Skip to main content
GET
https://api.cerebras.ai
/
v1
/
batches
/
{batch_id}
/
results
from cerebras.cloud.sdk import Cerebras
import os

client = Cerebras(
    api_key=os.environ.get("CEREBRAS_API_KEY"),
)

results = client.batches.retrieve_results("batch_123")

print(results)

{"custom_id":"req-001","status":"succeeded","response":{"id":"cmpl_1","object":"chat.completion","created":1699999999,"model":"llama-3.3-70b","choices":[{"index":0,"message":{"role":"assistant","content":"..."},"finish_reason":"stop"}],"usage":{"prompt_tokens":120,"completion_tokens":80,"total_tokens":200}}}
{"custom_id":"req-002","status":"failed","error":{"code":"invalid_request","message":"Prompt length exceeds model limit."}}
{"custom_id":"req-003","status":"expired","error":{"code":"timeout","message":"Batch expired before this request completed."}}
Downloads the output JSONL file containing results for all requests in the batch. This endpoint is only available once the batch job is complete or the 24-hour processing window has elapsed.

​
Path Parameters

​
batch_id
string
required
The ID of the batch job whose results to retrieve.

​
Response

The response is a JSONL file where each line contains the result for a single request. Each line includes:
​
custom_id
string
The unique identifier from the input request.
​
status
string
The status of the individual request. Possible values: succeeded, failed, expired.
​
response
object
The completion response object (only present for successful requests).
​
error
object
Error information (only present for failed or expired requests).
Results are only available once the batch job is complete or the 24-hour processing window has elapsed. Results are retained for 7 days (configurable for enterprise customers).
from cerebras.cloud.sdk import Cerebras
import os

client = Cerebras(
    api_key=os.environ.get("CEREBRAS_API_KEY"),
)

results = client.batches.retrieve_results("batch_123")

print(results)

{"custom_id":"req-001","status":"succeeded","response":{"id":"cmpl_1","object":"chat.completion","created":1699999999,"model":"llama-3.3-70b","choices":[{"index":0,"message":{"role":"assistant","content":"..."},"finish_reason":"stop"}],"usage":{"prompt_tokens":120,"completion_tokens":80,"total_tokens":200}}}
{"custom_id":"req-002","status":"failed","error":{"code":"invalid_request","message":"Prompt length exceeds model limit."}}
{"custom_id":"req-003","status":"expired","error":{"code":"timeout","message":"Batch expired before this request completed."}}