Upfyn Rishi: Hard multi-step reasoning, research, media
Upfyn
Deep · Agentic
Deep · Agentic
Meet Rishi
Best for hard multi-step reasoning, research, media.
Rishi plans, executes, and then verifies its own work across long multi-step runs, which is why it is slower and why it costs the most per token. It is the only model that accepts video as input and generates video. Reach for it when being wrong is expensive — research you intend to act on, a migration you are about to run, an analysis someone will make a decision from — and let the other two carry everything else.
The only model that accepts video as input and generates video
A 1M-token context
Slower and the most thorough — for when being wrong is expensive
Rishi
Tax table migration
Today 11:20 AM
Move billing to the new tax table and prove every total still matches.
Plan4 of 4 done
Read the billing code and the new table
Wrote the migrationsrc/billing/tax.ts
Replayed 1,284 invoices on both tables
Compared every total1,284 of 1,284 match
Done, and checked: all 1,284 invoice totals match to the paisa. The change is waiting in Review.
Checkout walkthrough.mp42:14
Where do people get stuck in this checkout?
Watched Checkout walkthrough.mp4 · 2:14
0:42 the coupon field hides the Pay button on small screens
1:18 the address form clears itself after an error
1:57 nothing shows progress while the payment confirms
Ask a follow-up
LocalRishi Extra High
RishiOne of Upfyn's own frontier models.
Rishi plans, does the work, then checks it
The only model that watches video
It makes video too
Plans, executes, then checks
Rishi works across long multi-step runs: it plans the work, carries it out, and verifies the result before you see it. That is why it is slower, and why it costs the most per token.
Plan · Execute · Verify
Printer and workflow settings migration
1,240 settings moved from the legacy INI format to the new JSON schema
September 2026
1 / 10
Research you intend to act on
Reach for Rishi when a plausible wrong answer is the failure: research you mean to act on, an analysis someone will decide from, a change you are about to run. Let Bala and Yuva carry everything else.
Ask Rishi anything
ManualCloudRishi
Video in, video out
Rishi is the only one of the three that understands video and generates it. Video generation is available through /v1/videos.
Ask Rishi anything
ManualCloudRishi
Finish your research with something you can use
Compare options, collect evidence, and turn research into a useful brief with Upfyn. Keep the findings connected to the sources behind them.
Research brief
Choosing a patient CRM
Caretrack, PatientLoop and Clinicore compared for our five clinics
September 2026
1 / 10
Give your weekly report a repeatable starting point
Build a weekly report from your working files, refine it in chat, and schedule the preparation so you can spend more time reviewing the result.
Ask Rishi anything
ManualCloudRishi
Where it runs
Rishi is available wherever you use Upfyn: the desktop app, the web app and your phone, and through the UpfynAI gateway under the model id upfyn-rishi. It is one of Upfyn’s own frontier models, hosted on AWS in the India region. Your projects, tools and permissions stay with you when you switch models.
Chat/v1/chat/completions
Images/v1/images/generations
Speech/v1/audio/speech
Transcription/v1/audio/transcriptions
Video generation/v1/videos
How the three compare
Bala
Yuva
Rishi
Best for
Everyday chat, drafting, high-volume text
Production chat, coding, vision + audio
Hard multi-step reasoning, research, media
Speed
Fastest
Fast
Deliberate
Depth
Direct — single pass
Considered — up to 2 stages
Agentic — most thorough
Modality
Text
Text + image + audio
Text + image + audio + video generation
Context
up to 1M
1M
1M
Plans
Every plan, including Free
Every plan, including Free
Every plan · usage charged in credits
Where it stops
Longer reasoning and media generation use more of your usage limit. Usage depends on the request, output length and tools used; there is no fixed number of runs per plan.
Availability
Every plan · usage charged in credits. Usage counts toward your plan’s limit; the plans and what each includes are on the pricing page.