I
INCLUSIONAI / inclusionAI/Qwen3.8-Flash-Next-singprobe

SingProbe Qwen3.8-Flash-Next

Trained inclusionAI probe that reuses its base model's hidden states to classify intent, response unsafety and hallucination risk during generation. Its own checkpoint was published on October 27, 2026. It is not a standalone assistant or a new base-model version. Its ten outputs cover eight intent categories and two risk signals.

01 / SUMMARY

The essential

ORIENTATIONSafety probe during generation

Primary use stated or inferred cautiously from official documentation.

CONTEXTDepends on the base model and runtime

Maximum input capacity when published by the source.

EXITTen scores per token

Documented maximum generation limit.

ACCESSHugging Face

Verified availability channels.

MODEL TYPEText classification

Primary functional family and verified specialties.

LICENSEQwen Community License 1.0

Declared terms for API access, model weights, or self-hosting.

02 / TECHNICAL SHEET

Limits and integration

API IDinclusionAI/Qwen3.8-Flash-Next-singprobe
Model typeText classification
Access modelOpen weights
LicenseQwen Community License 1.0
DeploymentBase model and adapted runtime
Release27 OCT 2026
Knowledge cutoffNot published
EntranceHidden states
ExitPer-token scores
Context windowDepends on the base model and runtime
maximum outputTen scores per token
ReasoningNot published
Published tools
Structured OutingsNot published
Batch processingNot published
Prompt cacheNot published
Fine-tuningNot published
Verified platformsHugging Face · SGLang · vLLM
BEST SUITED FOR

Monitoring per-token risks in systems already serving the compatible base model. The probe weights are small relative to the model being observed, but do not replace it. The client receives label_0 through label_9 using the integrations listed in the card; it must choose thresholds and how to act on these signals.

WORTH MONITORING

Requires the exact base-model/probe pair and a modified runtime. It cannot accept a conversation on its own and does not guarantee the absence of hallucinations. Overhead below 0.5% is reported by the provider, not promised for all hardware. Do not confuse its scores with a general language benchmark.

03 / CAPABILITIES

What it can do

01

Base model

Qwen/Qwen3.8-Flash-Next

02

Probe parameters

5,18 M

03

False positives on benign responses

0,03 %

Input modalities
Hidden states
04 / PRICES

Documented cost

ConceptWorthUnit/condition
Standard inputNo published official API rateStandard API rate
Cached inputNot publishedReading reused prefixes
Cache write or storageNot publishedThe condition varies by provider
Standard outputSelf-hosted infrastructure costMay include reasoning tokens
Batch inputNot publishedAsynchronous processing
Batch outputNot publishedAsynchronous processing

No API price is published for the probe. Costs include the base model, memory, runtime and monitoring. The card refers to the base model's license; the Qwen variant retains Qwen Community License 1.0, with specific conditions for commercial services. The GLM variant links to MIT. Public downloads do not remove these obligations.

i Prices change and may depend on level, region or context length. Check the source before making a decision.

05 / EVALUATIONS

How to read the results

“

The card reports intent F1 across six benchmarks, safety F1 across eight, streaming safety R-AUC and T-AUC across three, and hallucination AUC across six. These average different suites; they should not be added together or compared with coding accuracy. False positives are averaged across five datasets. Not reproduced by Inferama.

Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.

06 / VERSIONS

Chronology

SingProbe Qwen3.8-Flash-Next

Version added to Inferama's verified catalog.

07 / SOURCES

Traceability