Aion 3.5 Mini: Specifications & Sources

Specification	Value and source
API model ID	aion-labs/aion-3.5-miniSource
System type	Multi-model system built on the GLM family; several specialist models work together on each responseSource
Input modalities	TextSource
Output modalities	TextSource
Context window	262,144 tokensSource
Maximum output	32,768 tokensSource

Specification

Value and source

API model ID

aion-labs/aion-3.5-miniSource

System type

Multi-model system built on the GLM family; several specialist models work together on each responseSource

Input modalities

TextSource

Output modalities

TextSource

Context window

262,144 tokensSource

Maximum output

32,768 tokensSource

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

EvalMap: English long role-play / Turns breaking no rule (Show measurement, test conditions, and source)

Source value: 75
Score: 75
Metric: Share of turns with no system-prompt rule broken
Unit: %
Category: EvalMap role-play system evaluation
Direction: Higher is better
Sample: 216
Source type: independent-evaluator
Evaluator: EvalMap, Small tests
Status: active
Retrieved at: 2026-10-07
Methodology: Independent evaluation. Route=OpenRouter; model ID=openrouter/aion-labs/aion-3.5-mini; language=English; run date=2026-09-25; six matched generated role-play scenarios, 36 turns each; up to 8,000 output tokens per turn; reasoning effort not stated.
Context: EvalMap measured the Aion multi-model role-play system through OpenRouter, not an isolated GLM checkpoint. Its six generated scenarios per language are a small sample, and the prompts and responses are not published. The evaluator says index differences of 0.02-0.03 are noise. The values describe this system run, not a general capability score.

Source EvalMap, Small tests

EvalMap: Russian long role-play / Turns breaking no rule (Show measurement, test conditions, and source)

Source value: 96
Score: 96
Metric: Share of turns with no system-prompt rule broken
Unit: %
Category: EvalMap role-play system evaluation
Direction: Higher is better
Sample: 216
Source type: independent-evaluator
Evaluator: EvalMap, Small tests
Status: active
Retrieved at: 2026-10-07
Methodology: Independent evaluation. Route=OpenRouter; model ID=openrouter/aion-labs/aion-3.5-mini; language=Russian; run date=2026-09-25; six matched generated role-play scenarios, 36 turns each; up to 8,000 output tokens per turn; reasoning effort not stated.
Context: EvalMap measured the Aion multi-model role-play system through OpenRouter, not an isolated GLM checkpoint. Its six generated scenarios per language are a small sample, and the prompts and responses are not published. The evaluator says index differences of 0.02-0.03 are noise. The values describe this system run, not a general capability score.

Source EvalMap, Small tests

NC Bench: Bad Writing Habits / Detailed Writing Rules / Fantasy: entering an ancient ruin (Show measurement, test conditions, and source)

Source value: 92
Score: 92
Metric: NC Bench reported score
Unit: %
Category: NC Bench / Bad Writing Habits / Detailed Writing Rules
Direction: Higher is better
Sample: 5
Source type: independent-evaluator
Evaluator: NC Bench (Novelcrafter)
Status: active
Retrieved at: 2026-10-07
Methodology: Independent evaluation. Model ID=aion-labs/aion-3.5-mini; displayed configuration=Aion 3.5 Mini (Reasoning, High); route=OpenRouter; evaluation date not stated. Scenario totals use the evaluator's displayed row totals; the page shows 5 or 10 numbered samples for individual tasks.
Context: NC Bench is Novelcrafter's own creative-writing, rule-following and tool-use test suite. The scenarios are unpublished and are not standardized general-purpose LLM benchmarks. The page displays task totals but does not state the last evaluation date or how category aggregates are weighted.

Source NC Bench (Novelcrafter)

NC Bench: Bad Writing Habits / Detailed Writing Rules / Horror: alone in an eerie place at night (Show measurement, test conditions, and source)

Source value: 94
Score: 94
Metric: NC Bench reported score
Unit: %
Category: NC Bench / Bad Writing Habits / Detailed Writing Rules
Direction: Higher is better
Sample: 5
Source type: independent-evaluator
Evaluator: NC Bench (Novelcrafter)
Status: active
Retrieved at: 2026-10-07
Methodology: Independent evaluation. Model ID=aion-labs/aion-3.5-mini; displayed configuration=Aion 3.5 Mini (Reasoning, High); route=OpenRouter; evaluation date not stated. Scenario totals use the evaluator's displayed row totals; the page shows 5 or 10 numbered samples for individual tasks.
Context: NC Bench is Novelcrafter's own creative-writing, rule-following and tool-use test suite. The scenarios are unpublished and are not standardized general-purpose LLM benchmarks. The page displays task totals but does not state the last evaluation date or how category aggregates are weighted.

Source NC Bench (Novelcrafter)

NC Bench: Bad Writing Habits / Detailed Writing Rules / Literary fiction: old friends reunite (Show measurement, test conditions, and source)

Source value: 90
Score: 90
Metric: NC Bench reported score
Unit: %
Category: NC Bench / Bad Writing Habits / Detailed Writing Rules
Direction: Higher is better
Sample: 5
Source type: independent-evaluator
Evaluator: NC Bench (Novelcrafter)
Status: active
Retrieved at: 2026-10-07
Methodology: Independent evaluation. Model ID=aion-labs/aion-3.5-mini; displayed configuration=Aion 3.5 Mini (Reasoning, High); route=OpenRouter; evaluation date not stated. Scenario totals use the evaluator's displayed row totals; the page shows 5 or 10 numbered samples for individual tasks.
Context: NC Bench is Novelcrafter's own creative-writing, rule-following and tool-use test suite. The scenarios are unpublished and are not standardized general-purpose LLM benchmarks. The page displays task totals but does not state the last evaluation date or how category aggregates are weighted.

Source NC Bench (Novelcrafter)

NC Bench: Bad Writing Habits / Detailed Writing Rules / Mystery: examining a crime scene (Show measurement, test conditions, and source)

Source value: 92
Score: 92
Metric: NC Bench reported score
Unit: %
Category: NC Bench / Bad Writing Habits / Detailed Writing Rules
Direction: Higher is better
Sample: 5
Source type: independent-evaluator
Evaluator: NC Bench (Novelcrafter)
Status: active
Retrieved at: 2026-10-07
Methodology: Independent evaluation. Model ID=aion-labs/aion-3.5-mini; displayed configuration=Aion 3.5 Mini (Reasoning, High); route=OpenRouter; evaluation date not stated. Scenario totals use the evaluator's displayed row totals; the page shows 5 or 10 numbered samples for individual tasks.
Context: NC Bench is Novelcrafter's own creative-writing, rule-following and tool-use test suite. The scenarios are unpublished and are not standardized general-purpose LLM benchmarks. The page displays task totals but does not state the last evaluation date or how category aggregates are weighted.

Source NC Bench (Novelcrafter)

NC Bench: Bad Writing Habits / Detailed Writing Rules / Romance: separated couple reunites (Show measurement, test conditions, and source)

Source value: 87
Score: 87
Metric: NC Bench reported score
Unit: %
Category: NC Bench / Bad Writing Habits / Detailed Writing Rules
Direction: Higher is better
Sample: 5
Source type: independent-evaluator
Evaluator: NC Bench (Novelcrafter)
Status: active
Retrieved at: 2026-10-07
Methodology: Independent evaluation. Model ID=aion-labs/aion-3.5-mini; displayed configuration=Aion 3.5 Mini (Reasoning, High); route=OpenRouter; evaluation date not stated. Scenario totals use the evaluator's displayed row totals; the page shows 5 or 10 numbered samples for individual tasks.
Context: NC Bench is Novelcrafter's own creative-writing, rule-following and tool-use test suite. The scenarios are unpublished and are not standardized general-purpose LLM benchmarks. The page displays task totals but does not state the last evaluation date or how category aggregates are weighted.

Source NC Bench (Novelcrafter)

NC Bench: Bad Writing Habits / Detailed Writing Rules / Thriller: chase through city streets (Show measurement, test conditions, and source)

Source value: 92
Score: 92
Metric: NC Bench reported score
Unit: %
Category: NC Bench / Bad Writing Habits / Detailed Writing Rules
Direction: Higher is better
Sample: 5
Source type: independent-evaluator
Evaluator: NC Bench (Novelcrafter)
Status: active
Retrieved at: 2026-10-07
Methodology: Independent evaluation. Model ID=aion-labs/aion-3.5-mini; displayed configuration=Aion 3.5 Mini (Reasoning, High); route=OpenRouter; evaluation date not stated. Scenario totals use the evaluator's displayed row totals; the page shows 5 or 10 numbered samples for individual tasks.
Context: NC Bench is Novelcrafter's own creative-writing, rule-following and tool-use test suite. The scenarios are unpublished and are not standardized general-purpose LLM benchmarks. The page displays task totals but does not state the last evaluation date or how category aggregates are weighted.

Source NC Bench (Novelcrafter)

NC Bench: Bad Writing Habits / Detailed Writing Rules / subcategory total (Show measurement, test conditions, and source)

Source value: 91.19
Score: 91.19
Metric: NC Bench reported score
Unit: %
Category: NC Bench / Bad Writing Habits / Detailed Writing Rules
Direction: Higher is better
Source type: independent-evaluator
Evaluator: NC Bench (Novelcrafter)
Status: active
Retrieved at: 2026-10-07
Methodology: Independent evaluation. Model ID=aion-labs/aion-3.5-mini; displayed configuration=Aion 3.5 Mini (Reasoning, High); route=OpenRouter; evaluation date not stated. Scenario totals use the evaluator's displayed row totals; the page shows 5 or 10 numbered samples for individual tasks.
Context: NC Bench is Novelcrafter's own creative-writing, rule-following and tool-use test suite. The scenarios are unpublished and are not standardized general-purpose LLM benchmarks. The page displays task totals but does not state the last evaluation date or how category aggregates are weighted.

Source NC Bench (Novelcrafter)

NC Bench: Bad Writing Habits / genre / Fantasy: entering an ancient ruin (Show measurement, test conditions, and source)

Source value: 84
Score: 84
Metric: NC Bench reported score
Unit: %
Category: NC Bench / Bad Writing Habits / genre
Direction: Higher is better
Sample: 5
Source type: independent-evaluator
Evaluator: NC Bench (Novelcrafter)
Status: active
Retrieved at: 2026-10-07
Methodology: Independent evaluation. Model ID=aion-labs/aion-3.5-mini; displayed configuration=Aion 3.5 Mini (Reasoning, High); route=OpenRouter; evaluation date not stated. Scenario totals use the evaluator's displayed row totals; the page shows 5 or 10 numbered samples for individual tasks.
Context: NC Bench is Novelcrafter's own creative-writing, rule-following and tool-use test suite. The scenarios are unpublished and are not standardized general-purpose LLM benchmarks. The page displays task totals but does not state the last evaluation date or how category aggregates are weighted.

Source NC Bench (Novelcrafter)

NC Bench: Bad Writing Habits / genre / Horror: alone in an eerie place at night (Show measurement, test conditions, and source)

Source value: 82
Score: 82
Metric: NC Bench reported score
Unit: %
Category: NC Bench / Bad Writing Habits / genre
Direction: Higher is better
Sample: 5
Source type: independent-evaluator
Evaluator: NC Bench (Novelcrafter)
Status: active
Retrieved at: 2026-10-07
Methodology: Independent evaluation. Model ID=aion-labs/aion-3.5-mini; displayed configuration=Aion 3.5 Mini (Reasoning, High); route=OpenRouter; evaluation date not stated. Scenario totals use the evaluator's displayed row totals; the page shows 5 or 10 numbered samples for individual tasks.
Context: NC Bench is Novelcrafter's own creative-writing, rule-following and tool-use test suite. The scenarios are unpublished and are not standardized general-purpose LLM benchmarks. The page displays task totals but does not state the last evaluation date or how category aggregates are weighted.

Source NC Bench (Novelcrafter)

NC Bench: Bad Writing Habits / genre / Literary fiction: old friends reunite (Show measurement, test conditions, and source)

Source value: 83
Score: 83
Metric: NC Bench reported score
Unit: %
Category: NC Bench / Bad Writing Habits / genre
Direction: Higher is better
Sample: 5
Source type: independent-evaluator
Evaluator: NC Bench (Novelcrafter)
Status: active
Retrieved at: 2026-10-07
Methodology: Independent evaluation. Model ID=aion-labs/aion-3.5-mini; displayed configuration=Aion 3.5 Mini (Reasoning, High); route=OpenRouter; evaluation date not stated. Scenario totals use the evaluator's displayed row totals; the page shows 5 or 10 numbered samples for individual tasks.
Context: NC Bench is Novelcrafter's own creative-writing, rule-following and tool-use test suite. The scenarios are unpublished and are not standardized general-purpose LLM benchmarks. The page displays task totals but does not state the last evaluation date or how category aggregates are weighted.

Source NC Bench (Novelcrafter)

Aion 3.5 Mini

Reasoning (requested): low

Current attempt

Run date: Oct 11, 2026
API provider: AionLabs
Requested API model: aion-labs/aion-3.5-mini
API model reported in response: aion-labs/aion-3.5-mini
Reasoning setting: low
Pinned endpoint: AionLabs | aion-labs/aion-3.5-mini-20260923
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Reasoning tokens: 2,341
Test protocol: community-visual-low-v1
Technical checks: Passed, not a quality rating
Response time: 89.8 s

Visually reviewed. This individual test does not establish overall model quality.

Type	Evidence and data date
Price	Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. Source: Pricing · Aion Labs model catalog (retrieved October 7, 2026) · Aion Labs model catalog · Editorial description reviewed October 7, 2026
Input	Documented modalities. Retrieved October 7, 2026. Source: Aion Labs API reference · Aion Labs API reference (retrieved October 7, 2026) · Aion Labs API reference · Editorial description reviewed October 7, 2026
Output	Documented modalities. Retrieved October 7, 2026. Source: Aion Labs API reference · Aion Labs API reference (retrieved October 7, 2026) · Aion Labs API reference · Editorial description reviewed October 7, 2026
Research status	Research date October 7, 2026. 4 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not found in the inspected sources	standardized general-purpose benchmark scores Original wording The checked Aion catalog and API reference publish no scores. EvalMap and NC Bench publish exact-system custom tests, but no exact Aion 3.5 Mini score in a standardized general-purpose suite was located in this review.
Unresolved	base-checkpoint-specific scores Original wording Aion Labs describes Aion 3.5 Mini as a multi-model GLM-family system. The checked sources do not identify its contributing checkpoints or attribute any score to one isolated checkpoint.
Additional source	EvalMap, Small tests (retrieved October 7, 2026)
Additional source	NC Bench (Novelcrafter) (retrieved October 7, 2026)

Aion 3.5 Mini

Specifications and access

Measurements without matching peer values

Our tests

Pelican on a bicycle

Published prices

Sources and data date