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

Raised by _transcribe_audio_to_text when AudioService raises ModelCurrentlyNotSupportError — the Dify Hosted OpenAI trial does not support the requested model on the trial path (the canned message names GPT-4). Translated to ProviderModelCurrentlyNotSupportError (400, error_code 'model_currently_not_support').

Source

Thrown at api/controllers/console/app/audio.py:169

    except services.errors.app_model_config.AppModelConfigBrokenError:
        logger.exception("App model config broken.")
        raise AppUnavailableError()
    except NoAudioUploadedServiceError:
        raise NoAudioUploadedError()
    except AudioTooLargeServiceError as e:
        raise AudioTooLargeError(str(e))
    except UnsupportedAudioTypeServiceError:
        raise UnsupportedAudioTypeError()
    except ProviderNotSupportSpeechToTextServiceError:
        raise ProviderNotSupportSpeechToTextError()
    except SpeechToTextDisabledServiceError:
        raise SpeechToTextDisabledError()
    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 HTTPException:
        raise
    except ValueError:
        raise
    except Exception as e:
        logger.exception("Failed to transcribe audio to text")
        raise InternalServerError() from e


@console_ns.route("/apps/<uuid:app_id>/audio-to-text")
class ChatMessageAudioApi(Resource):
    @console_ns.doc("chat_message_audio_transcript")
    @console_ns.doc(description="Transcript audio to text for chat messages")
    @console_ns.doc(
        consumes=["multipart/form-data"],
        params={"app_id": "App ID", "file": _AUDIO_TRANSCRIPT_FILE_PARAM},

View on GitHub (pinned to ef8544b173)

Solutions

1. Switch to a supported trial model (e.g., gpt-3.5-turbo family).
2. Configure your own OpenAI/compatible provider credentials to unlock GPT-4.
3. Re-select the model in the app's model settings to a non-blocked option.
4. Confirm the tenant plan supports the model.

try { return await axios.post(`/apps/${id}/audio-to-text`, form); }
catch (e) {
  if (e.code === 'model_currently_not_support') {
    // retry with a trial-supported model or user-configured credentials
  }
}

When it happens

Trigger: App configured to use a model the hosted trial explicitly excludes (notably GPT-4) while still on the Dify Hosted trial provider; STT/transcription request routed to that model.

Common situations: Tenant still on trial trying to use GPT-4-class models; model setting left at a default the trial blocks.

Related errors

• provider_quota_exceeded
• app_unavailable
• unsupported_audio_type
• provider_not_support_speech_to_text
• completion_request_error

AI-assisted analysis of langgenius/dify@ef8544b173 (2026-08-12). Data as JSON: /api/errors/bcf77f8b5596cf30. Report an issue: GitHub.