AionLabs: Aion 3.5
AionLabs' flagship GLM-based multi-model system with adjustable reasoning effort.
aion-labs/aion-3.5Drop this model into any OpenAI-compatible client by setting the base URL, your API key, and the model ID below.
curl https://api.kyara-intelligence.com/v1/chat/completions \
-H "Authorization: Bearer $KYARA_INTELLIGENCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "aion-labs/aion-3.5",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'Aion 3.5 is the successor to Aion-3.0 from AionLabs, a multi-model system built on the GLM family of models. Multiple specialized models each contribute to a response through a collaborative generation process, giving long-form creative writing stronger structure and progression. It reasons on every request with adjustable effort (low, high or max), supports tool calling and structured outputs, and offers a 262K token context window with up to 32K tokens of output, so long documents and extended sessions stay coherent.
- Input
- 7.5x
- Output
- 5x
Multiples are relative to the catalog median; bars are scaled to the most expensive model.
- Reasoning
- Available
- Status
- Current
Kyara Intelligence does not add a moderation layer. Moderating what goes in and out of your integration is up to you as the developer.
Kyara routes API calls without modifying inputs or outputs, and does not log prompt or response content. You are responsible for how your app uses the models and for complying with Kyara's terms.