Aion 3.5

by AionLabsaion-labs/aion-3.5

  • Text
  • No route yet
  • Released

LLMCompare cannot run Aion 3.5 yet.No route to this model is configured on this site yet. Its prices and parameters are listed below for reference.

See the models that can be run now

Aion 3.5 at a glance

Context length
262,144 tokens
Maximum output
32,768 tokens
Accepts
Text
Returns
Text
Features
ReasoningJSON outputTool callingPrompt caching
Reasoning effort levels
maxhighlowReasoning is always on for this model.
Released
23 Sep 2026
Knowledge cutoff
Not published

Model facts synced from the OpenRouter model list on 21 Oct 2026.

Aion 3.5 pricing by route

A route is the service LLMCompare calls to reach the model. Aion 3.5 has 1 route. Prices are in US dollars.

Prices of Aion 3.5 on each route
RouteOn LLMCompareInputper 1M tokensOutputper 1M tokensCache readper 1M tokensPrice verified onSource
OpenRouterDefaultNot configured$3.00$6.00$0.75openrouter.ai/aion-labs/aion-3.5

The cost shown in an LLMCompare report is calculated from these prices as they were at the time of the run.

Cost calculator

Estimate what a batch of calls to Aion 3.5 costs. The starting numbers are examples. Change them to match your task.

Part of the input tokens above, billed at the cache read price.

Billed in addition to the output tokens.

Cost per call
$0.006
8 credits
Cost of 100 calls
$0.60
800 credits

Calculated from the OpenRouter prices verified on 21 Oct 2026. Credits are the cost plus a 20% service fee, at $0.001 per credit, rounded up for each call, with a minimum of 1 per call. A real run is charged for the usage the provider reports.

Parameters you can set

These are the parameters LLMCompare can set when it calls the model through OpenRouter.

Parameters of Aion 3.5
ParameterTypeRange or optionsDefault
temperatureNumber0 to 2in steps of 0.1Provider default
top_pNumber0 to 1in steps of 0.05Provider default
max_tokensInteger1 to 32,768Provider default
reasoning_effortOne ofmaxhighlowhigh
response_formatOne oftextjson_objectProvider default

About Aion 3.5

Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...

Description as published for this model. LLMCompare has not edited it.

Models to compare with Aion 3.5

Text models from the same provider and models at the nearest price. The order is not a ranking.

Models to compare with Aion 3.5
Add to comparisonModelContextMax outputInput priceper 1M tokensOutput priceper 1M tokensFeaturesReleasedOn LLMCompare
Aion-3.0AionLabsaion-labs/aion-3.0131k32.8k$3.00$6.00JSONToolsCacheNo route yet
Aion-2.0AionLabsaion-labs/aion-2.0131k32.8k$0.80$1.60JSONToolsCacheNo route yet
Aion-RP 1.0 (8B)AionLabsaion-labs/aion-rp-llama-3.1-8b32.8k29.5k$0.80$1.60—No route yet
Mistral Medium 3.5Mistralmistralai/mistral-medium-3-5262k210k$1.50$7.50ReasoningJSONToolsVisionNo route yet
Pareto 26.9unbiasedunbiased/pareto-26.9262k131k$2.50$7.50JSONToolsCacheVisionNo route yet
o3OpenAIopenai/o3200k100k$2.00$8.00JSONToolsCacheVisionNo route yet

Questions about Aion 3.5

How much does Aion 3.5 cost?
On the OpenRouter route, Aion 3.5 costs $3.00 per 1 million input tokens and $6.00 per 1 million output tokens, in US dollars. Input tokens that Aion 3.5 reads from the prompt cache cost $0.75 per 1 million tokens. LLMCompare verified this price on 21 Oct 2026.
What is the context length of Aion 3.5?
Aion 3.5 has a context length of 262,144 tokens and returns up to 32,768 output tokens in one call.
What inputs does Aion 3.5 accept?
Aion 3.5 accepts these inputs: Text. Aion 3.5 returns: Text.
Which reasoning effort levels does Aion 3.5 support?
Aion 3.5 supports these reasoning effort levels: max, high, low. Reasoning is always on for Aion 3.5 and cannot be turned off.
Can I test Aion 3.5 on my own data?
Not yet. LLMCompare lists the prices and parameters of Aion 3.5, but no route to Aion 3.5 is configured on LLMCompare, so it cannot be selected for an evaluation.