Spaces:
Running
Running
File size: 1,949 Bytes
0ba585f db83b53 0ba585f db83b53 0ba585f db83b53 0ba585f db83b53 0ba585f db83b53 0ba585f db83b53 0ba585f db83b53 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 | """Test Cerebras API key directly."""
import os
import httpx
from openai import AsyncOpenAI
CEREBRAS_API_KEY = "csk-2ewy2h26eeph4yex94kmjnfwwx35pdpyyxkv3j6wcj4cxc3t"
CEREBRAS_BASE_URL = "https://api.cerebras.ai/v1"
async def test_models_list():
"""Test listing models."""
print("=== Testing /v1/models ===")
async with httpx.AsyncClient() as client:
try:
response = await client.get(
f"{CEREBRAS_BASE_URL}/models",
headers={"Authorization": f"Bearer {CEREBRAS_API_KEY}"},
timeout=10.0,
)
print(f"Status: {response.status_code}")
print(f"Response: {response.text[:800]}")
except Exception as e:
print(f"Error: {e}")
async def test_chat():
"""Test a chat completion."""
print("\n=== Testing /v1/chat/completions ===")
client = AsyncOpenAI(
api_key=CEREBRAS_API_KEY,
base_url=CEREBRAS_BASE_URL,
timeout=httpx.Timeout(60.0),
)
models_to_try = [
"qwen-3-235b-a22b-instruct-2507",
"zai-glm-4.7",
"gpt-oss-120b",
"llama3.1-8b",
]
for model in models_to_try:
print(f"\nTrying model: {model}")
try:
response = await client.chat.completions.create(
model=model,
messages=[{"role": "user", "content": "hi"}],
max_tokens=20,
)
print(f"Success!")
print(f"Model: {response.model}")
print(f"Content: {response.choices[0].message.content}")
break
except Exception as e:
error_text = str(e)
if hasattr(e, "response") and e.response:
error_text = e.response.text
print(f"Error: {error_text[:300]}")
async def main():
await test_models_list()
await test_chat()
if __name__ == "__main__":
import asyncio
asyncio.run(main())
|