A wandb API key or wandb JWT. Browser sessions are exchanged by the Model Distillation web app backend; job capabilities are internal only.
Accessible personal or team entity. Omit to list all accessible entities on GET /projects and GET /projects/summaries. Other endpoints use the authenticated user's default entity.
Pattern: ^[a-z0-9-]{1,64}$
One-based result page. Defaults to 1.
Required range: x <= 9007199254740991
Entries per page. Defaults to 50; maximum 200.
Required range: 1 <= x <= 200
Return outputs from this relabeling strategy.
Pattern: ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$
Sort all matching entries before pagination by created, input_tokens, or output_tokens. Evaluation sorting takes precedence.
Available options:
created,
input_tokens,
output_tokens
Sort direction. Defaults to asc for created and desc for token counts.
Available options:
asc,
desc
Evaluation whose critical failures should be returned. Use with critical_failure_output_key.
Pattern: ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$
critical_failure_output_key
Output key whose critical failures should be returned. Use with critical_failure_eval_id.
Required string length: 1 - 600
Return the dataset entry associated with this evaluation result.
Pattern: ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$
Read entries from a specific immutable dataset version.
Required range: 0 <= x <= 9007199254740991
Paginated dataset entries and attached outputs/results.
Approximate input/output token totals over all matching rows, plus counts for the returned entries. Null on the experimental Weave data plane.
Last modified on October 6, 2026