The RightNow mark over a green hill and a blue sky.

RightNow decision model

RightNow is our first decision model.

It doesn't write text. You send it a state and your questions, and for each question it returns a decision with a probability for every option, a confidence, and a calibration version. Output is not charged, and refused calls are not charged.

RightNow AI is a YC-backed GPU research lab. This is the first checkpoint of our post-trained models, and more checkpoints will follow.

The step before thinking

Reflex Training. Decision models usually read the whole input, then answer. RightNow decides on whatever has arrived so far: stream in text, JSON, images, voice, PDF and video, and it returns a probability for every option at any moment. It is trained to hold back until the evidence is there, then commit. That is the step before thinking.

Reflex Architecture. RightNow keeps a probability for every option and updates it as each part of the input arrives.

One model, eight inputs

RightNow takes text, JSON, robot state, codebases, PDF, images, voice and video (preview).

Text

JSON

Robot state

Codebase

PDF

Images

Voice

Video (preview)preview

Supported formats are PNG and JPEG for images; WAV audio at 16 kHz; and PDF for documents.

Each call takes:

up to 1,024 questions
up to 38,000 state tokens
up to 16 attachments, including up to 4 images, 1 audio file and 1 video

Text questions take 2 to 10 options or 2 to 4 levels. Media questions take 2 to 26 options or 2 to 10 levels.

Streaming decisions

You don't have to wait for the full input. Send changes as they happen: append text, update the state, or add attachments. RightNow returns versioned decisions. Every new decision carries its version, and the probability for every option updates as each part of the input arrives.

An example

State: The blender I ordered arrived with a cracked jar.
Question (boolean): Did the item arrive damaged?
Decision: true

true0.999501

false0.000499

Recorded example, RightNow, Oct 26, 2026.

Speed

Decision latencyIncluding the input

0ms506

Text

30 to 33 ms

Session

34 to 36 ms

Image

41 ms178 ms

Audio

34 ms96 ms

Video (preview)

41 ms168 ms

Document

46 ms506 ms

Medians. Record MODEL-SPEED-ROW-1027, Oct 27, 2026.

Input	Decision latency	Including the input
Text	Decision latency30 to 33 ms (p95 32 to 34 ms)
Single token	Decision latency7.2 ms
Session	Decision latency34 to 36 ms
Image	Decision latency41 ms	Including the input178 ms
Audio	Decision latency34 ms	Including the input96 ms
Video (preview)	Decision latency41 ms	Including the input168 ms
Document	Decision latency46 ms	Including the input506 ms

Medians. Record MODEL-SPEED-ROW-1027, Oct 27, 2026.

Benchmarks

Artificial Analysis Decision Index

RightNow scores 63.20, measured 2026-10-28. This was measured by RightNow AI on the public held-out half. It is not an Artificial Analysis evaluation. The published rows come from Artificial Analysis's own evaluation, so the two are different evaluations. The chart shows positions and values only.

Index0100

d1-ultra65USD per million tasks: 32

SubQ Snap 1.165USD per million tasks: 30

Elephant 9B65USD per million tasks: 8.4

Drex Max64USD per million tasks: 23

RightNow63.20

Drex 2.058USD per million tasks: 41

Jev 1.14 by TypeSafe57USD per million tasks: 42

Decider v1.256USD per million tasks: 15

GLiDE54USD per million tasks: 119

Microsoft-Decision-154USD per million tasks: 31

Mercury Decide53USD per million tasks: 15

Celeris-1 Decision52USD per million tasks: 32

d150USD per million tasks: 15

Decider Flash v1.250USD per million tasks: 8.2

GPT-6 Luna (Decisions)48USD per million tasks: 79

RightNow: measured by RightNow AI on the public held-out half on 2026-10-28, on the model version served that day. Not an Artificial Analysis evaluation. Published rows: Artificial Analysis (artificialanalysis.ai), downloaded Oct 30, 2026.

Amazon Polarity

Accuracy: 97.33%
Cost per case: USD 0.0005726
Time per case: 0.3371 s

Amazon Polarity. Run BENCH-FRONTIER-1026A, Oct 26, 2026.

Invoice Processing and Security Incidents

Model	Agreement	USD per workflow	Seconds per workflow
RightNow	AgreementPending	USD per workflowPending	Seconds per workflowPending
Claude Haiku 4.5	Agreement42.9%	USD per workflow$0.0558	Seconds per workflow30.8 s
Claude Opus 5	Agreement78.4%	USD per workflow$0.4856	Seconds per workflow92.1 s
Claude Sonnet 5	Agreement72.9%	USD per workflow$0.3616	Seconds per workflow241.3 s
DeepSeek V4 Flash	Agreement69.8%	USD per workflow$0.0133	Seconds per workflow84.1 s
DeepSeek V4 Pro	Agreement72.7%	USD per workflow$0.0830	Seconds per workflow137.4 s
GPT-5.6 Luna	Agreement67.8%	USD per workflow$0.0081	Seconds per workflow21.4 s
GPT-5.6 Sol	Agreement79.1%	USD per workflow$0.2152	Seconds per workflow34.3 s
GPT-5.6 Terra	Agreement74.7%	USD per workflow$0.0778	Seconds per workflow17.3 s
Jev	Agreement61.8%	USD per workflow$0.0011	Seconds per workflow0.5 s

TypeSafe's published workflow boards, snapshot Sept 28, 2026. RightNow: Pending.

Model	Agreement	USD per workflow	Seconds per workflow
RightNow	AgreementPending	USD per workflowPending	Seconds per workflowPending
Claude Haiku 4.5	Agreement58.8%	USD per workflow$0.0047	Seconds per workflow3.4 s
Claude Opus 5	Agreement66.2%	USD per workflow$0.0574	Seconds per workflow15.1 s
Claude Sonnet 5	Agreement60.8%	USD per workflow$0.0271	Seconds per workflow18.9 s
DeepSeek V4 Flash	Agreement37.9%	USD per workflow$0.0032	Seconds per workflow37.4 s
DeepSeek V4 Pro	Agreement41.7%	USD per workflow$0.0234	Seconds per workflow60.0 s
GPT-5.6 Luna	Agreement52.1%	USD per workflow$0.0013	Seconds per workflow7.0 s
GPT-5.6 Sol	Agreement62.5%	USD per workflow$0.0295	Seconds per workflow8.5 s
GPT-5.6 Terra	Agreement51.2%	USD per workflow$0.0119	Seconds per workflow5.7 s
Jev	Agreement61.7%	USD per workflow$0.0001	Seconds per workflow0.3 s

TypeSafe's published workflow boards, snapshot Sept 28, 2026. RightNow: Pending.

RightNow and Jev by TypeSafe

Capability	RightNow	Jev by TypeSafe
Inputs	RightNowtext, JSON, robot state, codebase, PDF, images, voice, video (preview)	Jev by TypeSafeText, JSON; images opt in.
Voice	RightNowWAV audio	Jev by TypeSafeNot supported
Video (preview)	RightNowMP4 video (preview)	Jev by TypeSafeNot supported
Files	RightNowPNG, JPEG, WAV, PDF, MP4	Jev by TypeSafePNG, JPEG (opt in)
Standard context	RightNow38,000 tokens	Jev by TypeSafe64k per-request / 32k per-question
Questions per call	RightNowMultiple questions per call	Jev by TypeSafeMultiple questions per call
Probabilities	RightNowPer-option probabilities	Jev by TypeSafeTyped probabilities
Streaming	RightNowStreaming
versioned decisions

Jev by TypeSafe column from TypeSafe docs, read Oct 28, 2026.

Pricing

Item	Price
Text input	0.19 per million tokens
Cached text input	0.019 per million tokens
Output	Not charged
Answered question	0.0001 per answered question
Call fee	0.00001 per answered call
Image	0.003 per image
Audio	0.0002 per started second
PDF	0.002 per page
Video (preview)	0.0008 per started second, 0.008 minimum per clip

USD. Rate card sz-card-2026-11-11-h, as of Nov 11, 2026.

The call fee is never charged on refusals, zero-answer calls, or free, promotional or replay calls.

Two reference costs:

356 uncached tokens with one answered question costs USD 0.00018
38,000 tokens with one question costs USD 0.0073

New accounts get USD 1 in credit at sign-up. It's one per eligible verified email, subject to eligibility checks. Top-ups start at USD 5.

Start building

API: https://api.rightnowai.co/v1
Docs: https://www.rightnowai.co/docs/decision-model
SDKs: @rightnowai/system-zero on npm and rightnow-system-zero on PyPI