Skip to main content
Aion LabsSep 23, 2026

Aion 3.5

aion-labs-aion-3-5AnonymizedUncensored

Aion 3.5, the successor to Aion 3.0, is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models, with a longer context window. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.

$3.75/$7.50
per 1M in / out
256K
context window
32K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 21%67.2%
Blended pricecheaper than 23%$4.69
Context windowlarger than 32%256K
Max outputlarger than 21%32K

Further right is better. Hover a dot for its model.

Time to first token— 
Output speed— 
Uptime— 

Last 24 hours of Venice traffic.How it’s measured

Capabilities

What the model takes in, returns and supports through the API.

InText
OutText

Not supportedimage input, video input, audio input, X search and log probabilities

Benchmarks

GPQA Diamond
67.2%110th of 139 · 77 score higher for less, including GPT-6.2 Sol, GPT-6.2 Sol Pro and Gemini 3.8 Flash

Specs

Model ID
aion-labs-aion-3-5
Endpoint
POST /api/v1/chat/completions
Context window
262,144 tokens
Max output
32,768 tokens
Reasoning
Always on
Precision
Set by the provider
Privacy
Anonymized
Weights
Closed
Added
Sep 23, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
Aion 3.5$3.75$7.5067.2%256K32K——
Gemini 4 Argon$2.50$12.5096.0%1M64K——
Gemini 4 Carbon$2.50$12.5095.5%1M64K——
Kimi K3.1 Pro E2EE$2.50$12.5091.4%1M128K——
GPT-5.6 Terra$2.00$12.0093.9%1M128K——

Other versions

  1. Aion 3.0Jul 2026
  2. Aion 3.5Sep 2026

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$3.75per 1M tokens
Cached input$0.937575% off input
Output$7.50per 1M tokens

Estimate a workload

$0.0112per request
$113for 10,000 requests

Blended price against similar models

Aion 3.5$4.69

Per 1M tokens at three input tokens for each output token.

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.

curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "aion-labs-aion-3-5",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelaion-labs-aion-3-5Required
messagestextContent parts the model reads
max_completion_tokensUp to 32,768Counts reasoning tokens
toolsFunction definitionsWith tool_choice
response_format{ type: "json_schema" }Output that matches a schema
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations