TokenRoute — Hybrid Token-Efficient Routing Agent

Created by team Asad on July 07, 2026
Anthropic Claude
Hybrid Token-Efficient Routing Agent

TokenRoute handles all eight Track 1 categories (factual, math, sentiment, summarization, NER, code debugging, logic, code generation). A deterministic local classifier assigns each task a category with no API call, then a per-category policy selects a Fireworks model and a tight output cap: Gemma-4-26B-MoE for easy tasks, Gemma-4-31B for math and logic, Kimi-K2.7-Code for code, and MiniMax-M3 as a last-resort escalation. Token efficiency comes from terse system prompts, capped completions, a single call per task, and zero-token local classification. The agent is containerized for linux/amd64, reads ALLOWED_MODELS, FIREWORKS_API_KEY, and FIREWORKS_BASE_URL from the environment at runtime, and runs deterministically at temperature 0.

Category tags:
GithubPresentationDemo
Explore more applications

Thymus

Thymus is a lightweight hybrid token-efficient router designed to maximize accuracy while minimizing token costs in multi‑task LLM pipelines. It dynamically routes user queries across local and remote models on LLM providers.

The Disappointer

HuggingFace HubLLaMAAMD Developer Cloud
Vercel
application badge

AI Classroom Edge Intelligence

A privacy-first classroom AI platform that routes sensitive work to local edge systems and eligible anonymized analysis to Fireworks AI, helping teachers make faster, safer instructional decisions even with unreliable internet.

AI Classroom Edge

AMD Developer CloudQwen3rest apiGithub CopilotCodexChatGPT

Taskly: Smart Multi-Model Task Router

Taskly classifies incoming tasks into 8 categories (QA, math, code, NLP) and routes each to the optimal Fireworks AI model with a tuned prompt — maximizing accuracy while minimizing token usage in a fully Dockerized pipeline.

RuntimeTerror

AMD Developer CloudAMD ROCm
Streamlit
application badge

router_007_v3

router_007_v2 is a Track 1 agent that records **zero billable tokens**: every answer is computed inside the container by a Qwen2.5-7B-Instruct model bundled in the Docker image and served in-process with llama-cpp-python

roc_auc_half

Claude CodeChatGPTAMD ROCmAMD Developer CloudCodexGemmaGPT-5NVIDIAQwen3

Lexyprep

Agent knows how to make thorough legal research based on my experience of winning legal cases. It understands your issue and advises on procedure

Lexyprep - Do you have a case

AMD Developer CloudAMD ROCmCodexGemma