mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-07 08:26:10 +00:00
3653e5893f
* feat(terraform): close key/team schema gaps, fix team read envelope, add import support * feat(terraform): add fallback resource/data source and key/team block resources * feat(terraform): add access group and unified access group resources and data sources * feat(terraform): add guardrail and prompt resources and data sources * feat(terraform): add agent and search tool resources and data sources * feat(terraform): add user and budget resources and data sources * feat(terraform): add tag and project resources and data sources * docs(terraform): changelog and readme for parity additions * feat(terraform): add data sources for keys, teams, models, organizations, and mcp servers * fix(terraform): key update 400 on empty budget_duration, key info envelope, config-supplied key * fix(terraform): hash raw keys to SHA-256 tokens in key lookup URLs and block resource IDs
1.4 KiB
1.4 KiB
litellm_fallback Resource
Manages a fallback configuration for a model in LiteLLM. Fallbacks are triggered when a call to the primary model fails after retries.
Example Usage
Basic Fallback Configuration
resource "litellm_fallback" "gpt4_fallbacks" {
model = "gpt-4"
fallback_models = ["claude-3-sonnet", "gpt-3.5-turbo"]
}
Context Window Fallback
resource "litellm_fallback" "gpt4_context_window" {
model = "gpt-4"
fallback_models = ["claude-3-sonnet"]
fallback_type = "context_window"
}
Argument Reference
The following arguments are supported:
model- (Required, Forces new resource) The model name to configure fallbacks for. The model must already exist on the proxy.fallback_models- (Required) List of fallback model names in order of priority. Each model must exist on the proxy, and the primary model cannot be its own fallback.fallback_type- (Optional, Forces new resource) Type of fallback. One ofgeneral(default),context_window, orcontent_policy.
Attribute Reference
In addition to the arguments above, the following attribute is exported:
id- The primary model name.
Import
Fallback configurations can be imported using the primary model name:
terraform import litellm_fallback.example gpt-4
Note: import always reads the general fallback type. Fallbacks of type context_window or content_policy cannot be imported.