---
title: "List available models"
method: GET
path: "/agent/models"
tags: ["agent"]
---

# List available models

`GET /agent/models`

Retrieve the list of LLM models available to the authenticated user for
agent runs. The response includes which model is the default, as well as
per-model metadata such as provider, cost, and whether the model is
currently disabled (and why).

## Response `200`

List of available models

- ListModelsResponse
  - `default_model_id` string, required — The ID of the default model for agent runs
  - `models` ModelInfo[], required — List of available models
    - `id` string, required — Unique identifier for the model (e.g. "claude-4-6-opus-high" or "gpt-5-4-high")
    - `display_name` string, required — Human-readable name of the model
    - `provider` 'OPENAI' | 'ANTHROPIC' | 'GOOGLE' | 'UNKNOWN', required — The LLM provider
    - `vision_supported` boolean, required — Whether the model supports vision/image inputs
    - `description` string — Optional extra descriptor for the model
    - `reasoning_level` string — Reasoning level descriptor, if any (e.g. "low", "medium", "high")
    - `disable_reason` 'PROVIDER_OUTAGE' | 'OUT_OF_REQUESTS' | 'ADMIN_DISABLED' | 'REQUIRES_UPGRADE' — If set, the model is currently unavailable for the given reason

## Other responses

- `401` — Authentication required
- `500` — Internal server error

---

[API](https://skmtc.net/warp/apis/oz-agent-api.md) · [All operations](https://skmtc.net/warp/apis/oz-agent-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/warp/oz-agent-api/versions/97be876c33e3/schema)