Aller au contenu
TakoAPI
Retour aux skills

api-benchmark

par polarjunction

Coding Agents & IDEs
—Pas encore noté
Ta note

Résumé

Benchmark token generation speed across multiple LLM API providers.

Description

Ce que fait ce skill

Benchmarks token generation speed across multiple LLM API providers by measuring TTFT, tokens-per-second throughput, and total generation time. Configuration is read from ~/.openclaw/openclaw.json, with support for anthropic-messages, openai-completions, and openai-responses API formats.

Measures TTFT separately from total generation time, giving a more accurate picture of perceived latency than simple end-to-end timing scripts.

Quand l'utiliser

  • Comparing TTFT between OpenAI and Anthropic for a latency-sensitive app
  • Verifying a new API key and endpoint are reachable before deploying
  • Measuring throughput differences between two versions of the same model
  • Checking whether a self-hosted LLM endpoint matches a hosted provider's speed
  • Running repeated benchmark runs to catch API performance regressions

Exemple de workflow

ENTRÉE

User asks: Compare token generation speed across all configured providers

AGENT
  1. 1

    Reads provider definitions from ~/.openclaw/openclaw.json

  2. 2

    Runs preflight connectivity check on all targets

  3. 3

    Sends short, medium, and long prompts to each provider

  4. 4

    Records TTFT, TPS, and total time per run

  5. 5

    Outputs results as a formatted comparison table

SORTIE

Table showing TTFT, tokens/sec, and total time for each configured provider and model

Prérequis

  • API keys for each LLM provider to benchmark (e.g., ANTHROPIC_API_KEY, OPENAI_API_KEY)

Installation

clawhub install polarjunction/api-benchmark

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens