Model schemas - AgentMark Docs

You can add models to your AgentMark project in two ways: pull pre-configured models from supported providers using the CLI, or define custom model schemas with full control over settings and pricing.

The model dropdown in the Dashboard prompt editor draws its options from the builtInModels and modelSchemas fields in your agentmark.json. If the dropdown is empty, your config has no models yet; add some with the steps below and they’ll appear. New projects include one model (openai/gpt-5.5) by default.

Pulling built-in models

Use the pull-models command to add models to your agentmark.json:

agentmark pull-models

Run interactively, it:

Shows you the available providers
Lets you select which models to add
Updates builtInModels in your agentmark.json

For scripts, CI, or coding agents, skip the picker with flags. List the available IDs, then add the ones you want:

# Print a provider's model IDs as JSON (no changes, no auth):
agentmark pull-models --provider anthropic --list

# Add specific models non-interactively:
agentmark pull-models --provider anthropic --models anthropic/claude-sonnet-4-5,anthropic/claude-opus-4-5

The CLI writes each pulled entry in provider/model form. For example, selecting OpenAI’s gpt-5 writes "openai/gpt-5" to builtInModels, and selecting Ollama’s llama3.1 writes "ollama/llama3.1". The tables below list the model IDs without the provider prefix for readability. The full set of models comes from AgentMark’s model registry (sourced from LiteLLM and OpenRouter). Run pull-models --provider <name> --list to print the authoritative list for each provider as JSON. The tables below highlight a handful of commonly used IDs.

Supported providers

AgentMark ships provider labels for: OpenAI, Anthropic, Google (including Vertex AI), xAI Grok, Groq, Cohere, Mistral, DeepSeek, Together AI, Ollama, Fireworks, AWS Bedrock, Azure OpenAI, and Perplexity. The tabs below show a subset with example IDs.

Language models: gpt-5, gpt-5-mini, gpt-4.1, o3, o4-mini, and moreImage models: dall-e-3, dall-e-2Speech models: tts-1, tts-1-hd, gpt-4o-mini-tts

Language models: claude-4-opus-20250514, claude-4-sonnet-20250514, claude-3-7-sonnet-20250219, claude-3-opus-20240229, claude-3-haiku-20240307, plus *-latest aliases, and more.The registry contains both dated IDs (e.g. claude-4-opus-20250514) and bare IDs (e.g. claude-opus-4, claude-3-haiku, claude-3.5-sonnet); if a bare name isn’t found, use the dated ID or -latest alias instead.

Language models: gemini-2.0-flash, gemini-2.5-pro, and more

Language models: codellama, deepseek-r1, gemma, gemma2, llama3.1, llama3.2, llava, mistral, mistral-small, mistral-small3.1, qwen, qwen2.5, tinyllama

Language models: grok-3, grok-3-mini, grok-3-fast-beta, grok-3-fast-latest, grok-2-vision, and more

Language models: llama-3.3-70b-versatile, llama-3.1-8b-instant, openai/gpt-oss-120b, moonshotai/kimi-k2-instruct-0905, qwen/qwen3-32b, meta-llama/llama-4-scout-17b-16e-instruct, and more

Pulled models land in builtInModels, an allowlist the client enforces at render time. At call time, the code that calls your SDK (your call site or executor) maps each prompt’s model_name to the model ID your SDK expects. See Model names vs provider model IDs.

Custom model schemas

For models not covered by the built-in providers, or when you need custom settings and pricing, define model schemas in your agentmark.json under modelSchemas.

Basic structure

Each model schema includes:

label: Display name shown in the AgentMark Dashboard prompt editor
cost: Pricing configuration for cost tracking
settings: Configurable parameters with UI controls

{
  "modelSchemas": {
    "my-custom-model": {
      "label": "My Custom Model",
      "cost": {
        "inputCost": 0.01,
        "outputCost": 0.03,
        "unitScale": 1000000
      },
      "settings": {}
    }
  }
}

Cost configuration

The cost object defines pricing for cost tracking:

Property	Description
`inputCost`	Cost per unit for input tokens (USD)
`outputCost`	Cost per unit for output tokens (USD)
`unitScale`	Number of tokens per unit (for example, `1000000` = cost per million tokens)

"cost": {
  "inputCost": 0.01,
  "outputCost": 0.03,
  "unitScale": 1000000
}

This means

0.01 per million input tokens and

0.03 per million output tokens.

Settings configuration

Settings define configurable parameters that appear in the Dashboard prompt editor. Each setting has:

Property	Description
`label`	Display name shown in the Dashboard
`order`	Sort order (ascending, so lower values appear first)
`default`	Default value
`type`	One of `"slider"` or `"number"` (numeric, paired with `ui: "slider"`), or `"string"` (for select, imageSize, and aspectRatio controls)
`ui`	Which control to render: `slider`, `select`, `imageSize`, or `aspectRatio`

If you omit ui, the Dashboard editor infers the control from type (for example, number renders a slider, and string with an options array renders a select). A ui value outside the supported set renders as “unsupported”. The available controls are:

Slider
Select
Image size / aspect ratio

For numeric values with a range:

"temperature": {
  "label": "Temperature",
  "order": 1,
  "default": 0.7,
  "minimum": 0,
  "maximum": 2,
  "multipleOf": 0.1,
  "type": "slider",
  "ui": "slider"
}

For dropdown selection, use type: "string" with ui: "select" and an options array:

"response_format": {
  "label": "Response format",
  "order": 3,
  "default": "json",
  "type": "string",
  "ui": "select",
  "options": [
    { "label": "JSON", "value": "json" },
    { "label": "Text", "value": "text" }
  ]
}

Specialized controls for image generation models:

"image_size": {
  "label": "Image size",
  "order": 4,
  "default": "1024x1024",
  "type": "string",
  "ui": "imageSize"
}

"aspect_ratio": {
  "label": "Aspect ratio",
  "order": 5,
  "default": "16:9",
  "type": "string",
  "ui": "aspectRatio"
}

Complete example

Here’s a full example with a text model and an image model:

agentmark.json

{
  "$schema": "https://raw.githubusercontent.com/agentmark-ai/agentmark/refs/heads/main/packages/cli/agentmark.schema.json",
  "version": "2.0.0",
  "agentmarkPath": ".",
  "modelSchemas": {
    "gpt-4-custom": {
      "label": "GPT-4 Custom",
      "cost": {
        "inputCost": 0.03,
        "outputCost": 0.06,
        "unitScale": 1000000
      },
      "settings": {
        "temperature": {
          "label": "Temperature",
          "order": 1,
          "default": 0.7,
          "minimum": 0,
          "maximum": 2,
          "multipleOf": 0.1,
          "type": "slider",
          "ui": "slider"
        },
        "max_tokens": {
          "label": "Max tokens",
          "order": 2,
          "default": 2048,
          "minimum": 1,
          "maximum": 8192,
          "multipleOf": 1,
          "type": "slider",
          "ui": "slider"
        },
        "response_format": {
          "label": "Response format",
          "order": 3,
          "default": "text",
          "type": "string",
          "ui": "select",
          "options": [
            { "label": "Text", "value": "text" },
            { "label": "JSON", "value": "json" },
            { "label": "JSON Schema", "value": "json_schema" }
          ]
        }
      }
    },
    "dall-e-3": {
      "label": "DALL-E 3",
      "cost": {
        "inputCost": 0.04,
        "outputCost": 0,
        "unitScale": 1
      },
      "settings": {
        "image_size": {
          "label": "Image size",
          "order": 1,
          "default": "1024x1024",
          "type": "string",
          "ui": "imageSize"
        },
        "quality": {
          "label": "Quality",
          "order": 2,
          "default": "standard",
          "type": "string",
          "ui": "select",
          "options": [
            { "label": "Standard", "value": "standard" },
            { "label": "HD", "value": "hd" }
          ]
        }
      }
    }
  }
}

Best practices

Use descriptive labels: make it clear what each setting does in the Dashboard.
Set appropriate ranges: define minimum and maximum values that make sense for your model.
Order settings logically: lower order values appear first in the prompt editor.
Provide sensible defaults: choose default values that work well for most use cases.
Document costs accurately: match the cost configuration to your provider’s pricing.

Have questions?

Reach out any time:

Email the team at hello@agentmark.co for support
Schedule an Enterprise Demo to learn about AgentMark’s business solutions

​Pulling built-in models

​Supported providers

​Custom model schemas

​Basic structure

​Cost configuration

​Settings configuration

​Complete example

​Best practices

​Have questions?

Pulling built-in models

Supported providers

Custom model schemas

Basic structure

Cost configuration

Settings configuration

Complete example

Best practices

Have questions?