Skip to main content
The Deepshi API uses standard HTTP status codes. Errors return a JSON body with an error object describing what went wrong. 
{
  "error": {
    "message": "budget exceeded",
    "type": "insufficient_quota",
    "code": "402"
  }
}

​
Status codes

StatusMeaningWhat to do
200 OKSuccessNothing to do.
400 Bad RequestMalformed request, or a model id that doesn’t exist in the catalogCheck your JSON body and that model is a valid catalog id.
401 UnauthorizedMissing, malformed, or unknown API keyVerify the Authorization: Bearer sk-bf-... header.
402 Payment RequiredOut of creditsTop up your balance.
403 ForbiddenKey revoked, or not allowed to use the requested modelUse an active key and a model your account can access.
429 Too Many RequestsRate limit exceededBack off and retry with exponential backoff.
5xxTemporary server errorRetry with backoff.
A real model your key isn’t permitted to use returns 403. A model id that doesn’t exist in the catalog returns 400, not 403 or 404.

​
Handling errors in code

Retry transient failures (429 and 5xx) with exponential backoff, and surface the others to the user: 
import time
from openai import OpenAI, APIStatusError

client = OpenAI(base_url="https://api.deepshi.ai/v1", api_key="sk-bf-...")

def chat_with_retry(messages, retries=3):
    for attempt in range(retries):
        try:
            return client.chat.completions.create(
                model="deepshi-3.0", messages=messages,
            )
        except APIStatusError as e:
            if e.status_code in (429, 500, 502, 503) and attempt < retries - 1:
                time.sleep(2 ** attempt)   # backoff
                continue
            raise
Don’t retry 400, 401, 402, or 403. They won’t succeed on retry. Fix the request, key, balance, or model access instead.