Model groups

All models all_models

Every model eligible for the capability. Applies no allowlist — the pool is computed per call, so there is no membership list to go stale. This is the default pool a task runs in when no group is named, and it exists so that pool has a name to be priced, latched and reported against.

This group is every active model.

Tasks on this group: Claim Continuity Classification, Public Response Generation, Voice Profile Generation, Promotional Campaign Generation, Public Engagement Reply Review, Topic Sequence Optimization, Model Specific Prompt Adaptation, Promotional Message Generation, Capability Category Matching, Section Prompt Generation, Report Outline Generation, Evidence Grounded Claim Generation, Atomic Fact Claim Extraction, Research Query Validation, Generated Content Relevance Scoring, Metadata Paragraph Rewriting, Structured Output Extraction, Markdown Newline Repair, Batch Text Translation, Authoritative Source Selection, Community Policy Evaluation, Bench Hypothesis Post Generation, Content To Image Prompt Generation, Report Executive Summary Generation, Factual Claim Refinement, Structured Content Summarization, Thematic Topic Discovery, Publication Section Taxonomy Generation, Research Query Generation, Newsletter Copy Generation, Language Identification, Bench Article Hypothesis Generation, Persona Policy Eligibility Check, Profile Pool Matching, Engagement Opportunity Triage, Content Set Relevance Scoring, Topic Section Assignment, Social Post Portfolio Selection, Community Content Promotion Generation, Profiled Document Section Analysis, Subject Configuration Generation, Research Community Selection, Reference Preserving Analytical Writing, Multi Perspective Decision Synthesis, Profiled Document Structure Extraction, Content Domain Suggestion, Topic Cluster Labeling, Research Region Identification, Publication Title Package Generation, Visual Theme Configuration Generation, Profiled Document Analysis, Catalyst And Scenario Analysis, Short Post Batch Relevance Scoring, Topic Taxonomy Matching.

US models us_models

Every active model from a US company. No cost filter — the flagship tier is included.

US workhorse us_workhorse

The US pool minus the flagship tier: a strict subset of us_models, and the US-only counterpart of workhorse.

Workhorse workhorse

Every active model except the flagship tier. The default working pool for cost-sensitive routing; premium models are the exception, named explicitly when wanted.