Ssylphx.ai
Models

The four models

One engine, four selection policies. Every Lumen tier reads the same request, scores the same internal lanes, and picks a seat — what you choose is how far it will spend for quality.

One engine. Four points on the curve.

Same router, same lanes, same learning ledger, on every tier — a tier is a selection policy over that identical, already-scored slate. Read left to right: cost-optimized to quality-ceiling. On an easy request all four may still pick the same lane, and that's the design working.

  1. 1

    Glow

    max_passes 2

    Thrift budget. Same engine, tighter deepen allowance.

    sylphx/glow
    Built forHigh-volume, interactive surfaces, bulk light work
    Selection policyRuns the shared executor + internal menu; spends deepen passes sparingly.
    Escalation speedTight max_passes — answers in one executor call unless the budget buys deepen.
  2. 2

    Lumen

    Defaultmax_passes 3

    The default. Balanced deepen budget.

    sylphx/lumen
    Built forEveryday agent work
    Selection policySame capability menu as Glow and Flare; mid budget for deepen passes.
    Escalation speedBalanced max_passes for routine agentic sessions.
  3. 3

    Flare

    max_passes 4

    Higher willingness to spend time on hard turns.

    sylphx/flare
    Built forHarder agent work, research, decisions that matter
    Selection policySame menu and seats as Glow/Lumen; highest cold-start max_passes.
    Escalation speedHighest max_passes — more room to deepen when needed.

Choosing a tier

Full capability — vision, tools, streaming, English and 中文 — is on every tier. You are choosing a quality ceiling, not a feature set.

  • Latency-sensitive UI or cost-sensitive volumeGlow
  • Not sure which tier you needLumen
  • You want more deepen budget on difficult workFlare

Certified, not claimed

Tier order isn't asserted once and left alone — it's checked continuously against production evidence.

Flash ≤ Standard ≤ Pro ≤ Ultra in judged quality is verified from real duels on live traffic, every day. If two neighbors ever stop separating beyond noise, they merge — four is a hypothesis the data has to keep earning, not doctrine.

See the full certification ladder and daily trajectory