BerriAI/litellm · warning · Exception

Promptlayer did not successfully log the response!

Error message

Promptlayer did not successfully log the response!

What it means

After POSTing a track-request payload to api.promptlayer.com, PromptLayer raises a generic Exception whenever the response JSON lacks success: true. This means the request reached PromptLayer but was rejected (auth, malformed body, or server-side failure) — it is not a network error, the HTTP layer succeeded.

Source

Thrown at litellm/integrations/prompt_layer.py:66

                "https://api.promptlayer.com/rest/track-request",
                json={
                    "function_name": "openai.ChatCompletion.create",
                    "kwargs": new_kwargs,
                    "tags": tags,
                    "request_response": dict(response_obj),
                    "request_start_time": int(start_time.timestamp()),
                    "request_end_time": int(end_time.timestamp()),
                    "api_key": self.key,
                    # Optional params for PromptLayer
                    # "prompt_id": "<PROMPT ID>",
                    # "prompt_input_variables": "<Dictionary of variables for prompt>",
                    # "prompt_version":1,
                },
            )

            response_json: Final = request_response.json()
            if not request_response.json().get("success", False):
                raise Exception("Promptlayer did not successfully log the response!")

            print_verbose(f"Prompt Layer Logging: success - final response object: {request_response.text}")

            if "request_id" in response_json:
                if metadata:
                    response: Final = litellm.module_level_client.post(
                        "https://api.promptlayer.com/rest/track-metadata",
                        json={
                            "request_id": response_json["request_id"],
                            "api_key": self.key,
                            "metadata": metadata,
                        },
                    )
                    print_verbose(f"Prompt Layer Logging: success - metadata post response object: {response.text}")

        except Exception:
            print_verbose(f"error: Prompt Layer Error - {traceback.format_exc()}")

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Verify PROMPTLAYER_API_KEY is the correct active key for the same workspace as any prompt ids used
2. Log request_response.text just before the raise (or reproduce the POST in curl) to see PromptLayer's actual error message
3. Remove unsupported optional fields (prompt_id / prompt_input_variables) from the payload and retry
4. If the failure is transient, wrap the call and retry once with backoff

Example fix

# before
response_json = request_response.json()
if not request_response.json().get("success", False):
    raise Exception("Promptlayer did not successfully log the response!")

# after — surface the upstream reason
if not response_json.get("success", False):
    raise Exception(
        f"PromptLayer logging failed (status={request_response.status_code}): "
        f"{response_json.get('message', request_response.text)}"
    )

import litellm
import os

assert os.getenv("PROMPTLAYER_API_KEY"), "PROMPTLAYER_API_KEY missing — PromptLayer logging will fail"

for attempt in range(2):
    try:
        resp = litellm.completion(model="gpt-4o", messages=msgs)
        break
    except Exception as e:
        if "Promptlayer did not successfully log" in str(e) and attempt == 0:
            continue  # transient PromptLayer rejection — retry once
        raise

When it happens

Trigger: Calling litellm with the prompt_layer callback while PROMPTLAYER_API_KEY is wrong/expired (key sent in the JSON body); prompt template references (prompt_id, prompt_input_variables) that do not match the account; PromptLayer API returning success: false for schema violations.

Common situations: Rotated or typo'd PromptLayer API keys; using a prompt id from a different workspace; PromptLayer API changes or transient 4xx/5xx that still return JSON with success false.

Related errors

• start_time is required, got={start_time} of type {type(start
• end_time is required, got={end_time} of type {type(end_time)
• usage is required, got={usage} of type {type(usage)}
• logging_obj is required
• logging_obj is required

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/24b2787f21deff78. Report an issue: GitHub.