Skip to main content
The Cerebras Inference API uses standard HTTP response status codes to indicate the success or failure of an API request. When errors occur, the SDK throws specific exceptions that inherit from cerebras.cloud.sdk.APIError. This documentation outlines the error types, how to handle them, and provides examples for effective error management.

​
Error Types

All errors in the Cerebras Inference API inherit from cerebras.cloud.sdk.APIError. The main categories of errors are:
  1. cerebras.cloud.sdk.APIConnectionError: The SDK raises this error when the library cannot connect to the API.
  2. cerebras.cloud.sdk.APIStatusError: The SDK raises this error when the API returns a non-success status code (4xx or 5xx).

​
HTTP Status Codes

Status CodeError Type
400BadRequestError
401AuthenticationError
402PaymentRequired
403PermissionDeniedError
404NotFoundError
413ContentTooLarge
422UnprocessableEntityError
429
500InternalServerError
503ServiceUnavailable
N/AAPIConnectionError

​
Image Input Errors

StatusConditionError Detail
413 Content Too LargeTotal image payload exceeds the configured request limit"Total request size exceeds maximum"
Number of image inputs exceeds the configured request limit"Number of image inputs exceeds maximum"
Decompressed RGB bytes exceed 350 MB for an individual image"Image decompression exceeds maximum memory limit"
400 Bad Requestimage_url.url is not a valid data: URI"Invalid image_url: expected base64 data URI"
image_url.url is an HTTPS URL"HTTPS image URLs are not supported. Use a base64-encoded data URI instead."
Base64 payload is corrupt or image cannot be decoded"Image data could not be decoded"
image_url content part on a non-user role"image_url content parts are only supported on user messages"
Image sent to a model without multimodal support"Model {model} does not support image inputs"

​
Handling Errors

Here’s an example of how to handle different types of errors: 
import cerebras.cloud.sdk
from cerebras.cloud.sdk import Cerebras

client = Cerebras()

try:
    client.chat.completions.create(
        messages=[
            {
                "role": "user",
                "content": "This should cause an error!",
            }
        ],
        model="some-model-that-doesnt-exist",
    )
except cerebras.cloud.sdk.APIConnectionError as e:
    print("The server could not be reached")
    print(e.__cause__)  # an underlying Exception, likely raised within httpx.
except cerebras.cloud.sdk.RateLimitError as e:
    print("A 429 status code was received; we should back off a bit.")
except cerebras.cloud.sdk.APIStatusError as e:
    print("Another non-200-range status code was received")
    print(e.status_code)
    print(e.response)

​
Retries

By default, the SDK automatically retries certain errors two times with a short exponential backoff. These include:
  • Connection errors
  • 408 Request Timeout
  • >= 500 Internal errors
You can configure or disable retry settings using the max_retries option: 
from cerebras.cloud.sdk import Cerebras

# Configure the default for all requests:
client = Cerebras(
    max_retries=0,  # Disable retries (default is 2)
)

# Or, configure per-request:
client.with_options(max_retries=5).chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": "Why is fast inference important?",
        }
    ],
    model="gpt-oss-120b",
)

​
Timeouts

Requests time out after 1 minute by default. You can configure this with a timeout option: 
from cerebras.cloud.sdk import Cerebras
import httpx

# Configure the default for all requests:
client = Cerebras(
    timeout=20.0,  # 20 seconds (default is 1 minute)
)

# More granular control:
client = Cerebras(
    timeout=httpx.Timeout(60.0, read=5.0, write=10.0, connect=2.0),
)

# Override per-request:
client.with_options(timeout=5.0).chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": "Why is fast inference important?",
        }
    ],
    model="gpt-oss-120b",
)
On timeout, the SDK throws an APITimeoutError. Note that the SDK retries requests that time out twice by default.