Skip to content
ShilpBot
AI Models

AionLabs Aion 3.5: Pricing, Specs and Limits

AionLabs Aion 3.5: multi-model roleplaying and storytelling system built on the GLM family, 262K context, 3.00 in / 6.00 out per 1M tokens. Specs, limits...

By ShilpBot Team · Published · 3 min read

Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. The listing says it uses a collaborative generation process in which several specialised models each contribute.

It is unusual in this list because it targets creative writing, not coding or agents. A smaller sibling, Aion 3.5 Mini, offers the same approach at a much lower price.

Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.

AionLabs Aion 3.5 quick facts

DetailValue
DeveloperAionLabs
Model IDaion-labs/aion-3.5
Added to the catalogue2026-09-23
TypeMulti-model roleplaying and storytelling system built on the GLM family
ParametersNot listed
Context window262K tokens (262,144)
Maximum output32,768 tokens
Input typestext
Price3.00 in / 6.00 out per 1M tokens (cached input 0.75)

Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Adjustable reasoning effort: listed.

What AionLabs Aion 3.5 is good for

  • Interactive fiction, roleplay and long-form storytelling.
  • Game masters and writers who want consistent characters over long sessions.
  • Creative tasks where tone matters more than tool use.

Limits of AionLabs Aion 3.5

  • At $3 input and $6 output it costs more than several general-purpose models.
  • Output is capped at 32,768 tokens.
  • Apply content rules suited to your audience, especially for platforms with minors.

How AionLabs Aion 3.5 compares

  • Mistral Large 4: It has a smaller context window (262,144 against 1,048,576 tokens); its output cap is 32,768 tokens against 262,144; it does not accept image input; it costs 3.00 input and 6.00 output per million tokens against 0.70 and 2.10.
  • Anthropic Claude Sonnet 5.5: It has a smaller context window (262,144 against 1,000,000 tokens); its output cap is 32,768 tokens against 128,000; it does not accept image or file input; it costs 3.00 input and 6.00 output per million tokens against 2.00 and 10.00.
  • Z.ai GLM-5.3-Prime: It has a smaller context window (262,144 against 1,000,000 tokens); its output cap is 32,768 tokens against 131,072; it costs 3.00 input and 6.00 output per million tokens against 2.80 and 8.80.

Calling AionLabs Aion 3.5 from code

Use the model ID aion-labs/aion-3.5 with any OpenAI-compatible client pointed at OpenRouter:

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "aion-labs/aion-3.5", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'

Prompts that show what AionLabs Aion 3.5 can do

  1. Start a short story with three characters and check that their voices stay distinct over 20 turns.
  2. Ask for a scene rewrite in a different tone.
  3. Compare Aion 3.5 and Mini on the same prompt and see whether the difference justifies the price.

What AionLabs Aion 3.5 costs

The catalogue lists 3.00 per million input tokens and 6.00 per million output tokens, with cached input at 0.75 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 3.60. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $0.51 before caching. If your client reuses the same prompt prefix, cached input at 0.75 per million tokens can cut the input side of that bill by about 75 percent. Aion 3.5 Mini is the smaller, lower-cost sibling at $0.70 per million input tokens and $1.40 per million output tokens, with the same 262,144-token context window and 32,768-token output cap. Prices are set by the provider, can change, and may differ between hosting providers, so check the live model page before you budget.

Keep reading

Compare every paid model by price in our AI model pricing roundup, or see the free models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.

Frequently asked questions

What is the difference between Aion 3.5 and Aion 3.5 Mini?

Mini is the smaller, cheaper sibling at $0.70 input and $1.40 output per million tokens, against $3 and $6 for the full model.

What are the cost and limits of AionLabs Aion 3.5?

As of 2026-11-16 the catalogue lists 3.00 per million input tokens and 6.00 per million output tokens. 262K tokens (262,144) context window, up to 32,768 output tokens, model ID aion-labs/aion-3.5. Prices can change, so check the live model page.

#AionLabs Aion 3.5#AionLabs model#AI model pricing#AI API pricing#AI chat model#creative model#OpenRouter