AONISDocs

Resources

Pricing

Simple pricing. Pay only for what you use.

No subscriptions. No fixed plans. Pay only for the tokens you use.

Aonis public pricing · USD per 1M tokens

Each discount compares the Aonis public input and output price with the corresponding provider's official API price. Cache pricing can differ by provider and configuration.

ModelInputOutputCache ReadCache WriteOfficial APIDiscount
Anthropic
Claude Fable 5claude-fable-5$1.50$7.50$0.15$1.875$10.00 input$50.00 output85% off
Claude Opus 5claude-opus-5$0.75$3.75$0.075$0.9375$5.00 input$25.00 output85% off
Claude Opus 4.8claude-opus-4-8$0.75$3.75$0.075$0.9375$5.00 input$25.00 output85% off
Claude Opus 4.7claude-opus-4-7$0.75$3.75$0.075$0.9375$5.00 input$25.00 output85% off
Claude Sonnet 5claude-sonnet-5$0.30$1.50$0.03$0.375$2.00 input$10.00 output85% off
Claude Sonnet 4.6claude-sonnet-4-6$0.45$2.25$0.045$0.5625$3.00 input$15.00 output85% off
OpenAI
GPT-5.6 Solgpt-5.6Aliases: gpt-5.6-sol, gpt-5.6-fast, codex-5.6-sol$0.75$4.50$0.075$0.9375$5.00 input$30.00 output85% off
GPT-5.6 Sol Ultragpt-5.6-sol-ultraAliases: codex-5.6-sol-ultra$0.75$4.50$0.075$0.9375$5.00 input$30.00 output85% off
GPT-5.6 Terragpt-5.6-terraAliases: codex-5.6-terra$0.30$1.80$0.03$0.375$2.00 input$12.00 output85% off
GPT-5.6 Lunagpt-5.6-lunaAliases: codex-5.6-luna$0.05$0.30$0.005$0.0625$0.20 input$1.20 output75% off
Google
Gemini 3.1 Progemini-3.1-pro$0.40$2.40$0.04$0.40$2.00 input$12.00 output80% off
Gemini 2.5 Progemini-2.5-pro$0.25$2.00$0.025$0.25$1.25 input$10.00 output80% off
DeepSeek
DeepSeek V4 Prodeepseek-v4-pro$0.261$0.522$0.005695$0.261$0.435 input$0.87 output40% off
DeepSeek V4 Flashdeepseek-v4-flash$0.105$0.21$0.00427125$0.105$0.14 input$0.28 output25% off
Qwen
Qwen 3.7 Maxqwen3.7-max$0.295$0.885$0.0295$0.3688$1.475 input$4.425 output80% off
Qwen 3.6 Plusqwen3.6-plus$0.11375$0.6825$0.011375$0.142205$0.325 input$1.95 output65% off
Moonshot AI
Kimi K3kimi-k3$0.60$3.00$0.06$0.60$3.00 input$15.00 output80% off
xAI
Grok 4.5grok-4.5$0.40$1.20$0.06N/A$2.00 input$6.00 output80% off
Z.AI
GLM-5.2glm-5.2$0.28$0.88$0.052$0.28$1.40 input$4.40 output80% off

Token pricing

Input
Tokens sent to the model.
Output
Tokens generated by the model.
Cache Read
Eligible prompt or context tokens reused from cache.
Cache Write
Eligible tokens written into cache when supported.

Cache behavior and availability depend on the selected model and request. N/A means no separate public cache-write price is currently listed.