What is Phoenix
Arize Phoenix is the open-source, OpenTelemetry-based platform from Arize AI for observability, evaluation, prompt engineering, and experimentation with LLM workflows and agents. Use Arize’s hosted Phoenix Cloud, or self-host Phoenix on your own infrastructure (a single container is enough to start). Dify sends traces server-side, so a self-hosted endpoint must be reachable from the internet. If you need the full-featured platform built for production teams, AI-native companies, and enterprises, set up Arize AX through the Arize integration instead. Once traces are flowing, see Arize’s agent evaluation guide and LLM evaluation guide for how to use them to debug failures, evaluate agent behavior, and monitor model quality.How to Configure Phoenix
For a self-hosted Phoenix instance without authentication, skip the account and API key steps below and leave API Key blank.1. Register/Login to Phoenix
2. Get your Phoenix API Key
Retrieve your Phoenix API Key from the user menu at the top-right. Click on API Key, then on the API Key to copy it:
3. Integrate Phoenix with Dify
Configure Phoenix in the Dify application. Open the application you need to monitor, open Monitoring in the side menu, and select Tracing app performance on the page.
/v1/traces; Dify adds the ingestion path.


How to Configure Phoenix Cloud
1. Register/Login to Phoenix Cloud
2. Create your Phoenix Space
You can create your Phoenix Space from the user menu at the top-right. Click on Create Space, then provide a unique URL identifier for your space:

3. Create your Phoenix API Key
After launching your space, you can create your Phoenix API Key from the Settings option in the user menu at the bottom-left. Click on System Key, then provide a name for your Phoenix API Key:
4. Integrate Phoenix Cloud with Dify
Configure Phoenix in the Dify application. Open the application you need to monitor, open Monitoring in the side menu, and select Tracing app performance on the page.
https://app.phoenix.arize.com/s/<space>), then save.


After saving and enabling tracing, run the app again and check for a new trace in the monitoring service. Delivery is asynchronous; saving the configuration alone does not confirm that a trace has arrived.For the new Agent app type and workflows using the new Agent node, Capture content is off by default: inputs, outputs, and most metadata are removed, and error text is redacted across the whole workflow. Enable it to send that content. Classic
agent-chat apps and workflows using only classic Agent nodes retain ordinary tracing.Monitoring Data List
The tables below describe ordinary traces. For the new Agent app type or workflows containing a new Agent node, traces use a new UUIDv7 trace ID, with source and tracing-run IDs retained asdify.source.id and dify.tracing.run_id attributes. For the new Agent app type, Agent attempt spans with internal model and tool calls replace the ordinary llm span when Capture Agent internals is on. Separate moderation, suggested-question, and naming records are omitted for collected runs.
Dify exports a hierarchy of operations: a message contains an llm call, and a Chatflow message contains its workflow and node operations. Trace IDs preserve the value of nonzero UUID or 32-hex message, workflow run, or caller-supplied IDs; other values are hashed. Span IDs are derived. A supplied X-Trace-Id takes precedence over the message or workflow run ID. Native token usage is reported on model calls only.
Each span’s user.id uses end_user_session_id when available, otherwise user_id. The separate metadata.user_id field keeps the Dify user record ID.
The detail lists below describe Dify’s source records and metadata. Only the relevant, available values are exported; the raw records are not sent in full.
Workflow/Chatflow Trace Information
Used to track workflows and chatflows| Workflow | Phoenix Trace |
|---|---|
| workflow_run_id | metadata.workflow_run_id |
| user_id | user.id (fallback); metadata.user_id |
| workflow | name |
| start_time | start_time_unix_nano |
| end_time | end_time_unix_nano |
| inputs | input.value |
| outputs | output.value |
| Model token consumption (LLM calls) | llm.token_count.prompt / completion / total |
| metadata | metadata |
| error | status.code / status.message |
| Session ID | session.id |
- workflow_id - Unique identifier of the workflow
- conversation_id - Conversation ID
- workflow_run_id - ID of the current run
- tenant_id - Tenant ID
- elapsed_time - Time taken for the current run
- status - Run status
- version - Workflow version
- total_tokens - Total tokens used in the current run
- file_list - List of processed files
- triggered_from - Source that triggered the current run
- workflow_run_inputs - Input data for the current run
- workflow_run_outputs - Output data for the current run
- error - Errors encountered during the current run
- query - Query used during the run
- workflow_app_log_id - Workflow application log ID
- message_id - Associated message ID
- start_time - Start time of the run
- end_time - End time of the run
- workflow node executions - Information about workflow node executions
- Metadata
- workflow_id - Unique identifier of the workflow
- conversation_id - Conversation ID
- workflow_run_id - ID of the current run
- tenant_id - Tenant ID
- elapsed_time - Time taken for the current run
- status - Run status
- version - Workflow version
- total_tokens - Total tokens used in the current run
- file_list - List of processed files
- triggered_from - Source that triggered the current run
Message Trace Information
Used to track LLM-related conversations| Chat | Phoenix Trace |
|---|---|
| message_id (unless X-Trace-Id is supplied) | trace_id |
| end_user_session_id | user.id; metadata.end_user_session_id |
| message | name |
| start_time | start_time_unix_nano |
| end_time | end_time_unix_nano |
| inputs | input.value |
| outputs | output.value |
| Model token consumption (LLM calls) | llm.token_count.prompt / completion / total |
| metadata | metadata |
| Session ID | session.id |
- message_id - Message ID
- message_data - Message data
- end_user_session_id - User session ID
- conversation_model - Conversation mode
- message_tokens - Number of tokens in the message
- answer_tokens - Number of tokens in the answer
- total_tokens - Total number of tokens in the message and answer
- error - Error information
- inputs - Input data
- outputs - Output data
- file_list - List of processed files
- start_time - Start time
- end_time - End time
- conversation_mode - Conversation mode
- Metadata
- conversation_id - Conversation ID
- ls_provider - Model provider
- ls_model_name - Model ID
- status - Message status
- from_end_user_id - ID of the sending user
- from_account_id - ID of the sending account
- agent_based - Whether the message is agent-based
- workflow_run_id - Workflow run ID
- from_source - Message source
Moderation Trace Information
Used to track conversation moderation| Moderation | Phoenix Tool |
|---|---|
| user_id | user.id (fallback); metadata.user_id |
| moderation | name |
| start_time | start_time_unix_nano |
| end_time | end_time_unix_nano |
| inputs | input.value |
| action, flagged | output.value |
| metadata | metadata |
- message_id - Message ID
- user_id: User ID
- workflow_app_log_id - Workflow application log ID
- inputs - Moderation input data
- message_data - Message data
- flagged - Whether the content is flagged for attention
- action - Specific actions taken
- preset_response - Preset response
- start_time - Moderation start time
- end_time - Moderation end time
- Metadata
- message_id - Message ID
- action - Specific actions taken
- preset_response - Preset response
Suggested Question Trace Information
Used to track suggested questions Sent as a tool span in the message’s trace.| Suggested Question | Phoenix Tool span |
|---|---|
| user_id | user.id (fallback); metadata.user_id |
| ”suggested_question” | name |
| start_time | start_time_unix_nano |
| end_time | end_time_unix_nano |
| inputs | input.value |
| suggested_question | output.value |
| metadata | metadata |
- message_id - Message ID
- message_data - Message data
- inputs - Input content
- outputs - Output content
- start_time - Start time
- end_time - End time
- total_tokens - Number of tokens
- status - Message status
- error - Error information
- from_account_id - ID of the sending account
- agent_based - Whether the message is agent-based
- from_source - Message source
- model_provider - Model provider
- model_id - Model ID
- suggested_question - Suggested question
- level - Status level
- status_message - Status message
- Metadata
- message_id - Message ID
- ls_provider - Model provider
- ls_model_name - Model ID
- status - Message status
- from_end_user_id - ID of the sending user
- from_account_id - ID of the sending account
- workflow_run_id - Workflow run ID
- from_source - Message source
Dataset Retrieval Trace Information
Used to track knowledge base retrieval| Dataset Retrieval | Phoenix Retriever |
|---|---|
| user_id | user.id (fallback); metadata.user_id |
| ”dataset_retrieval” | name |
| start_time | start_time_unix_nano |
| end_time | end_time_unix_nano |
| inputs | input.value |
| documents | output.value |
| metadata | metadata |
| ID derived from message_id | parent_span_id |
- message_id - Message ID
- inputs - Input content
- documents - Document data
- start_time - Start time
- end_time - End time
- message_data - Message data
- Metadata
- message_id - Message ID
- ls_provider - Model provider
- ls_model_name - Model ID
- status - Message status
- from_end_user_id - ID of the sending user
- from_account_id - ID of the sending account
- agent_based - Whether the message is agent-based
- workflow_run_id - Workflow run ID
- from_source - Message source
Tool Trace Information
Used to track tool invocation| Tool | Phoenix Tool |
|---|---|
| user_id | user.id (fallback); metadata.user_id |
| tool_name | name |
| start_time | start_time_unix_nano |
| end_time | end_time_unix_nano |
| tool_inputs | input.value |
| tool_outputs | output.value |
| metadata | metadata |
Tool Trace Info
- message_id - Message ID
- tool_name - Tool name
- start_time - Start time
- end_time - End time
- tool_inputs - Tool inputs
- tool_outputs - Tool outputs
- message_data - Message data
- error - Error information, if any
- inputs - Inputs for the message
- outputs - Outputs of the message
- tool_config - Tool configuration
- time_cost - Time cost
- tool_parameters - Tool parameters
- file_url - URL of the associated file
- Metadata
- message_id - Message ID
- tool_name - Tool name
- tool_inputs - Tool inputs
- tool_outputs - Tool outputs
- tool_config - Tool configuration
- time_cost - Time cost
- error - Error information, if any
- tool_parameters - Tool parameters
- message_file_id - Message file ID
- created_by_role - Role of the creator
- created_user_id - User ID of the creator
| Generate Name | Phoenix Tool |
|---|---|
| user_id | user.id (fallback); metadata.user_id |
| generate_name | name |
| start_time | start_time_unix_nano |
| end_time | end_time_unix_nano |
| inputs | input.value |
| outputs | output.value |
| metadata | metadata |
- conversation_id - Conversation ID
- inputs - Input data
- outputs - Generated conversation name
- start_time - Start time
- end_time - End time
- tenant_id - Tenant ID
- Metadata
- conversation_id - Conversation ID
- tenant_id - Tenant ID