From 9d891540a0560481ad012095705ac5010ceccb7c Mon Sep 17 00:00:00 2001 From: Brendan O'Leary Date: Tue, 27 Jan 2026 06:44:15 +0100 Subject: [PATCH] Add back free and budget models page --- packages/kilo-docs/lib/nav/code-with-ai.ts | 4 + packages/kilo-docs/mappingplan.md | 60 ++-- .../agents/free-and-budget-models.md | 284 ++++++++++++++++++ packages/kilo-docs/previous-docs-redirects.js | 2 +- 4 files changed, 317 insertions(+), 33 deletions(-) create mode 100644 packages/kilo-docs/pages/code-with-ai/agents/free-and-budget-models.md diff --git a/packages/kilo-docs/lib/nav/code-with-ai.ts b/packages/kilo-docs/lib/nav/code-with-ai.ts index 96ba9713466..a2459282040 100644 --- a/packages/kilo-docs/lib/nav/code-with-ai.ts +++ b/packages/kilo-docs/lib/nav/code-with-ai.ts @@ -37,6 +37,10 @@ export const CodeWithAiNav: NavSection[] = [ href: "/code-with-ai/agents/model-selection", children: "Model Selection", }, + { + href: "/code-with-ai/agents/free-and-budget-models", + children: "Free & Budget Models", + }, ], }, { diff --git a/packages/kilo-docs/mappingplan.md b/packages/kilo-docs/mappingplan.md index 75b83bf7398..4289e29d31a 100644 --- a/packages/kilo-docs/mappingplan.md +++ b/packages/kilo-docs/mappingplan.md @@ -1,22 +1,18 @@ -This is a great exercise. Let me map everything out. - ---- - ## Mapping Existing Pages to New Structure ### Get Started -| New Item | Existing Page(s) | -| --------------------------------- | ----------------------------------------------------------------------- | -| ☑️ Introduction / Overview | `index`, `getting-started/concepts` | -| ☑️ Installation | `getting-started/installing` | -| ☑️ Quickstart | `getting-started/your-first-task` | -| ☑️ Setup & Authentication | `getting-started/setting-up`, `getting-started/connecting-api-provider` | -| ☑️ AI Providers | `basic-usage/connecting-providers`, `providers/*` (all of them) | -| Settings | `basic-usage/settings-management` | -| ☑️ Adding Credits | `basic-usage/adding-credits` | -| ☑️ FAQ | Keep if it exists | -| ☑️ Migrating from Cursor/Windsurf | `advanced-usage/migrating-from-cursor-windsurf` | +| New Item | Existing Page(s) | +| ------------------------------ | ----------------------------------------------------------------------- | +| Introduction / Overview | `index`, `getting-started/concepts` | +| Installation | `getting-started/installing` | +| Quickstart | `getting-started/your-first-task` | +| Setup & Authentication | `getting-started/setting-up`, `getting-started/connecting-api-provider` | +| AI Providers | `basic-usage/connecting-providers`, `providers/*` (all of them) | +| Settings | `basic-usage/settings-management` | +| Adding Credits | `basic-usage/adding-credits` | +| FAQ | Keep if it exists | +| Migrating from Cursor/Windsurf | `advanced-usage/migrating-from-cursor-windsurf` | --- @@ -27,9 +23,9 @@ This is a great exercise. Let me map everything out. | **Platforms** (subheader) | | | VS Code Extension | Needs new page (or pull from install) | | JetBrains Extension | Needs new page | -| ☑️ CLI | `cli` | -| ☑️ Cloud Agent | `advanced-usage/cloud-agent` (partial) | -| ☑️ Mobile Apps | Needs new page | +| CLI | `cli` | +| Cloud Agent | `advanced-usage/cloud-agent` (partial) | +| Mobile Apps | Needs new page | | Slack | `slack` | | **Working with Agents** (subheader) | | | The Chat Interface | `basic-usage/the-chat-interface` | @@ -37,6 +33,7 @@ This is a great exercise. Let me map everything out. | Using Modes | `basic-usage/using-modes` | | Orchestrator Mode | `basic-usage/orchestrator-mode` | | Model Selection | `basic-usage/model-selection-guide` | +| Free & Budget Models | `advanced-usage/free-and-budget-models` | | **Features** (subheader) | | | Autocomplete | `basic-usage/autocomplete/index`, `basic-usage/autocomplete/mistral-setup` | | Code Actions | `features/code-actions` | @@ -93,20 +90,20 @@ This is a great exercise. Let me map everything out. | New Item | Existing Page(s) | | ------------------------------ | ------------------------------------- | -| ☑️ Integrations Overview | `advanced-usage/integrations` | -| ☑️ Code Reviews | `advanced-usage/code-reviews` | -| ☑️ Agent Manager | `advanced-usage/agent-manager` | +| Integrations Overview | `advanced-usage/integrations` | +| Code Reviews | `advanced-usage/code-reviews` | +| Agent Manager | `advanced-usage/agent-manager` | | **Extending Kilo** (subheader) | | -| ☑️ Local Models | `advanced-usage/local-models` | -| ☑️ Shell Integration | `features/shell-integration` | -| ☑️ Auto-launch Configuration | `features/auto-launch-configuration` | +| Local Models | `advanced-usage/local-models` | +| Shell Integration | `features/shell-integration` | +| Auto-launch Configuration | `features/auto-launch-configuration` | | **MCP** (subheader) | | -| ☑️ MCP Overview | `features/mcp/overview` | -| ☑️ Using MCP in Kilo Code | `features/mcp/using-mcp-in-kilo-code` | -| ☑️ Using MCP in CLI | `features/mcp/using-mcp-in-cli` | -| ☑️ What is MCP | `features/mcp/what-is-mcp` | -| ☑️ Server Transports | `features/mcp/server-transports` | -| ☑️ MCP vs API | `features/mcp/mcp-vs-api` | +| MCP Overview | `features/mcp/overview` | +| Using MCP in Kilo Code | `features/mcp/using-mcp-in-kilo-code` | +| Using MCP in CLI | `features/mcp/using-mcp-in-cli` | +| What is MCP | `features/mcp/what-is-mcp` | +| Server Transports | `features/mcp/server-transports` | +| MCP vs API | `features/mcp/mcp-vs-api` | --- @@ -173,8 +170,7 @@ This is a great exercise. Let me map everything out. | `advanced-usage/auto-cleanup` | Fold into Settings | | `features/model-temperature` | Fold into Model Selection | | `advanced-usage/rate-limits-costs` | Fold into Adding Credits or AI Providers | -| `advanced-usage/free-and-budget-models` | Fold into Model Selection | -| `features/footgun-prompting` | This feels like a blog post, not docs - consider removing or moving to tips | +| `features/footgun-prompting` | Remove | | `tips-and-tricks` | Could become a blog post or fold relevant bits elsewhere | | `features/experimental/experimental-features` | Keep but maybe as a single page, not a section | | **Tools Reference (entire section)** | This is 17 pages. Consider: (1) Keep as reference section but not in main nav, (2) Link from relevant pages, (3) Auto-generate from code | diff --git a/packages/kilo-docs/pages/code-with-ai/agents/free-and-budget-models.md b/packages/kilo-docs/pages/code-with-ai/agents/free-and-budget-models.md new file mode 100644 index 00000000000..17d9c518667 --- /dev/null +++ b/packages/kilo-docs/pages/code-with-ai/agents/free-and-budget-models.md @@ -0,0 +1,284 @@ +--- +title: Free and Budget Models +description: Learn how to use Kilo Code effectively while minimizing or eliminating costs through free models, budget-friendly alternatives, and smart usage strategies. +--- + +# Free and Budget Models + +**Why this matters:** AI model costs can add up quickly during development. This guide shows you how to use Kilo Code effectively while minimizing or eliminating costs through free models, budget-friendly alternatives, and smart usage strategies. + +## Completely Free Options + +### Grok Code Fast 1 + +This frontier AI model is 100% free in Kilo Code for a limited time. [See the blog post for more details](https://blog.kilo.ai/p/grok-code-fast-get-this-frontier-ai-model-free). + +### OpenRouter Free Tier Models + +OpenRouter offers several models with generous free tiers. **Note:** You'll need to create a free OpenRouter account to access these models. + +**Setup:** + +1. Create a free [OpenRouter account](https://openrouter.ai) +2. Get your API key from the dashboard +3. Configure Kilo Code with the OpenRouter provider + +**Available free models:** + +- **Qwen3 Coder (free)** - Optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. +- **Z.AI: GLM 4.5 Air (free)** - Lightweight variant of the GLM-4.5 family, purpose-built for agent-centric applications. +- **DeepSeek: R1 0528 (free)** - Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. +- **MoonshotAI: Kimi K2 (free)** - Optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. + +## Cost-Effective Premium Models + +When you need more capability than free models provide, these options deliver excellent value: + +### Ultra-Budget Champions (Under $0.50 per million tokens) + +**Mistral Devstral Small** + +- **Cost:** ~$0.20 per million input tokens +- **Best for:** Code generation, debugging, refactoring +- **Performance:** 85% of premium model capability at 10% of the cost + +**Llama 4 Maverick** + +- **Cost:** ~$0.30 per million input tokens +- **Best for:** Complex reasoning, architecture planning +- **Performance:** Excellent for most development tasks + +**DeepSeek v3** + +- **Cost:** ~$0.27 per million input tokens +- **Best for:** Code analysis, large codebase understanding +- **Performance:** Strong technical reasoning + +### Mid-Range Value Models ($0.50-$2.00 per million tokens) + +**Qwen3 235B** + +- **Cost:** ~$1.20 per million input tokens +- **Best for:** Complex projects requiring high accuracy +- **Performance:** Near-premium quality at 40% of the cost + +## Smart Usage Strategies + +### The 50% Rule + +**Principle:** Use budget models for 50% of your tasks, premium models for the other 50%. + +**Budget model tasks:** + +- Code reviews and analysis +- Documentation writing +- Simple bug fixes +- Boilerplate generation +- Refactoring existing code + +**Premium model tasks:** + +- Complex architecture decisions +- Debugging difficult issues +- Performance optimization +- New feature design +- Critical production code + +### Context Management for Cost Savings + +**Minimize context size:** + +```typescript +// Instead of mentioning entire files +@src/components/UserProfile.tsx + +// Mention specific functions or sections +@src/components/UserProfile.tsx:45-67 +``` + +**Use Memory Bank effectively:** + +- Store project context once in [Memory Bank](/advanced-usage/memory-bank) +- Reduces need to re-explain project details +- Saves 200-500 tokens per conversation + +**Strategic file mentions:** + +- Only include files directly relevant to the task +- Use [`@folder/`](/basic-usage/context-mentions) for broad context, specific files for targeted work + +### Model Switching Strategies + +**Start cheap, escalate when needed:** + +1. **Begin with free models** (Qwen3 Coder, GLM-4.5-Air) +2. **Switch to budget models** if free models struggle +3. **Escalate to premium models** only for complex tasks + +**Use API Configuration Profiles:** + +- Set up [multiple profiles](/features/api-configuration-profiles) for different cost tiers +- Quick switching between free, budget, and premium models +- Match model capability to task complexity + +### Mode-Based Cost Optimization + +**Use appropriate modes to limit expensive operations:** + +- **[Ask Mode](/basic-usage/using-modes#ask-mode):** Information gathering without code changes +- **[Architect Mode](/basic-usage/using-modes#architect-mode):** Planning without expensive file operations +- **[Debug Mode](/basic-usage/using-modes#debug-mode):** Focused troubleshooting + +**Custom modes for budget control:** + +- Create modes that restrict expensive tools +- Limit file access to specific directories +- Control which operations are auto-approved + +## Real-World Performance Comparisons + +### Code Generation Tasks + +**Simple function creation:** + +- **Mistral Devstral Small:** 95% success rate +- **GPT-4:** 98% success rate +- **Cost difference:** Free vs $0.20 vs $30 per million tokens + +**Complex refactoring:** + +- **Budget models:** 70-80% success rate +- **Premium models:** 90-95% success rate +- **Recommendation:** Start with budget, escalate if needed + +### Debugging Performance + +**Simple bugs:** + +- **Free models:** Usually sufficient +- **Budget models:** Excellent performance +- **Premium models:** Overkill for most cases + +**Complex system issues:** + +- **Free models:** 40-60% success rate +- **Budget models:** 60-80% success rate +- **Premium models:** 85-95% success rate + +## Hybrid Approach Recommendations + +### Daily Development Workflow + +**Morning planning session:** + +- Use **Architect mode** with **DeepSeek R1** +- Plan features and architecture +- Create task breakdowns + +**Implementation phase:** + +- Use **Code mode** with **budget models** +- Generate and modify code +- Handle routine development tasks + +**Complex problem solving:** + +- Switch to **premium models** when stuck +- Use for critical debugging +- Architecture decisions affecting multiple systems + +### Project Phase Strategy + +**Early development:** + +- Free and budget models for prototyping +- Rapid iteration without cost concerns +- Establish patterns and structure + +**Production preparation:** + +- Premium models for critical code review +- Performance optimization +- Security considerations + +## Cost Monitoring and Control + +### Track Your Usage + +**Monitor credit consumption:** + +- Check cost estimates in chat history +- Review monthly usage patterns +- Identify high-cost operations + +**Set spending limits:** + +- Use provider billing alerts +- Configure [rate limits](/advanced-usage/rate-limits-costs) to control usage +- Set daily/monthly budgets + +### Cost-Saving Tips + +**Reduce system prompt size:** + +- [Disable MCP](/features/mcp/using-mcp-in-kilo-code) if not using external tools +- Use focused custom modes +- Minimize unnecessary context + +**Optimize conversation length:** + +- Use [Checkpoints](/features/checkpoints) to reset context +- Start fresh conversations for unrelated tasks +- Archive completed work + +**Batch similar tasks:** + +- Group related code changes +- Handle multiple files in single requests +- Reduce conversation overhead + +## Getting Started with Budget Models + +### Quick Setup Guide + +1. **Create OpenRouter account** for free models +2. **Configure multiple providers** in Kilo Code +3. **Set up API Configuration Profiles** for easy switching +4. **Escalate to budget models** when needed +5. **Reserve premium models** for complex work + +### Recommended Provider Mix + +**Free tier foundation:** + +- [OpenRouter](/providers/openrouter) - Free models +- [Groq](/providers/groq) - Fast inference for supported models +- [Z.ai](https://z.ai/model-api) - Provides a free model GLM-4.5-Flash + +**Budget tier options:** + +- [DeepSeek](/providers/deepseek) - Excellent value models +- [Mistral](/providers/mistral) - Specialized coding models + +**Premium tier backup:** + +- [Anthropic](/providers/anthropic) - Claude for complex reasoning +- [OpenAI](/providers/openai) - GPT-4 for critical tasks + +## Measuring Success + +**Track these metrics:** + +- Monthly AI costs vs. development productivity +- Task completion rates by model tier +- Time saved vs. money spent +- Code quality improvements + +**Success indicators:** + +- 70%+ of tasks completed with free/budget models +- Monthly costs under your target budget +- Maintained or improved code quality +- Faster development cycles + +By combining free models, strategic budget model usage, and smart optimization techniques, you can harness the full power of AI-assisted development while keeping costs minimal. Start with free options and gradually incorporate budget models as your needs and comfort with costs grow. diff --git a/packages/kilo-docs/previous-docs-redirects.js b/packages/kilo-docs/previous-docs-redirects.js index 8d6f575be16..1faf8933149 100644 --- a/packages/kilo-docs/previous-docs-redirects.js +++ b/packages/kilo-docs/previous-docs-redirects.js @@ -616,7 +616,7 @@ module.exports = [ }, { source: "/advanced-usage/free-and-budget-models", - destination: "/docs/code-with-ai/agents/model-selection", + destination: "/docs/code-with-ai/agents/free-and-budget-models", basePath: false, permanent: true, },