---
title: "List currently supported LLM utility models"
method: GET
path: "/v1/models"
tags: ["LLM API"]
---

# List currently supported LLM utility models

`GET /v1/models`

## Request

- Base URL: `https://api.algenta.ai`
- URL: `https://api.algenta.ai/v1/models`
- Auth: one of:
  - HTTP bearer
  - API key in header `X-API-Key`

Returns the truthful, currently executable Algenta LLM model catalog. Only runtime-backed or explicitly configured provider-backed models are advertised.

## Response `200`

Successful Response

- LLMModelListResponse
  - `object` 'list'
  - `data` LLMModelResponse[], required
    - `id` string, required
    - `object` 'model'
    - `owned_by` string
    - `runtime_module` string, required
    - `description` string, required
    - `capabilities` string[], required
    - `supported_endpoints` string[], required
    - `runtime_functions` string[], required
    - `tokenizer_kind` string, nullable
    - `similarity_metric` string, nullable
    - `provider_backend` string, nullable: Provider backend identifier for provider-routed models.
    - `routing_targets` string[]: Ordered shared provider-routing targets for router-backed models.
    - `resolved_routing_targets` string[]: Flattened shared provider-routing leaf targets for router-backed models.
    - `chat_routing_targets` string[]: Ordered chat-completions provider-routing targets for router-backed models.
    - `resolved_chat_routing_targets` string[]: Flattened chat-completions provider-routing leaf targets for router-backed models.
    - `embedding_routing_targets` string[]: Ordered embeddings provider-routing targets for router-backed models.
    - `resolved_embedding_routing_targets` string[]: Flattened embeddings provider-routing leaf targets for router-backed models.
    - `routing_fallback_policy` string, nullable: Router failover policy for retryable provider errors when backend='router'.
    - `chat_routing_fallback_policy` string, nullable: Chat-specific router failover policy for retryable provider errors when backend='router'.
    - `embedding_routing_fallback_policy` string, nullable: Embeddings-specific router failover policy for retryable provider errors when backend='router'.
    - `routing_fallback_on` string[]: Shared retryable provider error codes that are allowed to trigger router failover when backend='router'.
    - `chat_routing_fallback_on` string[]: Chat-specific retryable provider error codes that are allowed to trigger router failover when backend='router'.
    - `embedding_routing_fallback_on` string[]: Embeddings-specific retryable provider error codes that are allowed to trigger router failover when backend='router'.
    - `routing_max_attempts` integer, nullable: Shared maximum number of routed provider targets to attempt when backend='router'.
    - `chat_routing_max_attempts` integer, nullable: Chat-specific maximum number of routed provider targets to attempt when backend='router'.
    - `embedding_routing_max_attempts` integer, nullable: Embeddings-specific maximum number of routed provider targets to attempt when backend='router'.
    - `timeout_seconds` number, nullable: Shared provider HTTP timeout in seconds for this model entry.
    - `chat_timeout_seconds` number, nullable: Chat-specific provider HTTP timeout in seconds for this model entry.
    - `embedding_timeout_seconds` number, nullable: Embeddings-specific provider HTTP timeout in seconds for this model entry.
    - `required_provider_headers` string[]: Additional upstream HTTP header names required by this provider-backed model configuration.
    - `chat_required_provider_headers` string[]: Additional upstream HTTP header names required for chat-completions on this provider-backed model configuration.
    - `embedding_required_provider_headers` string[]: Additional upstream HTTP header names required for embeddings on this provider-backed model configuration.
    - `provider_auth_env_vars` string[]: Environment variable names required to authenticate this provider-backed model configuration.
    - `chat_provider_auth_env_vars` string[]: Environment variable names required to authenticate chat-completions on this provider-backed model configuration.
    - `embedding_provider_auth_env_vars` string[]: Environment variable names required to authenticate embeddings on this provider-backed model configuration.
    - `provider_auth_configured` boolean: Whether all required provider auth environment variables are configured for this model entry.
    - `chat_provider_auth_configured` boolean: Whether all chat-completions provider auth environment variables are configured for this model entry.
    - `embedding_provider_auth_configured` boolean: Whether all embeddings provider auth environment variables are configured for this model entry.
    - `bridge_cache_root` string, nullable: Resolved artifact/cache bridge root when Hugging Face cache support is available.
    - `bridge_auth_env_vars` string[]: Supported environment variable aliases for artifact-bridge authentication.
    - `bridge_auth_configured` boolean: Whether one of the supported artifact-bridge auth environment variables is configured.
    - `bridge_tokenizer_backends` string[]: Detected optional tokenizer bridge backends available in the current checkout.
    - `bridge_artifact_backends` string[]: Detected optional artifact/cache bridge backends available in the current checkout.
    - `streaming_mode` 'passthrough' | 'synthetic': Truthful streaming capability for this model. 'passthrough' means stream=true returns the upstream's own incremental chunks as they are generated; 'synthetic' means stream=true still returns valid SSE, but the content is produced by one buffered call and sliced into fixed-size chunks afterward.
    - `supported_parameters` string[]: Chat-completions request parameters this model's backend actually honors.
    - `available` boolean, required

---

[API](https://skmtc.dev/codna/apis/algenta-api.md) · [All operations](https://skmtc.dev/codna/apis/algenta-api/llms.txt) · [OpenAPI document](https://skmtc.dev/codna/apis/algenta-api/revisions/35d30f84a5df?raw)