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

# API models

> See which models the DeepMask API offers and which accept images, find the model ID to send, and learn how per-token pricing works.

The DeepMask API gives you chat models from Anthropic, OpenAI, Mistral AI, and other makers through one OpenAI-compatible endpoint. Every model is hosted in the EU. To use a model, send its API model ID in the `model` field of a [chat completion request](https://documentation.deepmask.io/api/chat-completions.md).

This page lists the models, explains the **Models** tab in the app, and describes how pricing works. For current prices, check the **Models** tab, because prices update automatically.

![Models tab with models listed by maker and GPT-4o selected, showing the API model ID gpt-4o with a copy button, Input and Output rates per 1M tokens, and the note Rates include the 3% fee.](https://mintcdn.com/deepmaskgmbh/Tc7tJrGOE8MSnXNJ/images/api/models.jpg?fit=max\&auto=format\&n=Tc7tJrGOE8MSnXNJ\&q=85\&s=accd25dbe76363ddfad20842d756a86f)

Select a model to see its API model ID and its rates per 1M tokens.

## Browsing models in the app

At the bottom of the chat sidebar, click your name and choose **User Settings**. In the settings sidebar, click **API**, then select the **Models** tab.

Only organization admins can open the API settings. If you aren't an admin, use the tables under [Available models](#available-models) for model IDs and ask an admin for current rates. See [API overview](https://documentation.deepmask.io/api/overview.md) for who can use the API.

* **Model list:** Each entry shows the model name and its maker. Models are sorted by maker, then by name.
* **Search:** Type a model name, ID, or provider in the search field to filter the list.
* **Model details:** Select a model to see its maker, its name, and an EU flag. Hover over the flag to see "Hosted in the EU".
* **API model ID:** This is the exact value to send as `model`. To copy it, click the copy icon next to it (**Copy model ID**). The message "Model ID copied" confirms it.
* **Pricing:** The **Input** and **Output** rates, each **per 1M tokens**, followed by "Rates include the 3% fee."

If a model's prices aren't ready yet, the **Pricing** section shows "Prices will appear here when they’re available."

On a small screen, a dropdown replaces the model list.

### Model details while creating a key

When you create a key with **Choose models**, each model has an ⓘ button. It opens a short summary with the hosting region, **API modes**, **Context window**, **Image input**, **Tool calling**, and the same pricing. **Image input** shows **Supported** only for models that accept images through the API. Other models show **Not supported**, even if they accept images in DeepMask Chat. See [API keys](https://documentation.deepmask.io/api/keys.md) for the full flow.

![Create API key dialog with the OpenAI group at 2 of 4 models selected and GPT-4o and GPT-5.4 checked. The details for GPT-4o show OpenAI, Hosted in the EU, API modes Chat, Context window 128,000 tokens, Image input Supported, Tool calling Supported, Input and Output rates per 1M tokens, and the note Rates include the 3% fee.](https://mintcdn.com/deepmaskgmbh/Tc7tJrGOE8MSnXNJ/images/api/model-details.jpg?fit=max\&auto=format\&n=Tc7tJrGOE8MSnXNJ\&q=85\&s=02cceab8fc1853dcc742ee58588b7a43)

Click a model's ⓘ button to see whether it supports image input and tool calling, and what it costs.

## Available models

Use the value in the **API model ID** column as `model`.

* **Context window** is the value shown under **Context window** in a model's ⓘ details when you create a key. For some models, the provider accepts longer prompts than this value.
* **Max output tokens** is the largest `max_tokens` value the API accepts for the model. A larger value is refused with `400` and the code `API_REQUEST_UNBOUNDED`. `max_completion_tokens` works as an alias with the same limit, but don't send both.
* **Image input** shows whether the model accepts images in user messages. See [Image input](#image-input).

Your prompt and the output share the context window, so a long prompt leaves less room for output. The provider can also refuse a `max_tokens` value below the maximum. A provider refusal isn't billed.

If you omit `max_tokens`, the model's default output limit applies. For `glm-4.7` and `glm-4.7-flash`, the default is 65,536 output tokens. To allow longer replies, set `max_tokens` up to the listed maximum.

For how the context window and `max_tokens` limits work, see [Token limits](https://documentation.deepmask.io/api/limits.md#token-limits).

Some models ignore some sampling options, such as `top_p` or `seed`, without returning an error. `haiku-4.5`, `sonnet-4.5`, `opus-4.5`, `opus-4.6`, and `sonnet-4.6` accept `temperature` only from 0 to 1. So do `deepseek-v3.2`, `glm-4.7`, `glm-4.7-flash`, `glm-5`, `kimi-k2.5`, `minimax-m2.1`, `minimax-m2.5`, `nemotron-3-super`, and `qwen3-235b-2507`. The provider refuses a higher value with `API_UPSTREAM_REJECTED`. That refusal isn't billed. See [Options that some models ignore](https://documentation.deepmask.io/api/chat-completions.md#options-that-some-models-ignore).

### Anthropic

| API model ID | Name | Context window | Max output tokens | Image input | Tool calling |
| - | - | - | - | - | - |
| `haiku-4.5` | Haiku 4.5 | 200,000 | 64,000 | Yes | Yes |
| `haiku-5.5` | Haiku 5.5 | 1,000,000 | 128,000 | No | Yes |
| `opus-4.5` | Opus 4.5 | 200,000 | 64,000 | Yes | Yes |
| `opus-4.6` | Opus 4.6 | 200,000 | 128,000 | Yes | Yes |
| `opus-4.7` | Opus 4.7 | 1,000,000 | 128,000 | No | Yes |
| `opus-4.8` | Opus 4.8 | 1,000,000 | 128,000 | No | Yes |
| `opus-5` | Opus 5 | 1,000,000 | 128,000 | No | Yes |
| `opus-5.5` | Opus 5.5 | 1,000,000 | 128,000 | No | Yes |
| `sonnet-4.5` | Sonnet 4.5 | 200,000 | 64,000 | Yes | Yes |
| `sonnet-4.6` | Sonnet 4.6 | 200,000 | 128,000 | Yes | Yes |
| `sonnet-5` | Sonnet 5 | 1,000,000 | 128,000 | No | Yes |
| `sonnet-5.5` | Sonnet 5.5 | 1,000,000 | 128,000 | No | Yes |

### OpenAI

| API model ID | Name | Context window | Max output tokens | Image input | Tool calling |
| - | - | - | - | - | - |
| `gpt-4.1` | GPT-4.1 | 300,000 | 32,768 | Yes | Yes |
| `gpt-4o` | GPT-4o | 128,000 | 16,384 | Yes | Yes |
| `gpt-5.4` | GPT-5.4 | 272,000 | 128,000 | No | Yes |
| `o3-mini` | GPT-o3 Mini | 200,000 | 100,000 | No | Yes |

### Other makers

| API model ID | Name | Maker | Context window | Max output tokens | Image input | Tool calling |
| - | - | - | - | - | - | - |
| `qwen3-235b-2507` | Qwen3 235B (2507) | Alibaba | 262,144 | 262,144 | No | Yes |
| `deepseek-v3.2` | DeepSeek V3.2 | DeepSeek | 164,000 | 164,000 | No | Yes |
| `minimax-m2.1` | MiniMax M2.1 | MiniMax | 196,608 | 196,608 | No | Yes |
| `minimax-m2.5` | MiniMax M2.5 | MiniMax | 196,608 | 196,608 | No | Yes |
| `mistral-large-3` | Mistral Large 3 | Mistral AI | 128,000 | 128,000 | No | Yes |
| `kimi-k2.5` | Kimi K2.5 | Moonshot AI | 262,144 | 262,144 | No | Yes |
| `nemotron-3-super` | Nemotron 3 Super | NVIDIA | 262,144 | 262,144 | No | Yes |
| `glm-4.7` | GLM 4.7 | Z.AI | 202,752 | 202,752 | No | Yes |
| `glm-4.7-flash` | GLM 4.7 Flash | Z.AI | 202,752 | 202,752 | No | Yes |
| `glm-5` | GLM-5 | Z.AI | 200,000 | 200,000 | No | Yes |

> [!NOTE]
>
> `deepseek-v3.2` may refuse `max_tokens` values above 8,000 with `API_UPSTREAM_REJECTED`. That refusal isn't billed.

The provider enforces the model's actual context window. If a prompt is too long for the model, the provider refuses the request and you aren't billed. See [Provider errors](https://documentation.deepmask.io/api/errors.md#provider-errors-4xx-502-or-503) for the error code.

> [!NOTE]
>
> The API catalog differs from the models in DeepMask Chat. For Chat models, see [AI models](https://documentation.deepmask.io/models/overview.md).

## Image input

Seven models accept images: `gpt-4o`, `gpt-4.1`, `haiku-4.5`, `sonnet-4.5`, `opus-4.5`, `opus-4.6`, and `sonnet-4.6`. You send each image as a base64 data URL in a user message. Image links are refused and never downloaded. Other models refuse a valid image part with `400` and the code `API_IMAGE_INPUT_UNSUPPORTED`. Images are billed as input tokens, with no separate price.

To send an image, see the example in [Send an image](https://documentation.deepmask.io/api/chat-completions.md#send-an-image). For the formats and the limits for each model, see [Image data](https://documentation.deepmask.io/api/chat-completions.md#image-data) and [Image limits](https://documentation.deepmask.io/api/chat-completions.md#image-limits).

Content arrays that hold only text parts work on every model. For the content rules of each role, see [Messages](https://documentation.deepmask.io/api/chat-completions.md#messages).

## Tool calling

Every model supports function tool calling. The allowed `tool_choice` values and support for `parallel_tool_calls` differ by model. See [Model-specific tool restrictions](https://documentation.deepmask.io/api/chat-completions.md#model-specific-tool-restrictions) before you set either field.

## Listing models with the API

`GET /v1/models` returns the models that the calling key may use. It doesn't return the full catalog. The list is sorted by model ID. It doesn't show which models accept images, so use the tables under [Available models](#available-models) for that.

```bash cURL theme={null}
curl https://api.deepmask.io/v1/models \
  -H "Authorization: Bearer $DEEPMASK_API_KEY"
```

* A request for a model the key can't use returns `403` with the code `API_MODEL_NOT_ALLOWED`.
* A model removed from the catalog disappears from the list, even if the key was granted it.

For SDK examples and the response format, see [List models](https://documentation.deepmask.io/api/chat-completions.md#list-models).

### New models and existing keys

New models aren't added to existing keys. This also applies to keys created with **All current models**, which notes "Excludes future models." You can't change a key's models after you create it. To use a new model, create a new key that includes it. See [API keys](https://documentation.deepmask.io/api/keys.md).

## How pricing works

You pay for the tokens each request uses, at the model's rates. Rates are in euros per 1M tokens. The **Models** tab shows each model's current **Input** and **Output** rates.

| Unit | What it counts |
| - | - |
| **Input** | Tokens in your prompt, including messages, images, and tool definitions. Images have no separate price. |
| **Output** | Tokens the model generates, including tool call arguments and hidden reasoning. |
| **Cached input** | Prompt tokens served from the provider's cache, on models that cache prompts. They're billed at a lower rate than **Input**. The app doesn't show this rate. |

* **The fee is included:** Rates on the **Models** tab already include the 3% fee. The fee isn't added again on top. VAT isn't included. Your invoice adds it where applicable. See [What you pay](https://documentation.deepmask.io/api/billing.md#what-you-pay).
* **Rounding:** The app rounds rates for display. Billing uses the exact rates.
* **Prices change:** DeepMask updates API prices automatically. Each request is billed at the rate that applied when it ran. If you've had the page open for a while, click **Refresh** to see the latest rates.
* **Spending caps:** Caps measure model costs before the fee and tax. See [Spending caps](https://documentation.deepmask.io/api/spending-caps.md).
* **Content filter answers are billed:** `opus-4.7`, `opus-4.8`, `opus-5`, `opus-5.5`, `sonnet-5`, `sonnet-5.5`, and `haiku-5.5` can decline a request through the provider's safety classifiers. The response has `finish_reason: "content_filter"` and is billed like any other response.

For how charges reach your invoice, see [Billing](https://documentation.deepmask.io/api/billing.md). To track what you've spent this month, see [Usage and logs](https://documentation.deepmask.io/api/usage-and-logs.md).

### Long-prompt pricing

Two models charge higher rates for long prompts. Once a prompt is over the threshold, the whole request is billed at the higher rates.

| Model | Higher rates apply to prompts over |
| - | - |
| `gpt-5.4` | 272,000 tokens |
| `haiku-5.5` | 100,000 tokens |

For `gpt-5.4`, the **Context window** in the app (272,000 tokens) is the limit for standard rates. Longer prompts are accepted and billed at the long-prompt rates.

For these models, the **Models** tab shows **Input** and **Output** as a range. The lower value is the standard rate and the higher value is the long-prompt rate.

### Cached input

The OpenAI models (`gpt-4.1`, `gpt-4o`, `gpt-5.4`, and `o3-mini`) cache prompts of 1,024 tokens or more automatically. Prompt tokens served from the cache are billed at a lower cached-input rate instead of the **Input** rate. On `gpt-4o` and `gpt-4.1`, images you send again, for example in the conversation history, can also be served from the cache. You don't need to change your requests.

The Anthropic models, `mistral-large-3`, and the models from Alibaba, DeepSeek, MiniMax, Moonshot AI, NVIDIA, and Z.AI don't bill cached input. Every prompt token is billed at the **Input** rate.

Anthropic prompt caching isn't available through the API. A `cache_control` field on a text part is refused with `400` and the code `API_REQUEST_UNBOUNDED`. On an image part, it's refused with `400` and the code `API_IMAGE_INVALID`. So you can't mark content for caching.

### Reasoning and thinking tokens

If a model reasons before it answers, its hidden reasoning tokens count toward `max_tokens` and are billed as output tokens. This includes reasoning models such as `o3-mini` and the Claude models that always think: `opus-5`, `opus-5.5`, `sonnet-5`, `sonnet-5.5`, and `haiku-5.5`. You can't turn thinking off for these Claude models.

> [!TIP]
>
> When you set `max_tokens` for these models, leave room for both the reasoning and the answer. See [Output length](https://documentation.deepmask.io/api/chat-completions.md#output-length).

## Next steps

> [card] [Chat completions](https://documentation.deepmask.io/api/chat-completions.md)
>
> Send requests to a model, including streaming and tools.

> [card] [API keys](https://documentation.deepmask.io/api/keys.md)
>
> Create keys and choose which models each key can use.

> [card] [Limits and fair use](https://documentation.deepmask.io/api/limits.md)
>
> See the rate, token, and budget limits that apply to your requests.

> [card] [Billing](https://documentation.deepmask.io/api/billing.md)
>
> Enable API billing and read your monthly invoices.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.