Fala, pessoal!
Estou fazendo a aula sobre open LLM e Groq e estou recebendo erros.
**Esse é o codigo:
**
from groq import Groq
client = Groq()
completion = client.chat.completions.create(
model="openai/gpt-oss-120b",
messages=[
{
"role": "user",
"content": "What is AI? 5 words only."
}
],
temperature=1,
max_completion_tokens=8192,
top_p=1,
reasoning_effort="medium",
stream=True,
stop=None
)
for chunk in completion:
print(chunk.choices[0].delta.content or "", end="")
**E esse é o erro:
**
APIStatusError Traceback (most recent call last)
/tmp/ipykernel_6081/2444207085.py in <cell line: 0>()
2
3 client = Groq()
----> 4 completion = client.chat.completions.create(
5 model="openai/gpt-oss-120b",
6 messages=[
2 frames/usr/local/lib/python3.12/dist-packages/groq/resources/chat/completions.py in create(self, messages, model, citation_options, compound_custom, disable_tool_validation, documents, exclude_domains, frequency_penalty, function_call, functions, include_domains, include_reasoning, logit_bias, logprobs, max_completion_tokens, max_tokens, metadata, n, parallel_tool_calls, presence_penalty, reasoning_effort, reasoning_format, response_format, search_settings, seed, service_tier, stop, store, stream, temperature, tool_choice, tools, top_logprobs, top_p, user, extra_headers, extra_query, extra_body, timeout)
459 timeout: Override the client-level default timeout for this request, in seconds
460 """
--> 461 return self._post(
462 "/openai/v1/chat/completions",
463 body=maybe_transform(
/usr/local/lib/python3.12/dist-packages/groq/_base_client.py in post(self, path, cast_to, body, content, options, files, stream, stream_cls)
1282 method="post", url=path, json_data=body, content=content, files=to_httpx_files(files), **options
1283 )
-> 1284 return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
1285
1286 def patch(
/usr/local/lib/python3.12/dist-packages/groq/_base_client.py in request(self, cast_to, options, stream, stream_cls)
1069
1070 log.debug("Re-raising status error")
-> 1071 raise self._make_status_error_from_response(err.response) from None
1072
1073 break
APIStatusError: Error code: 413 - {'error': {'message': 'Request too large for model openai/gpt-oss-120b in organization org_01kqmve7mgf22rbrg1ehrgnd0h service tier on_demand on tokens per minute (TPM): Limit 8000, Requested 8272, please reduce your message size and try again. Need more tokens? Upgrade to Dev Tier today at https://console.groq.com/settings/billing', 'type': 'tokens', 'code': 'rate_limit_exceeded'}}
**Detalhe:
**
Acontece o mesmo erro, com o mesmo codigo no Colab e no Playground do Groq.
Alguma ideia da causa e solução?
Abraço!
