Replying to @SpardaAlexeus
Tokens are billed to their api pricing. Pro gets you $75 of manual usage + Auto and Ultra gets you $225+ Auto and no 5hr limits
Replying to @SpardaAlexeus
There is no catch, we offer subsidized plans so people can use our products at a lower price.
Replying to @SeiryuKyoto
DeepSeek V4.1 flash is our most economical model followed by GPT 6 Luna. Both will give you enough usage to work without worrying about limits. If you do hit limits you can always switch to Roost
Subagents vs sub-sessions: a subagent is a quick helper that hands back one answer. A sub-session is a full chat you can keep talking to, on its own model if you want.
Try it in the Perch desktop app: ask for two fixes “in separate sessions” and click Start on both.
perchai.app
How it works:
• Perch suggests a session, or you ask for one. Nothing starts until you click Start.
• Each runs in the background as its own chat, under the one that started it.
• Open one and type to steer it.
• When it’s done or needs you, it reports back.
Sub-sessions are now in Perch, on every plan, free included.
Some jobs are too big for one chat. Hand them off and each one gets a chat of its own: it runs in the background, you can open it and steer it mid-task, and it reports back when it’s done.
Replying to @CranelAnos
Depends on the model you use, Free plan usage is $20/month. On DeepSeek Flash that's billions of tokens.
Replying to @SpardaAlexeus
Yeah we could they seem simple enough, added it to our update roadmap
Replying to @AlexDu159740
Nope if you have a Pro or Ultra they are available everywhere in our desktop app, CLI and Web and Mobile too
Replying to @SpardaAlexeus
We do allow Skills, MCP's and plugins to an extent. Some plugins might need some additional support and we are happy to do so on request
Replying to @dolls0409
Love hearing that! Let us know if you would like us to add something!
We are extending our free model promo till Nov 20 on these models so you can continue testing out our app:
1) DeepSeek v4.1 Flash (1017)
2) GLM 5.3 Flash
3) Qwen 3.8 Max
Try it out perchai.app
Let us know if you have any feedback or would like us to add anything!
MiniMax M3.1 Flash is now available on Perch AI completely free of cost.
Our Free Lineup now includes:
1)MiniMax M3.1 Flash
2) GLM 5.3 Flash
3) DeepSeek V4.1 Flash
4) Beam 1.0
Try now: perchai.app
Replying to @TolkienFragment
Yes these rates are permanent and we only intend to make them better not worse hopefully.
Replying to @frankli23709971
It should be available, both wechat and alipay were enabled!
On Pro and hitting the 5-hour limit mid-task? Ultra removes it.
Upgrading from Pro only charges the difference for the rest of your billing period, and your new limits apply right away.
Tired of hitting limits on premium models? Introducing Perch AI Ultra
Ultra adds Fable 5.1 and Astra 6 to Perch's Model Lineup.
$30 a month. No 5-hour limit. 3x Pro’s weekly room, with $225 a month of manual usage plus fair-use auto router usage up to $450/month of usage
Perchai.app/ultra
Kimi K3.1 Pro is now available on Perch AI Pro with 7.5x usage as usual.
Sign up now to get $75 in credits for Kimi K3.1 Pro and more: perchai.app/pricing
Replying to @IAMDOWN4MALFOID
We are too broke for that 😭 . Hopefully once the open weights come out we can negotiate a deal with one of our providers






