langgenius/dify · error · ProviderModelCurrentlyNotSupportError

model_currently_not_support

model_currently_not_support

Error message

Dify Hosted OpenAI trial currently not support the GPT-4 model.

What it means

HTTP 400 with error_code model_currently_not_support, raised when generate_more_like_this raises ModelCurrentlyNotSupportError. The specific model the app uses is not permitted under the current provider grant — classically GPT-4 on the Dify hosted OpenAI trial.

Source

Thrown at api/controllers/console/explore/message.py:189

                session=session,
                app_model=app_model,
                user=current_user,
                message_id=message_id_str,
                invoke_from=InvokeFrom.EXPLORE,
                streaming=streaming,
            )
            # response-contract:ignore compact_generate_response
            return helper.compact_generate_response(response)
        except MessageNotExistsError:
            raise NotFound("Message Not Exists.")
        except MoreLikeThisDisabledError:
            raise AppMoreLikeThisDisabledError()
        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>/messages/<uuid:message_id>/suggested-questions",
    endpoint="installed_app_suggested_question",
)
class MessageSuggestedQuestionApi(InstalledAppResource):
    @console_ns.response(200, "Success", console_ns.models[SuggestedQuestionsResponse.__name__])
    @with_current_user
    def get(self, current_user: Account, installed_app: InstalledApp, message_id: UUID):
        app_model = installed_app.app_with_session(session=db.session())

View on GitHub (pinned to ef8544b173)

Solutions

1. Switch the app's model to one allowed by the current provider grant (e.g. GPT-3.5 on trial).
2. Configure your own provider credentials that include the restricted model.
3. Upgrade the plan/tier so the model becomes available.
4. Confirm the model name in the app config matches a supported identifier.

Example fix

# before: app configured for GPT-4 on hosted trial
# App Settings -> Model -> change to an allowed model

# after: verify model is allowed before generation
allowed = get_allowed_models(provider)
if app.model_name not in allowed:
    app.model_name = allowed[0]; save(app)
resp = get(more_like_this_url(id, mid))

// Confirm the app's model is in the provider's allowed list
const allowed = await get(`/console/workspaces/current/model-providers/${app.provider_name}/models`);
if (!allowed.includes(app.model_name)) {
  throw new ConfigError('Model not supported by current provider grant');
}

function modelIsAllowed(app, allowedModels) {
  return Array.isArray(allowedModels) && allowedModels.includes(app?.model_name);
}

try {
  return await get(moreLikeThisUrl(id, mid));
} catch (e) {
  if (e.code === 'model_currently_not_support') {
    await switchAppModel(id, allowedModels[0]);
    return get(moreLikeThisUrl(id, mid));
  }
  throw e;
}

When it happens

Trigger: GET more-like-this on an app configured to use a model the active provider grant disallows (e.g. GPT-4 on the hosted trial). The service raises ModelCurrentlyNotSupportError and the controller maps it to ProviderModelCurrentlyNotSupportError(400).

Common situations: Trial plan that only allows certain models; app was built against a model the current subscription tier does not include; provider changed its allowed-model list.

Related errors

• provider_not_initialize
• provider_quota_exceeded
• completion_request_error
• not_completion_app
• app_more_like_this_disabled

AI-assisted analysis of langgenius/dify@ef8544b173 (2026-08-12). Data as JSON: /api/errors/be14d2051493e2cf. Report an issue: GitHub.