How to Test Claude API & Models Endpoint

curl -s -X GET "https://api.anthropic.com/v1/models" \  -H "x-api-key: ${ANTHROPIC_API_KEY}" \  -H "anthropic-version: 2023-06-01"

{  "data": [    {      "type": "model",      "id": "claude-3-5-sonnet-20241022",      "display_name": "Claude 3.5 Sonnet",      "created_at": "2024-10-22T00:00:00Z"    },    {      "type": "model",      "id": "claude-3-5-haiku-20241022",      "display_name": "Claude 3.5 Haiku",      "created_at": "2024-10-22T00:00:00Z"    }  ],  "has_more": false,  "first_id": "claude-3-5-sonnet-20241022",  "last_id": "claude-3-5-haiku-20241022"}

import osimport sysimport timefrom dotenv import load_dotenvimport anthropicfrom anthropic import Anthropic, RateLimitError, InternalServerError, APIConnectionError, APIStatusErrorload_dotenv()api_key = os.environ.get("ANTHROPIC_API_KEY")if not api_key:    print("Error: ANTHROPIC_API_KEY environment variable is not set.")    sys.exit(1)client = Anthropic(api_key=api_key)def check_models():    """Query model inventory via client.models.list()."""    print("Probing models catalog...")    start_time = time.perf_counter()    try:        page = client.models.list(limit=20)        duration_ms = (time.perf_counter() - start_time) * 1000        print(f"Models probe successful: {len(page.data)} models discovered ({duration_ms:.2f} ms).")        return True    except RateLimitError as exc:        print(f"Rate limited (HTTP 429): {exc.message}")        return False    except InternalServerError as exc:        print(f"Anthropic Overloaded/Internal error (HTTP {exc.status_code}): {exc.message}")        return False    except APIConnectionError as exc:        print(f"Network connectivity error: {exc}")        return False    except APIStatusError as exc:        print(f"API returned status {exc.status_code}: {exc.message}")        return Falsedef check_latency(model: str = "claude-3-5-haiku-20241022"):    """Measure single-token completion latency."""    print(f"Probing message inference latency against {model}...")    start_time = time.perf_counter()    try:        response = client.messages.create(            model=model,            max_tokens=1,            messages=[{"role": "user", "content": "ping"}],        )        duration_ms = (time.perf_counter() - start_time) * 1000        print(f"Inference probe successful in {duration_ms:.2f} ms (Usage: {response.usage.input_tokens} input, {response.usage.output_tokens} output tokens).")        return True    except RateLimitError as exc:        print(f"Rate limited during inference probe: {exc.message}")        return False    except InternalServerError as exc:        print(f"Anthropic capacity error: {exc.message}")        return False    except APIConnectionError as exc:        print(f"Socket connection failure: {exc}")        return Falseif __name__ == "__main__":    models_healthy = check_models()    latency_healthy = check_latency()    if models_healthy and latency_healthy:        print("All connectivity probes passed.")        sys.exit(0)    else:        print("Connectivity probes failed.")        sys.exit(1)

import Anthropic from "@anthropic-ai/sdk";import * as dotenv from "dotenv";dotenv.config();const apiKey = process.env.ANTHROPIC_API_KEY;if (!apiKey) {  console.error("Error: ANTHROPIC_API_KEY environment variable is missing.");  process.exit(1);}const client = new Anthropic({ apiKey });async function verifyModels(): Promise {  const start = performance.now();  try {    const response = await client.models.list({ limit: 20 });    const elapsed = performance.now() - start;    console.log(`Retrieved ${response.data.length} models in ${elapsed.toFixed(2)} ms.`);    return true;  } catch (err: unknown) {    if (err instanceof Anthropic.RateLimitError) {      console.error(`Rate limit exceeded (HTTP 429): ${err.message}`);    } else if (err instanceof Anthropic.InternalServerError) {      console.error(`Server overloaded or unavailable (HTTP ${err.status}): ${err.message}`);    } else if (err instanceof Anthropic.APIConnectionError) {      console.error(`Connection handshake failed: ${err.message}`);    } else {      console.error(`API probe failed: ${err}`);    }    return false;  }}async function verifyLatency(model = "claude-3-5-haiku-20241022"): Promise {  const start = performance.now();  try {    const message = await client.messages.create({      model,      max_tokens: 1,      messages: [{ role: "user", content: "ping" }],    });    const elapsed = performance.now() - start;    console.log(`Latency probe succeeded in ${elapsed.toFixed(2)} ms. Tokens: in=${message.usage.input_tokens}, out=${message.usage.output_tokens}`);    return true;  } catch (err: unknown) {    if (err instanceof Anthropic.RateLimitError) {      console.error(`Rate limit encountered during ping: ${err.message}`);    } else if (err instanceof Anthropic.InternalServerError) {      console.error(`Upstream service issue (HTTP ${err.status}): ${err.message}`);    } else {      console.error(`Ping probe error: ${err}`);    }    return false;  }}async function run() {  const modelsOk = await verifyModels();  const latencyOk = await verifyLatency();  if (modelsOk && latencyOk) {    console.log("All systems operational.");    process.exit(0);  }  process.exit(1);}run();