langgenius/dify · error · ProviderNotInitializeError

provider_not_initialize

provider_not_initialize

Error message

No valid model provider credentials found. Please go to Settings -> Model Provider to complete your provider credentials.

What it means

Raised by CompletionApi.post (HTTP 400, error_code 'provider_not_initialize') when core.errors.error.ProviderTokenNotInitError is thrown during generation. The app references a model provider whose API credentials have not been configured (or were cleared) in Settings -> Model Provider. The exception's description is forwarded to the client.

Source

Thrown at api/controllers/console/explore/completion.py:134

                session=session,
                app_model=app_model,
                user=current_user,
                args=args,
                invoke_from=InvokeFrom.EXPLORE,
                streaming=streaming,
            )

            # response-contract:ignore compact_generate_response
            return helper.compact_generate_response(response)
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
        except services.errors.conversation.ConversationCompletedError:
            raise ConversationCompletedError()
        except services.errors.app_model_config.AppModelConfigBrokenError:
            logger.exception("App model config broken.")
            raise AppUnavailableError()
        except ProviderTokenNotInitError as ex:
            raise ProviderNotInitializeError(ex.description)
        except QuotaExceededError:
            raise ProviderQuotaExceededError()
        except ModelCurrentlyNotSupportError:
            raise ProviderModelCurrentlyNotSupportError()
        except InvokeError as e:
            raise CompletionRequestError(e.description)
        except ValueError as e:
            raise e
        except Exception:
            logger.exception("internal server error.")
            raise InternalServerError()


@console_ns.route(
    "/installed-apps/<uuid:installed_app_id>/completion-messages/<string:task_id>/stop",
    endpoint="installed_app_stop_completion",
)
class CompletionStopApi(InstalledAppResource):

View on GitHub (pinned to ef8544b173)

Solutions

1. Go to Settings -> Model Provider and add valid API credentials for the provider the app uses.
2. Identify which provider/model the app needs by opening it in Studio and checking the model node.
3. If using OpenAI, ensure the key is active and has credit.
4. After saving credentials, retry the completion request.

Example fix

# before: app uses gpt-4o but no OpenAI key is configured
# (request fails with provider_not_initialize)

# after: configure the provider, then retry
# Settings -> Model Provider -> OpenAI -> Add API Key -> Save
# then re-send the same completion request

// Before posting, confirm the tenant has credentials for the provider the app uses.
const providers = await fetch('/console/workspaces/current/model-providers').then(r => r.json());
const hasCreds = (providerName) =>
  providers.data.some(p => p.provider === providerName && p.is_valid);
if (!hasCreds(appProvider)) { promptConfigureProvider(appProvider); }

function providerIsConfigured(providerEntry) {
  return Boolean(providerEntry && providerEntry.is_valid);
}

try {
  await postCompletion(id, payload);
} catch (err) {
  if (err.code === 'provider_not_initialize') {
    // direct user to Settings -> Model Provider; do not blind-retry
    showProviderSetupUI();
  } else { throw err; }
}

When it happens

Trigger: POST /console/installed-apps/<id>/completion-messages where the app's configured model provider has no valid credentials on the tenant. AppGenerateService tries to load the provider credentials and ProviderTokenNotInitError fires before any model call.

Common situations: New deployment where no provider keys were added; provider credentials were rotated/expired and removed; the app was installed from a template that uses a provider the tenant never configured; switching from Dify-hosted trial to BYO-key without entering keys.

Related errors

• provider_quota_exceeded
• model_currently_not_support
• provider_not_initialize
• server_4xx_other
• provider_not_support_speech_to_text

AI-assisted analysis of langgenius/dify@ef8544b173 (2026-08-12). Data as JSON: /api/errors/6845aaf25cacd42f. Report an issue: GitHub.