> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apiyi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# GPT-6.1 Sol Is Live with Cache Reads Half the Price of GPT-6 Sol

> gpt-6.1-sol, launched by OpenAI at DevDay on 29 September, is now live on APIYI with capability close to GPT-6 Astra. Priced at 2 USD input and 10 USD output per 1M tokens in line with the provider, with cache reads cut from 0.20 to 0.10 USD; savings come through top-up promotions.

**2026/9/30 15:17 (UTC+8)** · New Model · OpenAI

🚀 **`gpt-6.1-sol` is live, with cache reads at half the price of `gpt-6-sol`**

OpenAI's upgraded Sol, launched at DevDay on 29 September, scores 52 on the Artificial Analysis Intelligence Index: 4 points above GPT-6 Sol and just 1 point below GPT-6 Astra.

Pricing (per 1M tokens, all four billing items match the provider):

* Input \$2 / output \$10, the same as `gpt-6-sol`
* Cache read \$0.10, down from \$0.20 on `gpt-6-sol`
* Cache write \$2.50; requests with more than 272K input tokens are billed at the second tier

Savings come through our [top-up promotions](/en/faq/recharge-promotions). Migrating from `gpt-6-sol` is a model-name change; note that reasoning effort no longer supports `none`, and the lowest level is `low`.

📖 Benchmarks, tier pricing and code samples: [GPT-6.1 Sol Is Live](/en/news/gpt-6-1-sol-launch)

***

← [Back to Live Updates](/en/live) · 📚 [Monthly archive](/en/live/archive)