The right model for the task
Auto reads the request and sends it to the model whose strengths fit that kind of work. It is a judgement, not a claim of perfection.
The best of AI. Without the guesswork.
Rileva chooses the right model for every question—or brings leading models together with Council.
Powered by leading AI models
- OpenAI
- Claude
- Gemini
- Grok
- Mistral
- Perplexity
In Action
A single interface for the world’s best models.
Whether you’re drafting complex prose, reasoning through code, or verifying facts with live citations, Rileva keeps your context, files, and thinking in one fluid flow.
Turn these research notes into a clear launch recommendation.
Mistral Small 4
A focused path to launch
Frame the release around one customer problem, support it with the strongest evidence, and keep the first commitment reversible.
Research notes.pdf2 citations
Why Rileva
No single lab has won AI.
Different models lead at different jobs. Rileva keeps track of their strengths and chooses an appropriate one for each question—without making you manage a stack of separate subscriptions.
- Claude01
Writing & nuance
Careful prose, tone, editing, and long-form thinking.
- OpenAI02
Planning & logic
Structured reasoning, technical plans, and complex problem-solving.
- Gemini03
Files & multimodal
Large documents, images, and mixed-format information.
- Perplexity04
Live research
Fresh web retrieval with sources you can inspect.
- Grok05
Fast critique
Direct analysis, alternative angles, and current topics.
- Mistral06
Multilingual work
Fast, fluent work across major European languages.
One subscription. One interface. The right model for the job.
Multiple perspectives when it matters
Council asks three strong models the same question and writes one considered answer from where they agree and differ.
Context that carries work forward
Projects hold chats, files and standing instructions together, so work that continues over days keeps its footing.
01 — Auto
Stop choosing models.
Rileva reads what you asked for and routes it to the model whose strengths fit that kind of work. It is a judgement, not a claim of perfection. You can lock a model or return to Auto at any time.
- 1
You ask one question.
Just say what you need. No model picker, no prompt engineering, no settings.
- 2
Rileva understands what it needs.
It reads the request and judges which model's strengths fit it — careful reasoning, nuanced writing, live research, large files, or speed.
- 3
The right model answers.
The best-suited model replies, and the answer always says who wrote it.
What is a multi-model AI router? Explain it in three short sentences.
Gemini 3.8 Flash
A router reads each request and sends it to the model best suited to that kind of work. You get a sensible choice without switching providers yourself.
Now design the TypeScript architecture — streaming, fallbacks, idempotent retries.
Mistral Small 4
Core invariant: every request is exactly-once deliverable — streamed once, or a deterministic fallback runs without duplication.
interface Router {
decide(req: ChatRequest): Promise<RouteDecision>;
stream(req: ChatRequest, id: RequestId): AsyncIterable<Token>;
}02 — Council
One question. Multiple perspectives.
Council puts the same question to several leading models, then writes one clear synthesis: where they agree, where they differ, and Rileva’s conclusion. The full perspectives remain available to read.
GPT-5.6 Luna29.5s
The challenge verdict: don’t commit to the original recommendation as written. It overstates the shared evidence and treats several distinct risks as one decision.
The strongest challenge
Demand matters before scale. Test the premise with a small, reversible commitment.
Claude Haiku 4.525.5s
A challenge round makes the hidden assumption visible. One perspective supports the direction; another shows where it could fail under pressure.
Challenge 1: the riskiest assumption
A technically sound idea can still fail when switching costs or adoption are underestimated.
Grok 4.3 Fast21.5s
The original recommendation is too compliance-centric. The stronger view ranks who pays, how fast, and whether the product is genuinely high-risk.
Where the prior case is weak
European delivery needs evidence that customers will convert before category timing runs out.
03 — Continuity
An intelligence that actually remembers.
Rileva keeps the thread of your work — how you think, what you decided last time, the files and chats that belong together — so a question picked up weeks later starts where you left off.
Stuck on the pricing page again. Honestly a bit frustrated — it feels like we’re going in circles.
Rileva remembers
- You think in tradeoffs
- You decide faster with one clear recommendation
- March — the onboarding rewrite
Claude Haiku 4.5
You’ve been here before. In March the onboarding rewrite stalled the same way, and what broke the loop wasn’t more options — it was choosing one audience and shipping the narrow version.
So let’s not reopen the tier debate. Pick the customer you already know pays, write the page for them alone, and leave the second plan out until that page converts. I’ll keep the rest of the thinking here for when you want it back.
Carried from 3 earlier chatsMemory you can read and edit
Connections — in progress
GmailComing soonRead email relevant to your questions.
Google CalendarComing soonCheck your schedule and availability.
Google DriveComing soonFind files and documents relevant to your questions.
Upload files and documents directly into any chat or project today. Direct connections for Google Drive, Gmail, and Google Calendar are currently in development.
Index
Strong models, one workspace.
These are the models Rileva can use right now. Auto chooses among them; you can also select one yourself.
- OpenAIGPT-5.6 LunaGPT-5.6 TerraGPT-6 Astra
- ClaudeClaude Haiku 4.5Claude Sonnet 5Claude Fable 5.1Claude Opus 5.5
- GeminiGemini 3.8 FlashGemini 3.1 Pro
- GrokGrok 4.3 FastGrok 4.7
- MistralMistral Small 4Mistral Large 3Magistral Medium
- PerplexityPerplexity FastPerplexity Research
Common questions
Clear by design.
Straight answers about how Rileva works, what it saves, and what it can reach.
- One place to work with leading AI models. You ask a question; Rileva sends it to an appropriate model and shows you which one answered.
- Auto reads the request and routes it to the model whose strengths fit it — careful reasoning, nuanced writing, live research, large files, or speed. You can lock a model or change it at any point.
- Council asks three strong models the same question, compares where they agree and disagree, and writes one considered answer. You can open the comparison and read each perspective.
- The models listed here are the ones currently available. Auto chooses among them, and you can select one manually in a chat.
- Yes. Conversations, uploaded files and generated images are saved to your workspace, and projects keep related work together. Sign in to keep it across devices.
Ask one question. Get the right answer.
Start in the browser. No setup, no model picker.