LaunchKit · 2026
Back to Skills

api-benchmark

Benchmark token generation speed across multiple LLM API providers.

0
0 downloads
by @polarjunction

Setup & Installation

openclaw skills install @polarjunction/api-benchmark

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install api-benchmark

What This Skill Does

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.

When to use it

  • 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

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Compare token generation speed across all configured providers

AGENT
  1. 1Reads provider definitions from ~/.openclaw/openclaw.json
  2. 2Runs preflight connectivity check on all targets
  3. 3Sends short, medium, and long prompts to each provider
  4. 4Records TTFT, TPS, and total time per run
  5. 5Outputs results as a formatted comparison table
OUTPUT

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

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

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