Skip to content
Agent

Models & routing

Auto-routing across providers, quality bias, and pinning a specific model.


The model chip in the agent input footer controls which model answers. The default is auto: Mel routes each turn to the best model for the job across every configured provider — Anthropic, OpenAI, Gemini, Groq, DeepSeek, and Moonshot — without you thinking about it.

How auto routing works

auto is an instant heuristic router, not another model call. It classifies your turn in microseconds from cheap signals — prompt length, code and agentic cues, reasoning cues, context size — into a tier:

TierTypical turn
TrivialQuick questions, one-liners
Simple codingSmall edits, straightforward scripts
Complex codingMulti-file changes, real builds
ReasoningHard analysis, tricky debugging
Huge contextVery large conversations or inputs

Each tier maps to the best available model for it, so there's no routing latency before your answer starts streaming. The chip updates to auto → <model> once a turn routes, and the usage summary records the routed model plus a "why this model" line.

Bias: a ceiling, not a pin

In the picker's auto submenu you can bias the router:

  • Responsive — balances quality, speed, and cost. The default.
  • Cost-efficient — prefers the cheapest capable model; escalates only when it has to.
  • Genius — escalates to the strongest model when the task is hard, while still using fast, cheap models for simple turns.

The bias raises or lowers the router's *ceiling* — it never pins one model for every turn. Genius does not mean "always the biggest model"; it means the hard turns are allowed to reach it.

Picking a model explicitly

Click the model chip (or type /model in the conversation) to open the picker. Models are grouped by provider, each with a brand monogram, and hovering a model shows its Model Specs card — intelligence, speed, and cost bars plus its context window. Select a model to pin it for the conversation; pick an auto tier to go back to routing. Your selection persists.

Reasoning levels

Models that support an adjustable reasoning effort (the OpenAI o-series) get a reasoning submenu — Low / Medium / High / XHigh. The level is only sent to models that actually support it.

Vision routing

When your turn includes image attachments, routing guarantees a model that can see them:

  • auto routes to a vision-capable model, and any failover stays vision-capable — attachments are never silently dropped.
  • A pinned model without vision is upgraded to a vision model for that turn, announced in the transcript's router info.
  • If no vision-capable provider is available, the turn fails with a clear error instead of ignoring your images.

For the wire-level routing contract, see Agent streaming.