The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Python ai-gatewayanthropicazure-openaibedrockgatewaylangchainlitellmllmllm-gatewayllmopsmcp-gatewayopenaiopenai-proxyrustrust-aivertex-ai
generated by https://github.com/hashicorp/terraform-plugin-docs
page_title: "litellm_models Data Source - terraform-provider-litellm" subcategory: "" description: |- Lists model deployments on the LiteLLM proxy.
litellm_models (Data Source)
Lists all model deployments via /v1/model/info. Sensitive litellm_params fields (API keys and other credentials) are never exposed.
Example Usage
data "litellm_models" "all" {}
output "model_names" {
value = [for m in data.litellm_models.all.models : m.model_name]
}
Argument Reference
The following arguments are supported:
team_id- (Optional) Filter models to those accessible by this team.
Attributes Reference
In addition to all arguments above, the following attributes are exported:
ids- LiteLLM model IDs of the returned models.models- List of model objects. Each entry exports:id- LiteLLM model ID.model_name- Public model name used for routing.model- The underlyinglitellm_paramsmodel.custom_llm_provider- Provider for the model.model_api_base- API base URL, if configured.base_model- Base model used for pricing and capabilities.tier- Model tier (freeorpaid).mode- Model mode, e.g.chatorembedding.team_id- Team the deployment is scoped to, if any.display_name- Human-readable name returned by/v1/models, if configured.db_model- Whether the deployment is stored in the database.