LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
ai

Aion 3.5 Mini

aion-labs·aion-labs/aion-3.5-mini·GA·Closed·NEW
Efficient model for low-latency assistance, extraction, and routine automation

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·OpenRouterGateway
$0.70 / $1.40
Blended $0.88 · 1.3× spread
Context
262,144
Output limit
32,768
Knowledge cutoff
—
Released / updated
2026-09-23 / 2026-09-23
Capabilities
✓ Reasoning✓ Tool useStructured output✓ TemperatureAttachments
Modalities
Text

Aion 3.5 Mini by aion-labs is offered by 4 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is OpenRouter at $0.70 / $1.40 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 1.3× across the providers that host it.

The context window is 262,144 tokens, with an output limit of 32,768 tokens. It supports reasoning and tool use.

Available at 4 providers4 with public prices

  • ProviderInput / Output
  • OpenRouterGateway
    $0.70 / $1.40
    Cache read $0.18Context 262,144Output limit 32,768
  • Kilo GatewayGateway
    $0.70 / $1.40
    Cache read $0.18Context 262,144Output limit 32,768
  • NanoGPTGateway
    $0.70 / $1.40
    Cache read $0.18Context 262,144Output limit 32,768
  • Venice AIGateway
    aion-labs-aion-3-5-mini
    $0.88 / $1.75
    Cache read $0.23Context 262,144Output limit 32,768
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
OpenRouterGateway$0.70$1.40$0.18—262,14432,768
Kilo GatewayGateway$0.70$1.40$0.18—262,14432,768
NanoGPTGateway$0.70$1.40$0.18—262,14432,768
Venice AI
aion-labs-aion-3-5-mini
Gateway$0.88$1.75$0.23—262,14432,768

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = loweffort = higheffort = max

2 / 4 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1OpenRouter$147.60
2Kilo Gateway$147.60
3NanoGPT$147.60
4Venice AI$184.50
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $0.88

Price history accumulates from each data sync; currently only 1 sample(s) (2026-09-24). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

aiAion 3.5same lab—aiAion-RP 1.0 (8B)same lab—
Data partly from models.dev (MIT)