Your First Conversation
Send your first message in under 30 seconds.
The 30-second version
- Sign in to app.nyquest.ai
- You're on the chat screen. There's a message box at the bottom and a model picker in the header.
- Type a question. Hit Enter or tap Send.
- The reply streams in as the model produces it.
Managed paid chat uses your wallet. With an active provider and BYOK enabled, your provider bills you directly. Saving a provider key alone does not enable BYOK.
What just happened under the hood
When you hit Enter, several things ran:
- Routing — new chats start on Auto, which selects an available model for your request and account. You can choose a specific model in the header. BYOK applies only while enabled with an active provider.
- Streaming — tokens stream back one at a time over Server-Sent Events (SSE), which is why you see the reply appear word-by-word instead of all at once.
- Memory recall — if previous conversations contained relevant context, summarized chunks were passed in as additional system context.
- Cost accounting — managed chat reserves funds before dispatch and settles from recorded provider usage at catalog rates, with eligible compression credits. Missing receipts can leave settlement pending. BYOK requests are billed by your provider; they do not debit the Nyquest wallet. Check Workspace navigation → More → Usage for recorded charges.
All of this is automatic. Nothing to configure for the basic chat case.
Picking a different model
The model picker is in the header — it shows the currently active model name. Click it to open the picker.
| What you'll see | What it means |
|---|---|
| Model name + provider | e.g. gpt-4o-mini (OpenAI) |
| Input price | published input rate per million tokens, when available |
| Context size | the model's advertised context window |
| Tools / Vision badges | advertised tool or image-input support |
| Free / Go Pro labels | free models or models that require funding or BYOK |
Type to filter and pick a model. The selection applies to the current chat; starting a new chat or switching conversations resets the picker to Auto. On phones, the model remains visible in the header. Open Chat controls beside it for BYOK, DynaRAG, and Optimize.
Conversations vs messages
A conversation is a list of messages between you and the model. Signed-in conversations are saved automatically. On desktop, use the header's History button to open the conversation list. On phones, open the header's Menu drawer. The circular Workspace navigation button opens Chat, Studios, Splicer, Agents, Vault, and More.
Each conversation has its own context window. The model sees the full history of that conversation when generating each new reply, up to the model's context limit. If you start a new conversation, the model has no memory of the old one (unless memory recall pulls relevant chunks in).
How long to expect
| Scenario | Approximate latency |
|---|---|
| First-token response from a fast model | 200–600 ms |
| Full short reply (50 words) | 1–2 sec |
| Long reply (1,000+ words) | 5–15 sec |
| Reasoning model (o1, GPT-5) | 10–60+ sec |
Slower replies are normal for reasoning models — they're working through chain-of-thought.
Where to next
- Picking a Model — how to compare and choose
- Streaming — what the live token streaming actually looks like
- BYOK Setup — bring your own API keys to skip platform fees