docs: add Auto Efficient tier to Auto Model documentation

This commit is contained in:
kiloconnect[bot]
2026-06-18 15:11:38 +00:00
parent b930a19b7b
commit c18baae9ca
2 changed files with 12 additions and 2 deletions
@@ -11,6 +11,7 @@ Auto Model is a smart routing system that selects an underlying model for each r
|---|---|---|
| `kilo-auto/frontier` | Maximum capability with the best available models | Paid |
| `kilo-auto/balanced` | Strong performance at a lower cost | Paid |
| `kilo-auto/efficient` | Lowest cost per task, with capability matched to difficulty | Paid |
| `kilo-auto/free` | The best free models available | Free |
## How It Works
@@ -31,8 +32,17 @@ The underlying models behind each Auto Model tier are updated server-side as bet
- **Frontier** — Routes to the latest and most capable paid models. Uses different models for reasoning-heavy tasks (planning, architecture, debugging) versus implementation tasks (coding, building, exploring), pairing the right capability to each type of work.
- **Balanced** — Routes to a cost-effective model for all modes. The specific model is selected based on the API interface in use, but does not vary by mode. A good default for most developers who want strong AI assistance without paying frontier prices.
- **Efficient** — Session-aware routing that classifies the difficulty of each request in real time and routes it to the cheapest model proven accurate enough for that task, based on Kilo's continuously-run benchmarks. Routine work stays lean while harder tasks get a more capable model. Because it watches your session in context, it keeps using a model across related turns and only switches when a cheaper option is clearly worth it. If a routing decision can't be made, it falls back to the Balanced tier, so quality never drops below Balanced.
- **Free** — Routes to the best available free models on OpenRouter, splitting traffic across them. Because free model availability shifts over time as providers change promotional periods, the mapping is updated server-side — you always get the best free option without having to track what's currently available. Quality will be lower than paid tiers, and the models may change over time.
### How Auto Efficient routing works
1. Kilo observes your coding session in context
2. It classifies each task by complexity
3. It routes to the benchmark-proven best model for that task automatically
You get lean costs on routine work and stronger models when the work demands it — with no manual switching.
{% callout type="warning" title="Data handling for Auto Free" %}
Auto Free may route your requests to providers that log prompts and outputs and use them to improve their services. Do not submit personal or confidential data when using Auto Free. In particular, it may route to NVIDIA's free endpoints.
@@ -51,7 +61,7 @@ No need to manually switch models when changing modes. Auto Model handles routin
### Flexible Cost Control
Pick the tier that fits your budget. Frontier gives you the best models for demanding work; Balanced offers capable models at a fraction of the cost; Free costs nothing.
Pick the tier that fits your budget. Frontier gives you the best models for demanding work; Balanced offers capable models at a fraction of the cost; Efficient minimizes cost per task by matching model capability to task difficulty; Free costs nothing.
## Requirements
@@ -60,7 +60,7 @@ While the specifics change constantly, some principles stay consistent:
## Free and Budget Model Picks
You don't need a paid API key to use Kilo Code productively. The fastest way to start for free is [Auto Model Free](/docs/code-with-ai/agents/auto-model) (`kilo-auto/free`), which routes to the best available free models automatically. See [Using Kilo for Free](/docs/getting-started/using-kilo-for-free) for the full zero-cost setup.
You don't need a paid API key to use Kilo Code productively. For the lowest cost on paid work, [Auto Efficient](/docs/code-with-ai/agents/auto-model#tiers) (`kilo-auto/efficient`) routes each request to the cheapest model proven accurate enough for that task. The fastest way to start for free is [Auto Model Free](/docs/code-with-ai/agents/auto-model) (`kilo-auto/free`), which routes to the best available free models automatically. See [Using Kilo for Free](/docs/getting-started/using-kilo-for-free) for the full zero-cost setup.
If you prefer to pick models yourself, type `free` in the model picker to filter by free models, or browse the full list at [kilo.ai/models](https://kilo.ai/models).