channel that spoke for it; each channel’s share is the weight it carried. Independent measurements replace this placement as boards list the model.

Fused estimate
67.7 ± 11.9
Independent share
0%
Shrink toward corpus
-5.9
Optimism haircut
None applied
Method
precision-weighted-v1
Channels fused into this model’s launch placement
ChannelEstimateShare
Corpus ladder · not independent
5 reported rows against measured corpus ladders
73.6 ± 13.973%
Publisher corpus prior · not independent
global-corpus-prior over 214 held-out anchors
51.7 ± 22.927%
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
—
Evidence status
No admitted measured evidence
General preference
—
Coding
—
Agents & tools
—
Reasoning
—
Evidence breadth
0%
Evidence coverage
0%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
21.0
Liquidity (providers × uptime)
98.7
Open reach (HF downloads)
70.3
Surface (context / tools / modalities)
85.0
Freshness
83.4
  • · OpenRouter popularity #101
  • · 1 live provider
  • · HF 30d downloads 6621
  • · Catalogue: context 1000000, reasoning, tools
  • · First seen 2026-10-02

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Experimental capability estimate

Estimate policy
66.6
53.2–80.0 uncertainty interval
Excluded from rank
Confidence
80%
Training support
225 models · 132 lineages
Out-of-domain check
in domain
Feature coverage
100%
Lineage-held-out error
8.1 MAE

Experimental estimate. This layer predicts from admitted evidence and safe metadata only. It never enters ModelCap Score or rank.

Deployment readiness

Metadata index
67.7
partial · 76% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
100.0
Deployability
74.0
Evaluation provenance
0.0

Not yet published: the base model it derives from, admitted benchmark results, results across several capability areas, results from more than one source, a confident match to its benchmark entries, pinned evaluation dataset versions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
50.9
OpenRouter weekly popularity
#101 of 345

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

No matched Arena rating

This model is visible because it is available in the live catalogue, but it has no trustworthy community result yet. ModelCap does not infer a quality score from price, features, or market activity.

Market Gravity breakdown

Usage55%
21.0

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
98.7

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
70.3

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
83.4

Time since first public availability, on a six-month half-life.

Specification

Model ID
inclusionai/ling-3.1-flash
Context window
1M tokens
Declared output cap
262K tokens

OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. OpenRouter metadata

Inputs
Text
Outputs
Text
Tokenizer
Other
Cached input tokens
$0.0090 / 1M
First seen on OpenRouter
2 Oct 2026

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Not supported: Structured output
  • Not supported: Response format
  • Not supported: Moderated

Weights & access

Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.

Access
Open weights
Licence
mit
Pinned revision
dde57b1c6a36
Parameters
572.1B
Architecture
BailingMoeV3ForCausalLM
Model type
bailing_hybrid
Hugging Face downloads (30d)
7K
Downloads (all time)
9K
Likes
173
Repository updated
3 Nov 2026, 10:06 UTC

Ling 3.1 Flash: common questions

How does Ling 3.1 Flash rank among AI models?

Ling 3.1 Flash is a superseded version and is not on the current board as of 19 November 2026. Its archive position, where one exists, is shown on the page; the newer version carries the current rank.

How much does Ling 3.1 Flash cost per 1M tokens?

Ling 3.1 Flash is listed at $0.045 per 1M input tokens and $0.135 per 1M output tokens as of 19 November 2026. Prices come from the OpenRouter catalogue and re-observe on every refresh. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply $0.158 total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.

What is the context window of Ling 3.1 Flash?

Ling 3.1 Flash has a published context window of 1M tokens (1,000,000). The snapshot lists a 262,144 token catalogue-declared route output cap. OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. The providers table lists each endpoint's context limit.

Is Ling 3.1 Flash open-weight?

Open weights (mit). Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI. The repository is inclusionAI/Ling-3.1-flash on Hugging Face.

Which API providers serve Ling 3.1 Flash?

One provider serves Ling 3.1 Flash through OpenRouter as of 19 November 2026: Novita. Each provider's price, context limit, quantization and measured uptime are in the providers table above.

When was Ling 3.1 Flash released?

Ling 3.1 Flash first appeared in the catalogue on 2 Oct 2026. It has since been superseded by Ling 3.1 flash 1019. Rank and price movements since then are recorded on the site's changes feed.