| license: apache-2.0 | |
| language: en | |
| tags: | |
| - agentic-ai | |
| - llm-routing | |
| - model-selection | |
| - cost-optimization | |
| - multi-provider | |
| pipeline_tag: any-to-any | |
| # AIF-Router | |
| **Intelligent Model Selection Engine** — Routes requests across 10+ LLM providers with quality-aware optimization and automatic fallback chains. | |
| ## 10+ Providers | |
| The Router maintains up-to-date profiles for all supported providers including cost per 1K tokens, average latency, health status, and capability matrix. | |
| ## Routing Strategy | |
| 1. **Capability Match**: Filter providers by required features (vision, function calling, streaming) | |
| 2. **Quality Scoring**: Weight by benchmark performance for the task type | |
| 3. **Cost Optimization**: Select cheapest provider meeting quality threshold | |
| 4. **Latency Budget**: Enforce max latency constraints | |
| 5. **Fallback Chain**: Pre-configured cascade on failure (3+ deep) | |
| ## Provider Profiles | |
| Each provider carries: | |
| - **Health**: Current availability and error rate | |
| - **Cost**: Input/output pricing per 1K tokens | |
| - **Latency**: P50/P95/P99 response times | |
| - **Capabilities**: Vision, tools, streaming, JSON mode | |
| - **Quality**: Task-specific benchmark scores | |
| ## Repository | |
| [https://github.com/frostyjay7813/AIF](https://github.com/frostyjay7813/AIF) | |