Skip to main content

Documentation Index

Fetch the complete documentation index at: https://arizeai-433a7140.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

​
Filter-Based Annotation Delete Endpoints

May 5, 2026 Available in arize-phoenix 15.4.0+ Three new DELETE endpoints let you bulk-remove annotations from a project by filter — without knowing every individual span/trace/session ID. This closes the annotation lifecycle loop for automated pipelines that tag annotations with a custom identifier on creation and need to roll them back later. 
DELETE /v1/projects/{project_identifier}/span_annotations
DELETE /v1/projects/{project_identifier}/trace_annotations
DELETE /v1/projects/{project_identifier}/session_annotations
Query parameters (all optional, but at least one time-bound or delete_all=true is required):
ParameterDescription
nameExact match on annotation name
identifierExact match on annotation identifier
annotator_kindLLM, CODE, or HUMAN
start_timeInclusive lower bound on created_at
end_timeExclusive upper bound on created_at
delete_allSet true to waive the time-bound requirement
# Delete all annotations tagged with identifier "eval-run-42" on spans
curl -X DELETE \
  "https://your-phoenix/v1/projects/my-project/span_annotations?identifier=eval-run-42" \
  -H "Authorization: Bearer $PHOENIX_API_KEY"

# Delete LLM annotations older than a cutoff
curl -X DELETE \
  "https://your-phoenix/v1/projects/my-project/trace_annotations?annotator_kind=LLM&end_time=2026-05-01T00:00:00Z" \
  -H "Authorization: Bearer $PHOENIX_API_KEY"

​
Token Counts in Trace and Session REST Payloads

May 5, 2026 Available in arize-phoenix 15.4.0+ The GET /v1/projects/{project_identifier}/traces and GET /v1/projects/{project_identifier}/sessions endpoints now include cumulative token usage fields — cumulative_token_count_prompt, cumulative_token_count_completion, and cumulative_token_count_total — so you can read aggregate token consumption directly from the REST API without recomputing from raw span attributes. Values are summed from root spans and default to 0 for traces or sessions with no LLM calls. The /v1/spans endpoint is unchanged — span-level token counts remain in the existing attributes dictionary.

​
Experiment CSV Export Includes Dataset Metadata

May 5, 2026 Available in arize-phoenix 15.3.0+ Downloading an experiment as CSV now includes per-example dataset metadata columns. Each metadata key appears as a metadata_<key> column — matching the format used by the dataset CSV export — so you can cross-reference experiment results with the original dataset context without a separate download.

​
Evals: Runtime Model Capability Detection

May 5, 2026 Available in arize-phoenix-evals 3.1.0+ The OpenAI evaluator adapter now detects structured-output and tool-call support at runtime rather than checking against a hardcoded model list. This unblocks OpenAI reasoning models (o1, o3, o3-mini, o4-mini) for use with ClassificationEvaluator and ensures new models work automatically without requiring a library update. The adapter tries structured output first, falls back to tool calling if unsupported, and caches the result per adapter instance — matching the approach already used by the Google GenAI adapter. 
from phoenix.evals import ClassificationEvaluator, OpenAIModel

# Reasoning models now work without any special configuration
evaluator = ClassificationEvaluator(
    model=OpenAIModel(model="o3-mini"),
    template="my-eval-template",
)