Home › Frontier and closed › aion-labs

Aion-3.0 aion-labs

Closed weights API only listed on OpenRouter 2026-07-07 (110d ago) · source Last verified 2026-10-25 06:51 UTC OpenRouter ↗

Release timeline

Stages observed by the nightly radar: announced → API only → weights public → served by third parties. Each entry carries the source it was seen at.

  1. 2026-07-07 · API only source
    seeded from the earliest dated observation when first seen · observed 2026-10-07 20:20 UTC

Description

Aion-3.0 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 contribute...

via OpenRouter listing · observed 2026-10-24 21:26 UTC. The listing text is the provider's own description, not an assessment.

Where to run 1 providers · 1 endpoints

Hosted endpoints observed for Aion-3.0, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting. Cheapest observed input price: $3.00/M.

ProviderModel refContextQuant$/M in$/M outtok/sTTFTToolsStatusObserved
AionLabs
openrouter
aion-labs/aion-3.0 128K unknown $3.00 $6.00 — — yes live 2026-10-24

No third-party providers observed beyond the lab's own endpoints. Cache-read price $0.75/M (source, observed 2026-10-24).

Facts

Context length131,072 tokens (128K) · OpenRouter listing
Modalitiestext → text
Max completion tokens32,768
Supported parametersinclude_reasoning, max_tokens, reasoning, response_format, temperature, tool_choice, tools, top_p
OpennessClosed weights · closed lab
StageAPI only
Confidencemedium
Pricing (USD per M tokens) in $3.00 · out $6.00 · cache read $0.75
OpenRouter list price (cheapest live endpoint) · source · observed 2026-10-24 21:26 UTC

Open alternatives 5

Nearest open-weights models by modality, context and price on this watch list. Not a quality ranking.

ModelOrgParamsContext$/M inLicenseWhy it is here
Meta-Llama-3-8B-Instruct meta-llama 8.03B — — llama3 closest by rank, context and price
Llama-3.1-8B meta-llama 8.03B — — llama3.1 closest by rank, context and price
DeepSeek-R1 deepseek-ai 684B 160K $0.70 mit similar context (164K), cheaper input price ($0.7/M vs $3/M)
Qwen3-0.6B Qwen 752M 40K — apache-2.0 closest by rank, context and price
DeepSeek-R1-Distill-Qwen-32B deepseek-ai 32.8B 128K — mit similar context (131K)

Get alerts

Watch the release radar

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.

Sources

Radar run: 2026-10-25 06:51 UTC · Last verified 2026-10-25 06:51 UTC