docs(kilo-docs): update Auto Balanced docs to reflect Qwen 3.6 Plus

Update all three docs files that reference the balanced tier model mappings
to reflect the switch from Kimi K2.5 / Minimax M2.7 to Qwen 3.6 Plus.
This commit is contained in:
Josh Lambert
2026-04-09 11:56:27 -04:00
parent ee332b4ec2
commit f3ce67fa26
3 changed files with 20 additions and 26 deletions
@@ -45,29 +45,23 @@ That's it. No configuration needed.
## Auto Balanced
`kilo-auto/balanced` follows the same mode-based routing structure as Frontier but uses more cost-effective modelsKimi K2.5 for reasoning-heavy modes and Minimax M2.7 for implementation modes.
`kilo-auto/balanced` follows the same mode-based routing structure as Frontier but uses a more cost-effective model — Qwen 3.6 Plus across all modes.
### Mode-to-Model Mapping
| Mode | Model Used | Best For |
| -------------- | ------------ | ---------------------------- |
| `architect` | Kimi K2.5 | System design, planning |
| `orchestrator` | Kimi K2.5 | Multi-step task coordination |
| `ask` | Kimi K2.5 | Questions, explanations |
| `plan` | Kimi K2.5 | Planning, reasoning |
| `general` | Kimi K2.5 | General assistance |
| `debug` | Kimi K2.5 | Debugging and fixing issues |
| `code` | Minimax M2.7 | Writing and editing code |
| `build` | Minimax M2.7 | Implementation tasks |
| `explore` | Minimax M2.7 | Codebase exploration |
| Mode | Model Used | Best For |
| -------------- | ------------- | ---------------------------- |
| `architect` | Qwen 3.6 Plus | System design, planning |
| `orchestrator` | Qwen 3.6 Plus | Multi-step task coordination |
| `ask` | Qwen 3.6 Plus | Questions, explanations |
| `plan` | Qwen 3.6 Plus | Planning, reasoning |
| `general` | Qwen 3.6 Plus | General assistance |
| `debug` | Qwen 3.6 Plus | Debugging and fixing issues |
| `code` | Qwen 3.6 Plus | Writing and editing code |
| `build` | Qwen 3.6 Plus | Implementation tasks |
| `explore` | Qwen 3.6 Plus | Codebase exploration |
**Planning and reasoning tasks** use Kimi K2.5, a strong open-weight reasoning model from Moonshot AI.
**Implementation tasks** use Minimax M2.7, which provides fast, capable code generation at a fraction of frontier model costs.
{% callout type="info" title="Image support" %}
Auto Balanced does not support image inputs, since Minimax M2.7 does not have vision capabilities.
{% /callout %}
**All tasks** use Qwen 3.6 Plus, a strong multimodal reasoning model with 1M context window, fast code generation, and vision capabilities — at a fraction of frontier model costs.
## Benefits
@@ -52,7 +52,7 @@ For the current mode-to-model mappings, see the [Auto Model user docs](/docs/cod
**Who it's for**: Cost-conscious developers who want better results than free models at a fraction of frontier cost.
**What it does**: Follows the same mode-based routing structure as Frontier but uses cost-effective open-weight models for both reasoning and implementation tasks.
**What it does**: Follows the same mode-based routing structure as Frontier but uses Qwen 3.6 Plus — a cost-effective multimodal model with strong reasoning and coding capabilities — across all modes.
**Pricing**: Paid, but significantly cheaper than Frontier.
@@ -80,13 +80,13 @@ Routes to the most capable paid models optimizing for cost, performance, and cap
### `kilo-auto/balanced`
Follows the same mode-based routing as Frontier but uses more cost-effective models.
Follows the same mode-based routing as Frontier but uses a more cost-effective model.
| Mode | Resolved Model |
| -------------------------------------------------------------- | ---------------------- |
| `plan`, `general`, `architect`, `orchestrator`, `ask`, `debug` | `moonshotai/kimi-k2.5` |
| `build`, `explore`, `code` | `minimax/minimax-m2.7` |
| Default (no mode specified) | `minimax/minimax-m2.7` |
| Mode | Resolved Model |
| -------------------------------------------------------------- | ------------------- |
| `plan`, `general`, `architect`, `orchestrator`, `ask`, `debug` | `qwen/qwen3.6-plus` |
| `build`, `explore`, `code` | `qwen/qwen3.6-plus` |
| Default (no mode specified) | `qwen/qwen3.6-plus` |
### `kilo-auto/free`