> ## Documentation Index
> Fetch the complete documentation index at: https://docs.galtea.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Create Model

> Create a new model for cost tracking.

## Returns

Returns a [Model](/concepts/model) object for the given parameters, or `None` if an error occurs.

## Example

```python theme={"system"}
model = galtea.models.create(
    name="gpt-5.5-pro " + run_identifier,
    input_cost_per_token=0.00001,
    output_cost_per_token=0.00003,
    cache_read_input_token_cost=0.000005,
    cache_creation_input_token_cost=0.0000125,
    tokenizer_provider="OpenAI",
    source="https://openai.com/api/pricing/",
)
```

## Parameters

<ResponseField name="name" type="string" required>
  Name of the model. Must be unique within your organization.
</ResponseField>

<ResponseField name="input_cost_per_token" type="float" optional>
  Cost in dollars per input token.
</ResponseField>

<ResponseField name="output_cost_per_token" type="float" optional>
  Cost in dollars per output token.
</ResponseField>

<ResponseField name="cache_read_input_token_cost" type="float" optional>
  Cost in dollars per cached input token. Some providers offer reduced rates for cached requests.
</ResponseField>

<ResponseField name="cache_creation_input_token_cost" type="float" optional>
  Cost in dollars per input token when creating a cache entry.
</ResponseField>

<ResponseField name="input_cost_per_token_above_128k_tokens" type="float" optional>
  Cost in dollars per input token for contexts larger than 128k tokens, if applicable.
</ResponseField>

<ResponseField name="output_cost_per_token_above_128k_tokens" type="float" optional>
  Cost in dollars per output token for contexts larger than 128k tokens, if applicable.
</ResponseField>

<ResponseField name="tokenizer_provider" type="string" optional>
  Provider of the tokenizer used by the model. Examples: `"OpenAI"` (uses [tiktoken](https://github.com/openai/tiktoken)), `"Anthropic"` (uses [anthropic-tokenizer](https://lunary.ai/anthropic-tokenizer)).
</ResponseField>

<ResponseField name="source" type="string" optional>
  The provider or source of the pricing model. This can be a URL to the model's pricing page or documentation (e.g., `https://openai.com/api/pricing/`).
</ResponseField>