Hero AI Models

overview hero ai does not use a single model for every feature for default swimlane managed routing, inference uses anthropic claude on amazon bedrock , with a different primary model per feature hero ai native action defaults to a faster haiku tier for playbook automation, while hero ai companion , agents (plan generation, remediation, playbook builder, and component agents), and code agent default to sonnet tiers suited to longer reasoning tasks when swimlane manages bedrock routing, each feature has its own primary model hero ai companion , agents , and code agent use automatic fallbacks if a model is unavailable or throttled hero ai native action uses a single default model with no automatic fallback chain (starting in 26 1 2 ) you can replace defaults with custom llm docid\ deoy k3jmcpdm c ikrq4 ( turbine cloud or turbine platform ) or with turbine platform installer settings use the sections below to see default models by feature, how fallbacks work for companion and agent features, and how to check data residency when you pick models in the product or configure your own bedrock endpoint default swimlane models and fallbacks for standard turbine cloud and turbine platform deployments, swimlane routes each hero ai feature to a primary claude model on bedrock for hero ai companion , agents , and code agent , if the primary model is unavailable or throttled (rate limits), the platform switches to the next fallback tier in that row when one exists on transient timeouts , the platform may retry the same model before failing over feature default (primary) secondary fallback tertiary fallback hero ai native action docid\ rx5y8x2 bzqjoup2j 8xq claude haiku 4 5 — — hero ai companion docid\ crqkfvngpcz wj8xthds7 claude sonnet 4 5 claude sonnet 4 claude sonnet 3 5 v2 agents (plan generation, remediation, playbook builder, component agents) claude sonnet 4 5 claude sonnet 4 agents share the same bedrock model chain as hero ai companion (companion chat, ai soc plan and remediation flows, text to playbook, and related agentic workflows) hero ai native action uses only the primary model in its row if that model is unavailable or throttled, the action returns an error rather than failing over to another tier code agent (playbook and code generation agent) uses a two tier sonnet chain only (sonnet 4 5, then sonnet 4; no tertiary fallback) condition what happens model unavailability companion , agents , and code agent switch to the next fallback tier (if configured) native action return an error request throttling / rate limits companion , agents , and code agent switch to the next fallback tier (if configured) native action return an error timeout (transient) retry the same model up to the configured attempt limit, then fail over if applicable (companion, agents, and code agent only) no further fallback tier return an error to the user exact foundation model version strings may change as swimlane and aws update bedrock offerings tier order and failover rules stay as in the table above swimlane does not use your content to train or fine tune these foundation models when defaults do not apply the tables above describe swimlane managed default routing your environment may use different models when override applies to details custom llm docid\ deoy k3jmcpdm c ikrq4 turbine cloud (litellm) and turbine platform (litellm or custom bedrock) account custom llm settings replace default bedrock routing with your proxy or bedrock inference profiles turbine platform installer turbine platform on premises environment variables (for example llm model id medium , swimlane heroaichat models bedrock model ) can override defaults confirm with your swimlane contact which settings apply in your cluster hero ai native action model selection playbooks that set an explicit model on the prompt tab choose a model in model selection or leave use default model the selected model overrides swimlane managed default routing for that action only respect regional availability for that model regional availability swimlane turbine cloud routes default hero ai models through amazon bedrock geo inference or global inference , depending on your instance the values us , eu , au , and jp match bedrock geo inference profiles (for example us anthropic claude haiku 4 5 20251001 v1 0 ) global uses bedrock global cross region inference, which can route requests worldwide when residency constraints allow the table below shows where claude haiku 4 5 (default for hero ai native action docid\ rx5y8x2 bzqjoup2j 8xq ) and claude sonnet 4 5 (default for hero ai companion docid\ crqkfvngpcz wj8xthds7 and agents ) run for each swimlane instance swimlane instance claude haiku 4 5 claude sonnet 4 5 usn swimlane app us us us1 swimlane app us us uk1 swimlane app eu eu de1 swimlane app eu eu ca1 swimlane app us us au1 swimlane app au au sg1 swimlane app global global jp1 swimlane app jp jp for source and destination aws regions within each geo profile, see the geo inference details on the aws model pages claude haiku 4 5 on amazon bedrock https //docs aws amazon com/bedrock/latest/userguide/model card anthropic claude haiku 4 5 html claude sonnet 4 5 on amazon bedrock https //docs aws amazon com/bedrock/latest/userguide/model card anthropic claude sonnet 4 5 html to see which bedrock models are offered in each aws region, see regional availability in amazon bedrock https //docs aws amazon com/bedrock/latest/userguide/models region compatibility html use that reference when you select models in hero ai native action or configure custom bedrock inference profile ids usage (tokens and credits) hero ai consumption appears in the hero ai dashboard docid\ fizav7ysvgmwke ms1sqc under admin panel usage reporting (tokens and credits, where enabled for your account)