The source behind the leaderboard: model IDs, pricing fields, context length, supported parameters, and update feeds.
The leaderboard needs primary model-router metadata, and this is the source that keeps prices, context windows, and model fields grounded.
OpenRouter data turns tokenmaxxing into a comparison problem: which model, price, context window, and route make sense for a given workload?
Use it for pricing and model catalog claims, while keeping public router usage clearly labeled as router-specific rather than global model volume.
BerriAI/litellm
An OpenAI-compatible gateway and SDK for calling many model providers with budgets, logging, load balancing, guardrails, and cost tracking.
langfuse/langfuse
Open-source LLM engineering platform for observability, traces, metrics, evals, prompt management, datasets, and playground workflows.
openai/tiktoken
A fast BPE tokenizer for OpenAI models, useful for counting and estimating token usage before requests go out.
OpenRouter's public app/agent leaderboard briefly put Hermes Agent at #1, illustrating how token-based usage dashboards can steer attention in the agent boom.
Anthropic ties higher Claude Code and API limits to new compute capacity, making capacity itself part of the agent-product story.
Public model metadata, download counts, likes, and tags can support an open-model momentum board.