---
title: "Model fields"
manual: "TYPO3 LLM Extension"
version: "0.35"
permalink: "https://docs.typo3.org/permalink/netresearch/nr-llm:configuration-model@0.35"
source: "Configuration/ModelFields.rst"
modified: "2026-09-16T22:09:16+00:00"
---

# Model fields

Models represent specific LLM models available
through a provider.

![Model list showing capabilities and pricing](../Images/backend-models.png)

## Required

-   **identifier (model)**

    -   *Type:* string
    -   *Required:* true

    Unique slug (e.g., `gpt-5`, `claude-sonnet`).

-   **name (model)**

    -   *Type:* string
    -   *Required:* true

    Display name (e.g., `GPT-5 (128K)`).

-   **provider**

    -   *Type:* reference
    -   *Required:* true

    Reference to the parent provider.

-   **model_id**

    -   *Type:* string
    -   *Required:* true

    The API model identifier as the provider expects
    it (e.g., `gpt-5.3-instant`,
    `claude-sonnet-4-6`, `gemini-3-flash`).

## Optional

-   **context_length**

    -   *Type:* integer
    -   *Default:* (provider default)

    Maximum context window in tokens.

-   **max_output_tokens**

    -   *Type:* integer
    -   *Default:* 0 (unknown)

    Maximum output tokens. Acts as the default
    output cap for requests whose configuration
    sets max_tokens
    to `0` and whose caller sent no per-call
    `max_tokens` option.

-   **dimensions**

    -   *Type:* integer
    -   *Default:* 0 (unknown)

    Embedding vector dimensionality. Acts as the
    default vector size for embedding requests
    whose options left `dimensions` unset.

-   **capabilities**

    -   *Type:* string (CSV)
    -   *Default:* chat

    Comma-separated capabilities: `chat`,
    `completion`, `embeddings`, `vision`,
    `streaming`, `tools`.

-   **cost_input**

    -   *Type:* integer
    -   *Default:* 0

    Cost per 1M input tokens in cents.

-   **cost_output**

    -   *Type:* integer
    -   *Default:* 0

    Cost per 1M output tokens in cents.

-   **is_default**

    -   *Type:* boolean
    -   *Default:* false

    Mark as default model for this provider.