---
title: "List Available Models"
api: "GET /v1/api/llm-models/call-flow-models"
description: "List the language models currently available to your workspace."
lastUpdated: "2026-11-04"
---

> **For AI agents:** the complete documentation index is at [llms.txt](https://trillet-ai.jamdesk.app/llms.txt). Append `.md` to any page URL for its markdown version.

Returns every language model your workspace can use, so you can pass a valid `id` as `llmModel` when creating or updating a call agent.

The available models change over time. Read this endpoint rather than hardcoding a list.

To list the models available to one particular call flow, call `GET /v1/api/llm-models/call-flow-models/{callFlowId}`. It returns the same fields, and also includes models enabled only for that flow.

### Headers

<ParamField header="x-workspace-id" type="string" required>
The unique identifier of the workspace being accessed.
</ParamField>

### Response Fields

<ResponseField name="id" type="string">
The model identifier. This is the value to pass as `llmModel` on agent create and update.
</ResponseField>

<ResponseField name="name" type="string">
Display name for the model.
</ResponseField>

<ResponseField name="description" type="string">
Short description, usually the context window. May be empty.
</ResponseField>

<ResponseField name="speed" type="string">
Relative speed score, as a percentage. May be empty.
</ResponseField>

<ResponseField name="quality" type="string">
Relative quality score, as a percentage. May be empty.
</ResponseField>

<ResponseField name="tier" type="string">
Broad performance band, for example `fast` or `balanced`.
</ResponseField>

<ResponseField name="provider" type="string">
The model's vendor.
</ResponseField>

<ResponseField name="tags" type="string[]">
Labels shown in the model picker. May be empty.
</ResponseField>

<ResponseField name="standardRatePerMinute" type="number">
Your workspace's standard per-minute call rate.
</ResponseField>

<ResponseField name="effectiveRatePerMinute" type="number">
What a minute costs your workspace with this model, including any model surcharge.
</ResponseField>

<ResponseField name="costMultiplier" type="number | null">
How many times the standard rate this model costs. `null` when it costs no more than a standard minute.
</ResponseField>

<ResponseField name="isRecommended" type="boolean">
Whether the model is recommended for general use.
</ResponseField>

<ResponseField name="isTopPick" type="boolean">
Whether the model is the current default choice. Exactly one model carries this.
</ResponseField>

<ResponseField name="averageLatency" type="number">
Mean time to first token in seconds, measured across recent calls. Present only once a model has enough traffic to report on.
</ResponseField>

### Response

<ResponseExample>

```json
[
  {
    "id": "platform-llm",
    "name": "Platform LLM",
    "description": "",
    "speed": "",
    "quality": "",
    "tier": "fast",
    "tags": [],
    "isRecommended": true,
    "isTopPick": true,
    "allowedFlowIds": [],
    "averageLatency": 0.32
  },
  {
    "id": "gpt-4.1",
    "name": "GPT-4.1",
    "description": "1M context window",
    "speed": "93%",
    "quality": "94%",
    "tier": "balanced",
    "tags": [],
    "isRecommended": true,
    "isTopPick": false,
    "allowedFlowIds": [],
    "averageLatency": 0.88
  },
  {
    "id": "gemini-2.5-flash",
    "name": "Gemini 2.5 Flash",
    "description": "1M context window",
    "speed": "99%",
    "quality": "98%",
    "tier": "balanced",
    "tags": [],
    "isRecommended": false,
    "isTopPick": false,
    "allowedFlowIds": [],
    "averageLatency": 0.83
  }
]
```

</ResponseExample>


---

📦 **OpenAPI specs:** Every OpenAPI specification referenced by this documentation is available as a single download — https://trillet-ai.jamdesk.app/api-specs.zip
