Перейти к содержимому
TakoAPI
Назад к навыкам

api-benchmark

от polarjunction

Coding Agents & IDEs
—Ещё нет оценок
Ваша оценка

Кратко

Benchmark token generation speed across multiple LLM API providers.

Описание

Что делает этот навык

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.

Когда его использовать

  • 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

Пример сценария

ВВОД

User asks: Compare token generation speed across all configured providers

АГЕНТ
  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

ВЫВОД

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

Требования

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

Установка

clawhub install polarjunction/api-benchmark

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки