> For the complete documentation index, see [llms.txt](https://docs.ionos.com/cloud/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ionos.com/cloud/api-reference/ai/ai-model-hub/models-1.md).

# Models

## The CompletionRequest object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"CompletionRequest":{"type":"object","properties":{"model":{"type":"string","description":"ID of the model to use."},"prompt":{"description":"The prompt to generate completions for. Either a single string, or an array of\nstrings to complete independently in one request. The response then carries one\nchoice per prompt, in the order given.\n\nThe model continues the prompt as plain text, without a chat template. A model that\nonly works in its own chat format, for example `openai/gpt-oss-120b`, rarely stops\non its own when given a plain prompt and generates until `max_tokens`. Use\n`/v1/chat/completions` for such a model.\n","oneOf":[{"type":"string"},{"type":"array","minItems":1,"items":{"type":"string"}}]},"temperature":{"type":"number","description":"Sampling temperature between 0 and 2. Higher values produce more random output.","minimum":0,"maximum":2},"top_p":{"type":"number","description":"Nucleus sampling probability mass, greater than 0 and at most 1. A value outside\nthat range, including exactly 0, is rejected with a 400.\n","exclusiveMinimum":true,"minimum":0,"maximum":1},"n":{"type":"integer","description":"Number of completions to generate. When omitted, the model chooses.","minimum":1},"stream":{"type":"boolean","description":"If true, stream partial results as Server-Sent Events.","default":false},"stop":{"description":"Up to 4 sequences at which generation stops.","oneOf":[{"type":"string"},{"type":"array","maxItems":4,"items":{"type":"string"}}]},"max_tokens":{"type":"integer","description":"Maximum number of tokens to generate. When omitted, the model chooses. The models\nin the catalog stop after 16 tokens, as OpenAI's completions API does.\n","minimum":1},"presence_penalty":{"type":"number","description":"Penalize tokens that have appeared so far in the text.","minimum":-2,"maximum":2},"frequency_penalty":{"type":"number","description":"Penalize tokens based on their frequency in the text.","minimum":-2,"maximum":2},"logit_bias":{"type":"object","description":"Per-token likelihood adjustment, keyed by token ID. OpenAI defines values from -100\n(effectively banned) to 100 (effectively required). The accepted range and its\neffect are model-specific.\n","additionalProperties":{"type":"integer"}},"user":{"type":"string","description":"Opaque identifier for your end user."},"stream_options":{"type":"object","description":"Options for streaming. Applies only when `stream` is true.","properties":{"include_usage":{"type":"boolean","description":"If true, the final SSE chunk includes a `usage` field with token counts."}}},"logprobs":{"type":"integer","nullable":true,"description":"Include the log probabilities of this many most-likely tokens, when set.","minimum":0},"suffix":{"type":"string","description":"Text to append after the completion. Support is model-specific."},"seed":{"type":"integer","description":"Seed for deterministic sampling. Repeated requests with the same seed and\nparameters return the same completion on a best-effort basis. Support is\nmodel-specific.\n"},"echo":{"type":"boolean","description":"If true, the prompt is echoed back at the start of the generated text. Support is\nmodel-specific.\n"}},"required":["model","prompt"],"description":"Request body for `POST /v1/completions` (OpenAI Completions API)."}}}}
```

## The ChatCompletionRequest object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ChatCompletionRequest":{"type":"object","properties":{"model":{"type":"string","description":"ID of the model to use."},"messages":{"type":"array","items":{"$ref":"#/components/schemas/ChatCompletionMessage"},"description":"List of messages forming the conversation so far. At most 500 messages. A longer\nconversation is rejected with a 413.\n","minItems":1,"maxItems":500},"response_format":{"description":"The format the model must output. Which formats a model supports is\nmodel-specific.\n","oneOf":[{"$ref":"#/components/schemas/ResponseFormatText"},{"$ref":"#/components/schemas/ResponseFormatJsonObject"},{"$ref":"#/components/schemas/ResponseFormatJsonSchema"}]},"temperature":{"type":"number","description":"Sampling temperature between 0 and 2.","minimum":0,"maximum":2},"top_p":{"type":"number","description":"Nucleus sampling probability mass, greater than 0 and at most 1. A value outside\nthat range, including exactly 0, is rejected with a 400.\n","minimum":0,"exclusiveMinimum":true,"maximum":1},"n":{"type":"integer","description":"Number of chat completion choices to generate. When omitted, the model chooses.","minimum":1},"stream":{"default":false,"type":"boolean","description":"If true, stream partial results as Server-Sent Events."},"stop":{"description":"Up to 4 sequences at which generation stops.","oneOf":[{"type":"string"},{"type":"array","maxItems":4,"items":{"type":"string"}}]},"max_tokens":{"type":"integer","description":"Maximum number of tokens to generate. For a reasoning model, the reasoning counts\ntoward this limit and comes before the answer. If the limit is reached while the\nmodel is still reasoning, the response has `finish_reason` `length`, an empty\n`content`, and the reasoning so far in `reasoning`. A lower `reasoning_effort`\nleaves more of the limit for the answer.\n","minimum":1},"max_completion_tokens":{"type":"integer","description":"Maximum number of tokens to generate, including any reasoning, as for `max_tokens`.\nOpenAI's replacement for the deprecated `max_tokens`. Avoid setting both in one\nrequest: which of the two applies is model-specific. The accepted range is\nmodel-specific.\n"},"presence_penalty":{"type":"number","description":"Penalize tokens that have appeared so far in the text.","minimum":-2,"maximum":2},"frequency_penalty":{"type":"number","description":"Penalize tokens based on their frequency in the text.","minimum":-2,"maximum":2},"logit_bias":{"type":"object","description":"Per-token likelihood adjustment, keyed by token ID. OpenAI defines values from -100\n(effectively banned) to 100 (effectively required). The accepted range and its\neffect are model-specific.\n","additionalProperties":{"type":"integer"}},"logprobs":{"type":"boolean","description":"Whether to return log probabilities of the output tokens."},"top_logprobs":{"type":"integer","description":"Number of most-likely tokens to return at each position, when `logprobs` is true.","minimum":0,"maximum":20},"user":{"type":"string","description":"Opaque identifier for your end user."},"reasoning_effort":{"type":"string","description":"How much reasoning to do before answering, for reasoning-capable models. Accepted\nvalues are model-specific. A value the model does not accept is rejected with a 400.\n"},"tools":{"type":"array","description":"List of tools the model may call.","items":{"$ref":"#/components/schemas/ChatCompletionTool"}},"tool_choice":{"description":"Controls which tool, if any, the model calls. `none` means no tool call, `auto` lets\nthe model decide, and `required` forces a tool call. A named tool object forces a\nspecific function.\n\nWhich values a model honors is model-specific. A model may answer with a normal\nmessage instead of the tool call that `required` or a named function asks for. The\nvalue is not checked, so how any other value is answered is also model-specific.\n","oneOf":[{"type":"string","enum":["none","auto","required"]},{"$ref":"#/components/schemas/ChatCompletionNamedToolChoice"}]},"stream_options":{"type":"object","description":"Options for streaming. Applies only when `stream` is true.","properties":{"include_usage":{"type":"boolean","description":"If true, the final SSE chunk includes a `usage` field with token counts."}}},"seed":{"type":"integer","description":"Seed for deterministic sampling. Repeated requests with the same seed and\nparameters return the same completion on a best-effort basis. Support is\nmodel-specific.\n"},"parallel_tool_calls":{"type":"boolean","description":"Whether the model may emit more than one tool call in a single turn. Whether it is\nhonored is model-specific.\n"}},"required":["model","messages"],"description":"Request body for `POST /v1/chat/completions` (OpenAI Chat Completions API)."},"ChatCompletionMessage":{"type":"object","description":"A single message in the conversation.\n\n`content` is required on every message except an `assistant` message carrying\n`tool_calls`, which the OpenAI schema allows to send `content` as null or omit it\nentirely. Such a message must be replayed with its `tool_calls` intact, because a\nlater `tool` message's `tool_call_id` is matched against them.\n","properties":{"role":{"type":"string","description":"The role of the message author. Support for `developer`, which OpenAI uses in\nplace of `system` for some models, is model-specific: a model that does not\nrecognize the role rejects the request with a 400. Use `system` for the widest\ncompatibility.\n","enum":["system","developer","user","assistant","tool"]},"content":{"oneOf":[{"type":"string"},{"type":"array","items":{"$ref":"#/components/schemas/ChatCompletionContentPart"},"minItems":1,"maxItems":2048}],"description":"Message content. Either a plain string, or an ordered array of content parts\nfor multi-modal input (text plus `image_url` parts, `video_url` parts, or both).\n\nImage and video parts are only accepted on `user` messages, and only for\nmodels advertising the matching capability. For other models, the request is\nrejected with a 400 naming the models that support it.\n"},"name":{"type":"string","description":"An optional name for the participant."},"tool_calls":{"type":"array","description":"Tool calls previously generated by the model, replayed on an `assistant` message\nwhen continuing a tool-calling conversation. Echo them back exactly as received,\nids included.\n","items":{"$ref":"#/components/schemas/ChatCompletionToolCall"},"nullable":true},"tool_call_id":{"type":"string","description":"Tool call ID this message is responding to. Required when role is `tool`."}},"required":["role"]},"ChatCompletionContentPart":{"type":"object","description":"A single content part: text, an image reference, or a video reference.","required":["type"],"properties":{"type":{"type":"string","description":"Discriminator for the content type.","enum":["text","image_url","video_url"]},"text":{"type":"string","description":"Text content when `type` is `text`."},"image_url":{"$ref":"#/components/schemas/ChatCompletionImageURL"},"video_url":{"$ref":"#/components/schemas/ChatCompletionVideoURL"}}},"ChatCompletionImageURL":{"type":"object","description":"Image reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI (`data:image/...;base64,...`) of at most 12 MiB\ndecoded.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the image."},"detail":{"type":"string","description":"Fidelity hint for image processing. Both its effect and whether it is honored at\nall are model-specific. Omit it to leave the choice to the model.\n","enum":["auto","low","high"]}}},"ChatCompletionVideoURL":{"type":"object","description":"Video reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI (`data:video/...;base64,...`) of at most 12 MiB\ndecoded. Prefer a remote URL for long clips: the whole request body is limited to\n16 MiB, and a base64 payload is about 4/3 the size of the media it carries.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the video."}}},"ChatCompletionToolCall":{"type":"object","description":"A tool call generated by the model.","required":["id","type","function"],"properties":{"id":{"type":"string","description":"Unique identifier for this tool call."},"type":{"type":"string","description":"Always `function`.","enum":["function"]},"function":{"type":"object","description":"The function the model called.","required":["name","arguments"],"properties":{"name":{"type":"string","description":"The name of the function to call."},"arguments":{"type":"string","description":"JSON-encoded arguments to pass to the function."}}}}},"ResponseFormatText":{"type":"object","properties":{"type":{"type":"string","enum":["text"]}},"required":["type"]},"ResponseFormatJsonObject":{"type":"object","required":["type"],"properties":{"type":{"type":"string","enum":["json_object"]}}},"ResponseFormatJsonSchema":{"type":"object","required":["type","json_schema"],"properties":{"type":{"type":"string","enum":["json_schema"]},"json_schema":{"type":"object","additionalProperties":true,"description":"The JSON schema the model must conform to.","required":["name","schema"],"properties":{"name":{"type":"string","description":"Identifier for the schema definition."},"schema":{"type":"object","additionalProperties":true,"description":"The JSON Schema object the output must conform to."},"strict":{"type":"boolean","description":"Whether the model must follow the schema exactly. Whether it is honored, and\nits default when omitted, are model-specific.\n"}}}}},"ChatCompletionTool":{"type":"object","description":"A tool the model may call.","required":["type","function"],"properties":{"type":{"type":"string","description":"Always `function`. The value is not checked, and how another type is answered is\nmodel-specific.\n","enum":["function"]},"function":{"type":"object","description":"The function the model may call.","required":["name"],"properties":{"name":{"type":"string","description":"The name of the function to call."},"description":{"type":"string","description":"Description of what the function does."},"parameters":{"type":"object","additionalProperties":true,"description":"The parameters the function accepts, described as a JSON Schema object."}}}}},"ChatCompletionNamedToolChoice":{"type":"object","description":"Forces the model to call a specific function.","required":["type","function"],"properties":{"type":{"type":"string","description":"Always `function`.","enum":["function"]},"function":{"type":"object","description":"The function to call.","required":["name"],"properties":{"name":{"type":"string","description":"The name of the function to call."}}}}}}}}
```

## The ChatCompletionMessage object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ChatCompletionMessage":{"type":"object","description":"A single message in the conversation.\n\n`content` is required on every message except an `assistant` message carrying\n`tool_calls`, which the OpenAI schema allows to send `content` as null or omit it\nentirely. Such a message must be replayed with its `tool_calls` intact, because a\nlater `tool` message's `tool_call_id` is matched against them.\n","properties":{"role":{"type":"string","description":"The role of the message author. Support for `developer`, which OpenAI uses in\nplace of `system` for some models, is model-specific: a model that does not\nrecognize the role rejects the request with a 400. Use `system` for the widest\ncompatibility.\n","enum":["system","developer","user","assistant","tool"]},"content":{"oneOf":[{"type":"string"},{"type":"array","items":{"$ref":"#/components/schemas/ChatCompletionContentPart"},"minItems":1,"maxItems":2048}],"description":"Message content. Either a plain string, or an ordered array of content parts\nfor multi-modal input (text plus `image_url` parts, `video_url` parts, or both).\n\nImage and video parts are only accepted on `user` messages, and only for\nmodels advertising the matching capability. For other models, the request is\nrejected with a 400 naming the models that support it.\n"},"name":{"type":"string","description":"An optional name for the participant."},"tool_calls":{"type":"array","description":"Tool calls previously generated by the model, replayed on an `assistant` message\nwhen continuing a tool-calling conversation. Echo them back exactly as received,\nids included.\n","items":{"$ref":"#/components/schemas/ChatCompletionToolCall"},"nullable":true},"tool_call_id":{"type":"string","description":"Tool call ID this message is responding to. Required when role is `tool`."}},"required":["role"]},"ChatCompletionContentPart":{"type":"object","description":"A single content part: text, an image reference, or a video reference.","required":["type"],"properties":{"type":{"type":"string","description":"Discriminator for the content type.","enum":["text","image_url","video_url"]},"text":{"type":"string","description":"Text content when `type` is `text`."},"image_url":{"$ref":"#/components/schemas/ChatCompletionImageURL"},"video_url":{"$ref":"#/components/schemas/ChatCompletionVideoURL"}}},"ChatCompletionImageURL":{"type":"object","description":"Image reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI (`data:image/...;base64,...`) of at most 12 MiB\ndecoded.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the image."},"detail":{"type":"string","description":"Fidelity hint for image processing. Both its effect and whether it is honored at\nall are model-specific. Omit it to leave the choice to the model.\n","enum":["auto","low","high"]}}},"ChatCompletionVideoURL":{"type":"object","description":"Video reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI (`data:video/...;base64,...`) of at most 12 MiB\ndecoded. Prefer a remote URL for long clips: the whole request body is limited to\n16 MiB, and a base64 payload is about 4/3 the size of the media it carries.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the video."}}},"ChatCompletionToolCall":{"type":"object","description":"A tool call generated by the model.","required":["id","type","function"],"properties":{"id":{"type":"string","description":"Unique identifier for this tool call."},"type":{"type":"string","description":"Always `function`.","enum":["function"]},"function":{"type":"object","description":"The function the model called.","required":["name","arguments"],"properties":{"name":{"type":"string","description":"The name of the function to call."},"arguments":{"type":"string","description":"JSON-encoded arguments to pass to the function."}}}}}}}}
```

## The ChatCompletionContentPart object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ChatCompletionContentPart":{"type":"object","description":"A single content part: text, an image reference, or a video reference.","required":["type"],"properties":{"type":{"type":"string","description":"Discriminator for the content type.","enum":["text","image_url","video_url"]},"text":{"type":"string","description":"Text content when `type` is `text`."},"image_url":{"$ref":"#/components/schemas/ChatCompletionImageURL"},"video_url":{"$ref":"#/components/schemas/ChatCompletionVideoURL"}}},"ChatCompletionImageURL":{"type":"object","description":"Image reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI (`data:image/...;base64,...`) of at most 12 MiB\ndecoded.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the image."},"detail":{"type":"string","description":"Fidelity hint for image processing. Both its effect and whether it is honored at\nall are model-specific. Omit it to leave the choice to the model.\n","enum":["auto","low","high"]}}},"ChatCompletionVideoURL":{"type":"object","description":"Video reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI (`data:video/...;base64,...`) of at most 12 MiB\ndecoded. Prefer a remote URL for long clips: the whole request body is limited to\n16 MiB, and a base64 payload is about 4/3 the size of the media it carries.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the video."}}}}}}
```

## The ImageGenerationRequest object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ImageGenerationRequest":{"type":"object","properties":{"model":{"type":"string","description":"ID of the model to use.","minLength":1},"prompt":{"type":"string","description":"Text description of the images to generate.","minLength":1},"n":{"type":"integer","minimum":1,"maximum":10,"description":"Number of images to generate, at most 10. A larger value is rejected with a 413.\nA model may also limit the total pixels one request may produce. See `size`. When\nomitted, the model chooses.\n"},"size":{"$ref":"#/components/schemas/ImageSize"},"output_format":{"$ref":"#/components/schemas/ImageOutputFormat"},"response_format":{"type":"string","description":"Format of the returned images. `b64_json` returns the image data inline and is\nthe only format this API serves. Images are not published at a fetchable address,\nso OpenAI's `url` is rejected with a 400.\n","enum":["b64_json"],"default":"b64_json"},"quality":{"type":"string","description":"Rendering quality of the generated images. Accepted values and their effect are\nmodel-specific.\n"},"style":{"type":"string","description":"Style of the generated images. Accepted values and their effect are\nmodel-specific.\n"}},"required":["model","prompt"],"description":"Request payload for generating images from a text prompt."},"ImageSize":{"type":"string","description":"Size of the generated images as `WIDTHxHEIGHT` in pixels, for example `1024x1024`. A\nside smaller than 1 or larger than 8192 pixels is rejected with a 413.\n\nWithin that, the sizes served are model-specific: a model may accept only a range of\nsizes, round each side to a step of its own, and limit the pixels one request may\nproduce (`n` times width times height). A request outside a model's limits is\nrejected with a 400 whose message states the limit.\n\nWhen omitted, the model chooses the size.\n"},"ImageOutputFormat":{"type":"string","description":"File format of the returned image, for example `png` or `jpeg`. Distinct from\n`response_format`, which controls how the image is delivered rather than what it\nis encoded as. Supported formats are model-specific. An unsupported value is rejected\nwith a 400 whose message states the supported formats.\n"}}}}
```

## The ImageEditRequest object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ImageEditRequest":{"type":"object","properties":{"url":{"type":"string","description":"The image to edit, given by reference instead of uploaded: an HTTP or HTTPS URL or a base64 data URL. Accepted as an alternative to `image` for compatibility with earlier versions of this API. Either this or `image` is required, and sending both is rejected."},"prompt":{"type":"string","description":"Text description of the desired edit.","minLength":1},"mask_image":{"type":"string","description":"The mask, given by reference instead of uploaded, in the same forms as `url`. Accepted as an alternative to `mask`."},"model":{"type":"string","description":"ID of the model to use.","minLength":1},"n":{"type":"integer","minimum":1,"maximum":10,"description":"Number of edited images to generate, at most 10. A larger value is rejected with a\n413. A model may also limit the total pixels one request may produce. See `size`.\nWhen omitted, the model chooses.\n"},"size":{"$ref":"#/components/schemas/ImageSize"},"output_format":{"$ref":"#/components/schemas/ImageOutputFormat"},"image":{"type":"string","format":"binary","description":"The image to edit, uploaded as a file part. Must be a PNG, JPEG, or WebP image of at most 10 MiB. A larger file is rejected with a 413. Either this or `url` is required, and sending both is rejected. Which images a model can edit (for example a minimum size or aspect ratio) is model-specific. An image outside a model's limits is rejected with a 400 whose message states the limit."},"mask":{"type":"string","format":"binary","description":"An additional image whose transparent areas indicate where to edit `image`. At\nmost 10 MiB. Whether the mask must match the dimensions of `image` is\nmodel-specific.\n"},"response_format":{"type":"string","description":"Format of the returned images. `b64_json` returns the image data inline and is\nthe only format this API serves. Images are not published at a fetchable address,\nso OpenAI's `url` is rejected with a 400.\n","enum":["b64_json"],"default":"b64_json"}},"required":["model","prompt"],"description":"Request payload for editing an existing image. Sent as `multipart/form-data`.\nThe source image is given either as the binary file part `image`, which is the\nOpenAI shape, or by reference as the text field `url`. The mask follows the\nsame pair, `mask` or `mask_image`, and must be given the same way the image\nwas: an uploaded mask alongside a referenced image, or the reverse, is\nrejected rather than silently dropped.\n\nExactly one of `image` or `url` is required. Sending neither, or both, is\nrejected with a 400 whose message names both fields.\n"},"ImageSize":{"type":"string","description":"Size of the generated images as `WIDTHxHEIGHT` in pixels, for example `1024x1024`. A\nside smaller than 1 or larger than 8192 pixels is rejected with a 413.\n\nWithin that, the sizes served are model-specific: a model may accept only a range of\nsizes, round each side to a step of its own, and limit the pixels one request may\nproduce (`n` times width times height). A request outside a model's limits is\nrejected with a 400 whose message states the limit.\n\nWhen omitted, the model chooses the size.\n"},"ImageOutputFormat":{"type":"string","description":"File format of the returned image, for example `png` or `jpeg`. Distinct from\n`response_format`, which controls how the image is delivered rather than what it\nis encoded as. Supported formats are model-specific. An unsupported value is rejected\nwith a 400 whose message states the supported formats.\n"}}}}
```

## The EmbeddingRequest object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"EmbeddingRequest":{"type":"object","properties":{"model":{"type":"string","description":"ID of the model to use.","minLength":1},"input":{"oneOf":[{"type":"string","minLength":1},{"type":"array","items":{"type":"string","minLength":1},"minItems":1,"maxItems":2048}],"description":"Text input. Either a single string or an array of up to 2048 strings.\nEach string must be non-empty. Mutually exclusive with `messages`.\n"},"messages":{"type":"array","description":"Multi-modal input: one `user` turn with `text`, `image_url`, or `video_url` content\nparts. Produces exactly one embedding per request. Mutually exclusive with `input`.\n","items":{"$ref":"#/components/schemas/EmbeddingMessage"},"minItems":1,"maxItems":1},"encoding_format":{"type":"string","description":"Format of the returned embedding vectors.","enum":["float","base64"],"default":"float"},"user":{"type":"string","description":"Opaque identifier for your end user. At most 256 characters. A longer value is\nrejected with a 400.\n","maxLength":256},"dimensions":{"type":"integer","description":"Number of dimensions for the returned vectors. Whether a model can shorten its\noutput, and to which sizes, is model-specific. A value the model does not support\nis rejected with a 400.\n"}},"required":["model"],"description":"Request payload for creating embeddings. Provide either `input` (text-only, batchable)\nor `messages` (multi-modal, single embedding). The two are mutually exclusive.\n"},"EmbeddingMessage":{"type":"object","description":"A multi-modal conversation turn.","required":["role","content"],"properties":{"role":{"type":"string","description":"Author of the message. Must be `user`.","enum":["user"]},"content":{"type":"array","description":"Ordered list of content parts.","minItems":1,"maxItems":2048,"items":{"$ref":"#/components/schemas/EmbeddingContent"}}}},"EmbeddingContent":{"type":"object","description":"A single content part: text, an image reference, or a video reference.","required":["type"],"properties":{"type":{"type":"string","description":"Discriminator for the content type.","enum":["text","image_url","video_url"]},"text":{"type":"string","description":"Text content when `type` is `text`. The text is embedded, not answered: write it as\ncontent to embed, such as a caption, a title or a search query, rather than as an\ninstruction or a question about the image. It is embedded together with the other\nparts of the request into the single returned vector.\n"},"image_url":{"$ref":"#/components/schemas/EmbeddingImageURL"},"video_url":{"$ref":"#/components/schemas/EmbeddingVideoURL"}}},"EmbeddingImageURL":{"type":"object","description":"Image reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI (`data:image/...;base64,...`) of at most 12 MiB\ndecoded.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the image."}}},"EmbeddingVideoURL":{"type":"object","description":"Video reference, for models advertising video input. Either a public HTTP or HTTPS\nURL, which must be reachable from the internet, or an inline base64 data URI\n(`data:video/...;base64,...`) of at most 12 MiB decoded. Prefer a remote URL for long\nclips: the whole request body is limited to 16 MiB, and a base64 payload is about 4/3\nthe size of the media it carries.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the video."}}}}}}
```

## The EmbeddingResponse object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"EmbeddingResponse":{"type":"object","properties":{"model":{"type":"string","description":"Model identifier used to produce the embeddings."},"object":{"type":"string","description":"Always `list`.","enum":["list"]},"data":{"type":"array","description":"One `EmbeddingObject` per input string (or a single object for multi-modal requests).","items":{"$ref":"#/components/schemas/EmbeddingObject"}},"usage":{"$ref":"#/components/schemas/EmbeddingUsage"}},"description":"Response containing one or more embeddings.","required":["object","data","model","usage"]},"EmbeddingObject":{"type":"object","description":"A single embedding result.","required":["object","index","embedding"],"properties":{"object":{"type":"string","description":"Always `embedding`.","enum":["embedding"]},"index":{"type":"integer","description":"Zero-based index matching the position of the input that produced this embedding.","minimum":0},"embedding":{"description":"Embedding vector. When `encoding_format` is `float`, an array of floating-point numbers.\nWhen `encoding_format` is `base64`, a base64-encoded little-endian float32 byte string.\n","oneOf":[{"type":"array","items":{"type":"number"}},{"type":"string"}]}}},"EmbeddingUsage":{"type":"object","properties":{"prompt_tokens":{"type":"integer","description":"Number of tokens consumed by the prompt.","minimum":0},"total_tokens":{"type":"integer","description":"Total tokens consumed by the request. Equal to `prompt_tokens` for embeddings.","minimum":0}},"description":"Token-based usage statistics for the embeddings request.","required":["prompt_tokens","total_tokens"]}}}}
```

## The EmbeddingUsage object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"EmbeddingUsage":{"type":"object","properties":{"prompt_tokens":{"type":"integer","description":"Number of tokens consumed by the prompt.","minimum":0},"total_tokens":{"type":"integer","description":"Total tokens consumed by the request. Equal to `prompt_tokens` for embeddings.","minimum":0}},"description":"Token-based usage statistics for the embeddings request.","required":["prompt_tokens","total_tokens"]}}}}
```

## The Error object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"Error":{"type":"object","description":"Error response.","properties":{"httpStatus":{"type":"integer","description":"HTTP status code of the operation as specified by RFC 7231."},"messages":{"type":"array","description":"List of error messages.","items":{"type":"object","properties":{"errorCode":{"type":"string","description":"Stable, machine-readable classification of the failure. Branch on this\nrather than on `message`, which is meant for humans and may be reworded.\n\nClient errors, safe to act on:\n\n- `VALIDATION_ERROR` (400) a field is missing, malformed or out of the\n  documented range. The message names the field.\n- `INVALID_JSON` (400) the body is not valid JSON.\n- `INVALID_MULTIPART` (400) the multipart form could not be parsed.\n- `INVALID_TOKEN` (401) the `Authorization` header is larger than 8 KiB.\n  Every other 401 carries one of the authentication codes instead:\n  `paas-auth-1` (the `Authorization` header is missing or does not hold a\n  `Bearer` token), `paas-token-1` (the token was not accepted) or\n  `paas-auth-2` (the token could not be verified as a customer token).\n- `INSUFFICIENT_PRIVILEGES` (403) the token is valid but its contract\n  lacks the privilege required to use this API.\n- `MODEL_NOT_SUPPORTED` (404) the model is unknown. A known model that lacks\n  the capability this endpoint or request needs is rejected with a 400\n  `VALIDATION_ERROR` naming the models that have it.\n- `ROUTE_NOT_FOUND` (404) no endpoint exists at the requested path.\n- `METHOD_NOT_ALLOWED` (405) the endpoint exists but does not accept the\n  HTTP method used.\n- `RESOURCE_LIMIT_ERROR` (413) the request exceeds a documented size or\n  count limit.\n- `RATE_LIMIT_EXCEEDED` (429) the contract's rate limit is exhausted.\n  Wait the number of seconds in `Retry-After` before retrying.\n- `SERVICE_OVERLOADED` (503) too many large requests are already being\n  handled at once. Applies only above a size threshold, or to a request\n  sent with chunked transfer encoding. An ordinary request is never\n  refused this way. Retry after the interval in `Retry-After`.\n- `CLIENT_DISCONNECTED` (499) you closed the connection before the\n  response was ready. You never receive this code, since the connection\n  is already gone. It identifies the request in usage records. Tokens\n  generated before the disconnect are still billed.\n\nThe model refused or could not be reached:\n\n- `UPSTREAM_REJECTED` the model rejected the request. The status is the\n  one it returned, and the message carries its explanation. Usually a 4xx\n  and usually worth fixing rather than retrying. An image or video URL in\n  the request that answers with a client error, such as 404, comes back\n  as 422 with this code: check that the URL exists and is publicly\n  reachable.\n- `UPSTREAM_NOT_IMPLEMENTED` (422) the model understood the request and\n  does not implement part of it. Retrying does not help. The same request\n  may succeed against a different model.\n- `UPSTREAM_UNAVAILABLE` (502) the model could not be reached, or stopped\n  before it finished answering. Retrying is reasonable. A partial answer\n  is never returned in its place, and nothing is billed for it. An image or\n  video URL whose host cannot be reached, times out or answers with a\n  server error comes back this way too.\n- `UPSTREAM_TIMEOUT` (504) the model did not answer within the time allowed\n  for it. The work may have been too expensive:\n  prefer a smaller request or a different model over retrying the same\n  one unchanged.\n\nAn internal error occurred (500). The code identifies where it happened\nand is not a contract to branch on. Treat these alike:\n`CHAT_COMPLETION_ERROR`, `COMPLETION_ERROR`, `EMBEDDING_ERROR`,\n`IMAGE_ERROR`, `RERANK_ERROR`, `RESPONSES_ERROR`, `TRANSCRIPTION_ERROR`,\n`CONVERSION_ERROR`.\n\nNew codes may be added, so treat an unrecognized value as a generic\nfailure of its HTTP status class rather than rejecting the response.\n"},"message":{"type":"string","description":"Human-readable explanation, intended for logs and for showing to a\ndeveloper. Wording may change between releases, so branch on `errorCode`.\n"}},"additionalProperties":false}}},"required":["httpStatus","messages"],"additionalProperties":false}}}}
```

## The ResponsesRequest object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesRequest":{"type":"object","description":"Request body for `POST /v1/responses`. A subset of the OpenAI Responses API. See the\nendpoint description for its limitations.\n","properties":{"model":{"type":"string","description":"ID of the model to use."},"input":{"description":"Either a single text string (shorthand for a single user message), or an ordered\nlist of input items: messages and, for multi-turn tool use, the `function_call` and\n`function_call_output` items from earlier turns.\n","oneOf":[{"type":"string"},{"type":"array","minItems":1,"items":{"$ref":"#/components/schemas/ResponsesInputItem"}}]},"instructions":{"type":"string","description":"System-level instructions prepended to the conversation as a developer message."},"max_output_tokens":{"type":"integer","description":"Maximum number of tokens to generate, including reasoning and tool call tokens.\nWhen the output reaches it, `status` is `incomplete` and `incomplete_details.reason`\nis `max_output_tokens`.\n","minimum":1},"temperature":{"description":"Sampling temperature between 0 and 2.","type":"number","minimum":0,"maximum":2},"top_p":{"description":"Nucleus sampling probability mass, greater than 0 and at most 1. A value outside\nthat range, including exactly 0, is rejected with a 400.\n","type":"number","minimum":0,"exclusiveMinimum":true,"maximum":1},"presence_penalty":{"description":"Penalizes tokens that have already appeared, encouraging new topics.","type":"number","minimum":-2,"maximum":2},"frequency_penalty":{"description":"Penalizes tokens by how often they have appeared so far.","type":"number","minimum":-2,"maximum":2},"top_logprobs":{"description":"Number of most-likely tokens to return log probabilities for at each position.","type":"integer","minimum":0,"maximum":20},"stop":{"description":"Up to 4 sequences where generation stops. The stop text is not included in the\noutput. Same semantics as `stop` on `/v1/chat/completions`.\n","oneOf":[{"type":"string"},{"type":"array","maxItems":4,"items":{"type":"string"}}]},"text":{"$ref":"#/components/schemas/ResponsesTextConfig"},"reasoning":{"$ref":"#/components/schemas/ResponsesReasoningConfig"},"tools":{"type":"array","description":"List of tools the model may call.","items":{"$ref":"#/components/schemas/ResponsesTool"}},"tool_choice":{"description":"Controls which tool, if any, the model calls. `none` means no tool call, `auto` lets\nthe model decide, and `required` forces a tool call. A named tool object forces a\nspecific function.\n\nSupport for these values is model-specific. A value the model does not support is\nrejected with a 422.\n","oneOf":[{"type":"string","enum":["none","auto","required"]},{"$ref":"#/components/schemas/ResponsesNamedToolChoice"}]},"parallel_tool_calls":{"description":"Whether to allow the model to call multiple tools in parallel. When omitted, the\nmodel chooses. Whether it is honored is model-specific.\n","type":"boolean"},"user":{"type":"string","description":"Opaque identifier for your end user."},"stream":{"type":"boolean","description":"If true, stream partial results as Server-Sent Events. Not supported: a request with\n`stream: true` is rejected with a 400.\n","default":false},"store":{"type":"boolean","description":"Whether to persist the response for later retrieval. Not supported: responses are\nnot stored, so a request setting `store: true` is rejected with a 400.\n"},"background":{"type":"boolean","description":"Whether to run the request asynchronously. Not supported, because it requires\n`store`. A request setting `background: true` is rejected with a 400.\n"},"conversation":{"type":"string","description":"Conversation this response belongs to. Not supported: a request that sets it is\nrejected with a 400. Send the full conversation in `input` instead.\n"},"previous_response_id":{"type":"string","description":"Not supported. Responses are not stored, so a request containing this field is\nrejected with a 400. Send the full conversation in `input` instead.\n"}},"required":["model","input"]},"ResponsesInputItem":{"type":"object","description":"A single item in the `input` array: a conversation message or, for multi-turn tool\nuse, an earlier tool call or its result. Which fields apply depends on `type`.\n","properties":{"type":{"type":"string","enum":["message","function_call","function_call_output"],"default":"message","description":"Discriminator for the item type. Optional: when omitted the item is treated as a\n`message`, matching OpenAI, whose `EasyInputMessage` requires only `role` and\n`content`. This is the shape the OpenAI SDKs emit by default.\n"},"role":{"description":"Message author. Required when `type` is `message`. The value is not checked, and\nhow a value outside this list is answered is model-specific.\n","type":"string","enum":["system","developer","user","assistant"]},"content":{"description":"Content of the message. Required when `type` is `message`. Either a plain string,\nor an ordered array of content parts for multi-modal input.\n\nThe Responses API uses its own part names (`input_text`, `input_image`), distinct\nfrom the Chat Completions part names `text` and `image_url`. There is no video part:\nthis API defines only text and image content, so video input is available on\n`/v1/chat/completions` and `/v1/embeddings` instead.\n\nImage parts are only accepted on `user` messages, and only for models advertising\nimage input. For other models, the request is rejected with a 400 naming the\nmodels that support it.\n","oneOf":[{"type":"string"},{"type":"array","minItems":1,"items":{"$ref":"#/components/schemas/ResponsesContentPart"}}]},"call_id":{"type":"string","description":"Identifier correlating a `function_call` with its `function_call_output`. Required\nwhen `type` is `function_call` or `function_call_output`.\n"},"name":{"type":"string","description":"Name of the called function. Required when `type` is `function_call`."},"arguments":{"type":"string","description":"JSON-encoded arguments the model produced for the call. Required when `type` is\n`function_call`.\n"},"output":{"type":"string","description":"The tool's result, as a string. Required when `type` is `function_call_output`.\n"}}},"ResponsesContentPart":{"type":"object","description":"A single content part of a Responses message: text or an image reference. The\n`type` values and the flat `image_url` string differ from the Chat Completions\ncontent part shape.\n","properties":{"type":{"description":"Discriminator for the content type.","type":"string","enum":["input_text","input_image"]},"text":{"description":"Text content when `type` is `input_text`.","type":"string"},"image_url":{"description":"Image reference when `type` is `input_image`. Either a public HTTP or HTTPS URL,\nwhich must be reachable from the internet, or an inline base64 data URI\n(`data:image/...;base64,...`) of at most 12 MiB decoded. Unlike Chat Completions,\nthis is a plain string, not an object with a `url` key.\n","type":"string"},"detail":{"description":"Fidelity hint for image processing. When omitted, the model chooses. Its effect,\nand how a value outside this list is answered, are model-specific.\n","type":"string","enum":["auto","low","high"]}},"required":["type"]},"ResponsesTextConfig":{"type":"object","description":"Configuration for the model's text output, including structured outputs. This is the\nResponses API's equivalent of `response_format` on `/v1/chat/completions`.\n","properties":{"format":{"$ref":"#/components/schemas/ResponsesTextFormat"}}},"ResponsesTextFormat":{"type":"object","description":"Output format. `text` is free-form prose. `json_object` constrains the reply to valid\nJSON. `json_schema` constrains it to the supplied schema, which is the form worth\nreaching for: it is the only one that guarantees a parseable shape.\n","properties":{"type":{"description":"The output format.","type":"string","enum":["text","json_object","json_schema"]},"name":{"description":"Name of the response format. Required when `type` is `json_schema`. OpenAI allows\nup to 64 characters. The length limit applied is model-specific.\n","type":"string"},"schema":{"description":"The JSON Schema the output must conform to. Required when `type` is `json_schema`.","type":"object","additionalProperties":true},"strict":{"description":"Whether to enforce the schema exactly. Whether it is honored, and its default when\nomitted, are model-specific.\n","type":"boolean"},"description":{"description":"What the format is for, used by the model to decide how to respond.","type":"string"}},"required":["type"]},"ResponsesReasoningConfig":{"type":"object","description":"Controls how much reasoning a reasoning-capable model does before answering. This is the Responses API's own shape. `/v1/chat/completions` takes the same control as a flat `reasoning_effort` string. Accepted values are model-specific, and a value the model does not accept is rejected. Keys other than `effort` and `summary` are ignored.","properties":{"effort":{"description":"How much reasoning to do before answering. Accepted values are model-specific.","type":"string"},"summary":{"description":"Whether, and how verbosely, to summarize the reasoning. Accepted values are\nmodel-specific.\n","type":"string"}}},"ResponsesTool":{"type":"object","description":"A tool the model may call. Unlike Chat Completions, the function definition is\nflattened directly onto the tool object rather than nested under a `function` key.\n","properties":{"type":{"description":"Always `function`. Built-in tool types are not available, and how one is answered\nis model-specific.\n","type":"string","enum":["function"]},"name":{"description":"The name of the function to call.","type":"string"},"description":{"description":"Description of what the function does.","type":"string"},"parameters":{"type":"object","description":"The parameters the function accepts, described as a JSON Schema object.","additionalProperties":true},"strict":{"description":"Whether to enforce strict schema adherence when generating arguments. Whether it is\nhonored is model-specific.\n","type":"boolean"}},"required":["type","name"]},"ResponsesNamedToolChoice":{"type":"object","description":"Forces the model to call a specific function.","properties":{"type":{"type":"string","enum":["function"]},"name":{"description":"The name of the function to call.","type":"string"}},"required":["type","name"]}}}}
```

## The ResponsesInputItem object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesInputItem":{"type":"object","description":"A single item in the `input` array: a conversation message or, for multi-turn tool\nuse, an earlier tool call or its result. Which fields apply depends on `type`.\n","properties":{"type":{"type":"string","enum":["message","function_call","function_call_output"],"default":"message","description":"Discriminator for the item type. Optional: when omitted the item is treated as a\n`message`, matching OpenAI, whose `EasyInputMessage` requires only `role` and\n`content`. This is the shape the OpenAI SDKs emit by default.\n"},"role":{"description":"Message author. Required when `type` is `message`. The value is not checked, and\nhow a value outside this list is answered is model-specific.\n","type":"string","enum":["system","developer","user","assistant"]},"content":{"description":"Content of the message. Required when `type` is `message`. Either a plain string,\nor an ordered array of content parts for multi-modal input.\n\nThe Responses API uses its own part names (`input_text`, `input_image`), distinct\nfrom the Chat Completions part names `text` and `image_url`. There is no video part:\nthis API defines only text and image content, so video input is available on\n`/v1/chat/completions` and `/v1/embeddings` instead.\n\nImage parts are only accepted on `user` messages, and only for models advertising\nimage input. For other models, the request is rejected with a 400 naming the\nmodels that support it.\n","oneOf":[{"type":"string"},{"type":"array","minItems":1,"items":{"$ref":"#/components/schemas/ResponsesContentPart"}}]},"call_id":{"type":"string","description":"Identifier correlating a `function_call` with its `function_call_output`. Required\nwhen `type` is `function_call` or `function_call_output`.\n"},"name":{"type":"string","description":"Name of the called function. Required when `type` is `function_call`."},"arguments":{"type":"string","description":"JSON-encoded arguments the model produced for the call. Required when `type` is\n`function_call`.\n"},"output":{"type":"string","description":"The tool's result, as a string. Required when `type` is `function_call_output`.\n"}}},"ResponsesContentPart":{"type":"object","description":"A single content part of a Responses message: text or an image reference. The\n`type` values and the flat `image_url` string differ from the Chat Completions\ncontent part shape.\n","properties":{"type":{"description":"Discriminator for the content type.","type":"string","enum":["input_text","input_image"]},"text":{"description":"Text content when `type` is `input_text`.","type":"string"},"image_url":{"description":"Image reference when `type` is `input_image`. Either a public HTTP or HTTPS URL,\nwhich must be reachable from the internet, or an inline base64 data URI\n(`data:image/...;base64,...`) of at most 12 MiB decoded. Unlike Chat Completions,\nthis is a plain string, not an object with a `url` key.\n","type":"string"},"detail":{"description":"Fidelity hint for image processing. When omitted, the model chooses. Its effect,\nand how a value outside this list is answered, are model-specific.\n","type":"string","enum":["auto","low","high"]}},"required":["type"]}}}}
```

## The ResponsesTool object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesTool":{"type":"object","description":"A tool the model may call. Unlike Chat Completions, the function definition is\nflattened directly onto the tool object rather than nested under a `function` key.\n","properties":{"type":{"description":"Always `function`. Built-in tool types are not available, and how one is answered\nis model-specific.\n","type":"string","enum":["function"]},"name":{"description":"The name of the function to call.","type":"string"},"description":{"description":"Description of what the function does.","type":"string"},"parameters":{"type":"object","description":"The parameters the function accepts, described as a JSON Schema object.","additionalProperties":true},"strict":{"description":"Whether to enforce strict schema adherence when generating arguments. Whether it is\nhonored is model-specific.\n","type":"boolean"}},"required":["type","name"]}}}}
```

## The ResponsesResponse object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesResponse":{"type":"object","description":"Response body for a `POST /v1/responses` request. Always synchronous, never streamed.","properties":{"id":{"description":"Unique identifier for this response.","type":"string"},"object":{"description":"Always `response`.","type":"string"},"created_at":{"type":"integer","description":"Unix timestamp of when the response was created."},"status":{"type":"string","enum":["completed","failed","incomplete"],"description":"Final status of the response."},"model":{"description":"Model used to generate the response.","type":"string"},"output":{"type":"array","description":"List of generated output items, in order.","items":{"$ref":"#/components/schemas/ResponsesOutputItem"}},"usage":{"$ref":"#/components/schemas/ResponsesUsage"},"error":{"description":"Error details, present when `status` is `failed`.","nullable":true,"allOf":[{"$ref":"#/components/schemas/ResponsesResponseError"}]},"incomplete_details":{"description":"Why the response is incomplete. Null unless `status` is `incomplete`.","nullable":true,"allOf":[{"$ref":"#/components/schemas/ResponsesIncompleteDetails"}]}},"required":["id","object","created_at","status","incomplete_details","model","output"]},"ResponsesOutputItem":{"type":"object","description":"A single generated output item. Which fields apply depends on `type`.","properties":{"type":{"description":"Discriminator for the item type.","type":"string","enum":["message","function_call","reasoning"]},"id":{"description":"Unique identifier for this output item.","type":"string"},"status":{"description":"Whether generating this item completed.","type":"string","enum":["completed","incomplete"]},"role":{"type":"string","enum":["assistant"],"description":"Present when `type` is `message`. Always `assistant`."},"content":{"type":"array","description":"Present when `type` is `message` (parts of type `output_text`) or `reasoning`\n(parts of type `reasoning_text`, the model's own reasoning trace).\n","items":{"$ref":"#/components/schemas/ResponsesOutputContent"}},"summary":{"type":"array","description":"Present when `type` is `reasoning`. A condensed form of the reasoning trace, when\nthe model produces one. Models that emit reasoning without a summary return an\nempty array.\n","items":{"$ref":"#/components/schemas/ResponsesSummaryContent"}},"call_id":{"type":"string","description":"Present when `type` is `function_call`. Correlates with a follow-up `function_call_output`."},"name":{"type":"string","description":"Present when `type` is `function_call`. Name of the called function."},"arguments":{"type":"string","description":"Present when `type` is `function_call`. JSON-encoded arguments."}},"required":["type"]},"ResponsesOutputContent":{"type":"object","description":"A single piece of output content, which is always text.\n\n`output_text` is the answer itself. `reasoning_text` is the model's reasoning trace,\ncarried on items of type `reasoning`.\n","properties":{"type":{"type":"string","enum":["output_text","reasoning_text"]},"text":{"description":"The generated text.","type":"string"}},"required":["type","text"]},"ResponsesSummaryContent":{"type":"object","description":"A single piece of reasoning summary content.","properties":{"type":{"type":"string","enum":["summary_text"]},"text":{"description":"The summary text.","type":"string"}},"required":["type","text"]},"ResponsesUsage":{"type":"object","description":"Token usage for the response.","properties":{"input_tokens":{"type":"integer","description":"Number of tokens in the input."},"output_tokens":{"type":"integer","description":"Number of tokens generated."},"total_tokens":{"type":"integer","description":"Total tokens consumed by the request."},"output_tokens_details":{"$ref":"#/components/schemas/ResponsesOutputTokensDetails"}}},"ResponsesOutputTokensDetails":{"type":"object","description":"Breakdown of `output_tokens`, present when the model reports one.","properties":{"reasoning_tokens":{"type":"integer","description":"Tokens the model spent reasoning. They are already counted in `output_tokens`."}}},"ResponsesResponseError":{"type":"object","description":"Present when `status` is `failed`.","properties":{"code":{"description":"Machine-readable error code.","type":"string"},"message":{"description":"Human-readable explanation of the failure.","type":"string"}}},"ResponsesIncompleteDetails":{"type":"object","description":"Why the response is incomplete.","required":["reason"],"properties":{"reason":{"type":"string","description":"`max_output_tokens` when the output reaches `max_output_tokens` before it is\nfinished.\n","enum":["max_output_tokens","content_filter"]}}}}}}
```

## The ResponsesOutputItem object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesOutputItem":{"type":"object","description":"A single generated output item. Which fields apply depends on `type`.","properties":{"type":{"description":"Discriminator for the item type.","type":"string","enum":["message","function_call","reasoning"]},"id":{"description":"Unique identifier for this output item.","type":"string"},"status":{"description":"Whether generating this item completed.","type":"string","enum":["completed","incomplete"]},"role":{"type":"string","enum":["assistant"],"description":"Present when `type` is `message`. Always `assistant`."},"content":{"type":"array","description":"Present when `type` is `message` (parts of type `output_text`) or `reasoning`\n(parts of type `reasoning_text`, the model's own reasoning trace).\n","items":{"$ref":"#/components/schemas/ResponsesOutputContent"}},"summary":{"type":"array","description":"Present when `type` is `reasoning`. A condensed form of the reasoning trace, when\nthe model produces one. Models that emit reasoning without a summary return an\nempty array.\n","items":{"$ref":"#/components/schemas/ResponsesSummaryContent"}},"call_id":{"type":"string","description":"Present when `type` is `function_call`. Correlates with a follow-up `function_call_output`."},"name":{"type":"string","description":"Present when `type` is `function_call`. Name of the called function."},"arguments":{"type":"string","description":"Present when `type` is `function_call`. JSON-encoded arguments."}},"required":["type"]},"ResponsesOutputContent":{"type":"object","description":"A single piece of output content, which is always text.\n\n`output_text` is the answer itself. `reasoning_text` is the model's reasoning trace,\ncarried on items of type `reasoning`.\n","properties":{"type":{"type":"string","enum":["output_text","reasoning_text"]},"text":{"description":"The generated text.","type":"string"}},"required":["type","text"]},"ResponsesSummaryContent":{"type":"object","description":"A single piece of reasoning summary content.","properties":{"type":{"type":"string","enum":["summary_text"]},"text":{"description":"The summary text.","type":"string"}},"required":["type","text"]}}}}
```

## The ResponsesContentPart object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesContentPart":{"type":"object","description":"A single content part of a Responses message: text or an image reference. The\n`type` values and the flat `image_url` string differ from the Chat Completions\ncontent part shape.\n","properties":{"type":{"description":"Discriminator for the content type.","type":"string","enum":["input_text","input_image"]},"text":{"description":"Text content when `type` is `input_text`.","type":"string"},"image_url":{"description":"Image reference when `type` is `input_image`. Either a public HTTP or HTTPS URL,\nwhich must be reachable from the internet, or an inline base64 data URI\n(`data:image/...;base64,...`) of at most 12 MiB decoded. Unlike Chat Completions,\nthis is a plain string, not an object with a `url` key.\n","type":"string"},"detail":{"description":"Fidelity hint for image processing. When omitted, the model chooses. Its effect,\nand how a value outside this list is answered, are model-specific.\n","type":"string","enum":["auto","low","high"]}},"required":["type"]}}}}
```

## The ResponsesNamedToolChoice object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesNamedToolChoice":{"type":"object","description":"Forces the model to call a specific function.","properties":{"type":{"type":"string","enum":["function"]},"name":{"description":"The name of the function to call.","type":"string"}},"required":["type","name"]}}}}
```

## The ResponsesTextConfig object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesTextConfig":{"type":"object","description":"Configuration for the model's text output, including structured outputs. This is the\nResponses API's equivalent of `response_format` on `/v1/chat/completions`.\n","properties":{"format":{"$ref":"#/components/schemas/ResponsesTextFormat"}}},"ResponsesTextFormat":{"type":"object","description":"Output format. `text` is free-form prose. `json_object` constrains the reply to valid\nJSON. `json_schema` constrains it to the supplied schema, which is the form worth\nreaching for: it is the only one that guarantees a parseable shape.\n","properties":{"type":{"description":"The output format.","type":"string","enum":["text","json_object","json_schema"]},"name":{"description":"Name of the response format. Required when `type` is `json_schema`. OpenAI allows\nup to 64 characters. The length limit applied is model-specific.\n","type":"string"},"schema":{"description":"The JSON Schema the output must conform to. Required when `type` is `json_schema`.","type":"object","additionalProperties":true},"strict":{"description":"Whether to enforce the schema exactly. Whether it is honored, and its default when\nomitted, are model-specific.\n","type":"boolean"},"description":{"description":"What the format is for, used by the model to decide how to respond.","type":"string"}},"required":["type"]}}}}
```

## The ResponsesTextFormat object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesTextFormat":{"type":"object","description":"Output format. `text` is free-form prose. `json_object` constrains the reply to valid\nJSON. `json_schema` constrains it to the supplied schema, which is the form worth\nreaching for: it is the only one that guarantees a parseable shape.\n","properties":{"type":{"description":"The output format.","type":"string","enum":["text","json_object","json_schema"]},"name":{"description":"Name of the response format. Required when `type` is `json_schema`. OpenAI allows\nup to 64 characters. The length limit applied is model-specific.\n","type":"string"},"schema":{"description":"The JSON Schema the output must conform to. Required when `type` is `json_schema`.","type":"object","additionalProperties":true},"strict":{"description":"Whether to enforce the schema exactly. Whether it is honored, and its default when\nomitted, are model-specific.\n","type":"boolean"},"description":{"description":"What the format is for, used by the model to decide how to respond.","type":"string"}},"required":["type"]}}}}
```

## The ResponsesReasoningConfig object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesReasoningConfig":{"type":"object","description":"Controls how much reasoning a reasoning-capable model does before answering. This is the Responses API's own shape. `/v1/chat/completions` takes the same control as a flat `reasoning_effort` string. Accepted values are model-specific, and a value the model does not accept is rejected. Keys other than `effort` and `summary` are ignored.","properties":{"effort":{"description":"How much reasoning to do before answering. Accepted values are model-specific.","type":"string"},"summary":{"description":"Whether, and how verbosely, to summarize the reasoning. Accepted values are\nmodel-specific.\n","type":"string"}}}}}}
```

## The ResponsesSummaryContent object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesSummaryContent":{"type":"object","description":"A single piece of reasoning summary content.","properties":{"type":{"type":"string","enum":["summary_text"]},"text":{"description":"The summary text.","type":"string"}},"required":["type","text"]}}}}
```

## The ResponsesResponseError object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesResponseError":{"type":"object","description":"Present when `status` is `failed`.","properties":{"code":{"description":"Machine-readable error code.","type":"string"},"message":{"description":"Human-readable explanation of the failure.","type":"string"}}}}}}
```

## The ResponsesOutputContent object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesOutputContent":{"type":"object","description":"A single piece of output content, which is always text.\n\n`output_text` is the answer itself. `reasoning_text` is the model's reasoning trace,\ncarried on items of type `reasoning`.\n","properties":{"type":{"type":"string","enum":["output_text","reasoning_text"]},"text":{"description":"The generated text.","type":"string"}},"required":["type","text"]}}}}
```

## The RerankDocument object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"RerankDocument":{"type":"object","description":"A candidate document as a multi-modal content part array.","properties":{"content":{"type":"array","description":"Ordered content parts making up the document.","minItems":1,"items":{"$ref":"#/components/schemas/RerankContentPart"},"maxItems":2048}},"required":["content"]},"RerankContentPart":{"type":"object","description":"A single content part of a rerank query or document: text, an image reference, or a\nvideo reference. Uses the same part names as Chat Completions.\n","required":["type"],"properties":{"type":{"type":"string","description":"Discriminator for the content type.","enum":["text","image_url","video_url"]},"text":{"type":"string","description":"Text content when `type` is `text`."},"image_url":{"$ref":"#/components/schemas/RerankMediaURL"},"video_url":{"$ref":"#/components/schemas/RerankMediaURL"}}},"RerankMediaURL":{"type":"object","description":"Media reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI of at most 12 MiB decoded.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI."}}}}}}
```

## The RerankRequest object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"RerankRequest":{"type":"object","properties":{"model":{"type":"string","description":"ID of the model to use.","minLength":1},"query":{"description":"The search query to rank documents against. Either a plain string, or an array\nof content parts, for example to rank against an image. Content parts are kept as\nseparate parts in the order given, even when all of them are text. Whether a model\naccepts content parts, and how it combines several of them, is model-specific.\n","oneOf":[{"type":"string","minLength":1},{"type":"array","minItems":1,"items":{"$ref":"#/components/schemas/RerankContentPart"},"maxItems":2048}]},"documents":{"type":"array","description":"Candidate documents to rank, in the order supplied. Each document is either a\nplain string or an object with a `content` array of parts, so images and video can\nbe ranked against the query. Content parts are kept as separate parts in the order\ngiven, even when all of them are text. Whether a model accepts content parts, and\nhow it combines several of them, is model-specific.\n","minItems":1,"maxItems":1000,"items":{"oneOf":[{"type":"string","minLength":1},{"$ref":"#/components/schemas/RerankDocument"}]}},"top_n":{"type":"integer","description":"Number of highest-scoring documents to return. When omitted or 0, all documents are\nreturned. A value above the number of documents returns all of them.\n"},"return_documents":{"type":"boolean","description":"If true, each result includes the document it ranks, in the form you sent it: a\nplain-string document as an object with a `text` field, a content-part document as\nan object with its `content` parts.\n","default":false}},"required":["model","query","documents"],"description":"Request payload for reranking a set of documents against a query."},"RerankContentPart":{"type":"object","description":"A single content part of a rerank query or document: text, an image reference, or a\nvideo reference. Uses the same part names as Chat Completions.\n","required":["type"],"properties":{"type":{"type":"string","description":"Discriminator for the content type.","enum":["text","image_url","video_url"]},"text":{"type":"string","description":"Text content when `type` is `text`."},"image_url":{"$ref":"#/components/schemas/RerankMediaURL"},"video_url":{"$ref":"#/components/schemas/RerankMediaURL"}}},"RerankMediaURL":{"type":"object","description":"Media reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI of at most 12 MiB decoded.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI."}}},"RerankDocument":{"type":"object","description":"A candidate document as a multi-modal content part array.","properties":{"content":{"type":"array","description":"Ordered content parts making up the document.","minItems":1,"items":{"$ref":"#/components/schemas/RerankContentPart"},"maxItems":2048}},"required":["content"]}}}}
```

## The RerankResponse object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"RerankResponse":{"type":"object","properties":{"model":{"type":"string","description":"Model identifier used to produce the ranking."},"results":{"type":"array","description":"Ranked results, ordered by descending `relevance_score`.","items":{"$ref":"#/components/schemas/RerankResult"}},"usage":{"$ref":"#/components/schemas/RerankUsage"}},"description":"Response containing ranked documents.","required":["model","results","usage"]},"RerankResult":{"type":"object","properties":{"index":{"type":"integer","description":"Zero-based index matching the position of the document in the request.","minimum":0},"document":{"description":"The ranked document, present only when `return_documents` was true, in the form you\nsent it. A plain-string document comes back as an object with a `text` field. A\ndocument sent as a `content` array comes back with the same `content` parts,\nincluding when every part is text.\n","oneOf":[{"$ref":"#/components/schemas/RerankResultText"},{"$ref":"#/components/schemas/RerankResultContent"}]},"relevance_score":{"type":"number","format":"double","description":"Relevance score of the document with respect to the query. Higher is more relevant."}},"description":"A single ranked document.","required":["index","relevance_score"]},"RerankResultText":{"type":"object","description":"A document you sent as a plain string, returned as sent.","required":["text"],"properties":{"text":{"type":"string","description":"The document string, exactly as sent."}}},"RerankResultContent":{"type":"object","description":"A document you sent as a `content` array, returned with the same parts in the same\norder, whether they are text, images, or video.\n","required":["content"],"properties":{"content":{"type":"array","minItems":1,"items":{"$ref":"#/components/schemas/RerankContentPart"}}}},"RerankContentPart":{"type":"object","description":"A single content part of a rerank query or document: text, an image reference, or a\nvideo reference. Uses the same part names as Chat Completions.\n","required":["type"],"properties":{"type":{"type":"string","description":"Discriminator for the content type.","enum":["text","image_url","video_url"]},"text":{"type":"string","description":"Text content when `type` is `text`."},"image_url":{"$ref":"#/components/schemas/RerankMediaURL"},"video_url":{"$ref":"#/components/schemas/RerankMediaURL"}}},"RerankMediaURL":{"type":"object","description":"Media reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI of at most 12 MiB decoded.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI."}}},"RerankUsage":{"type":"object","properties":{"prompt_tokens":{"type":"integer","description":"Number of tokens consumed by the query and documents.","minimum":0},"total_tokens":{"type":"integer","description":"Total tokens consumed by the request. Equal to `prompt_tokens` for rerank.","minimum":0}},"description":"Token-based usage statistics for the rerank request.","required":["prompt_tokens","total_tokens"]}}}}
```

## The RerankResult object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"RerankResult":{"type":"object","properties":{"index":{"type":"integer","description":"Zero-based index matching the position of the document in the request.","minimum":0},"document":{"description":"The ranked document, present only when `return_documents` was true, in the form you\nsent it. A plain-string document comes back as an object with a `text` field. A\ndocument sent as a `content` array comes back with the same `content` parts,\nincluding when every part is text.\n","oneOf":[{"$ref":"#/components/schemas/RerankResultText"},{"$ref":"#/components/schemas/RerankResultContent"}]},"relevance_score":{"type":"number","format":"double","description":"Relevance score of the document with respect to the query. Higher is more relevant."}},"description":"A single ranked document.","required":["index","relevance_score"]},"RerankResultText":{"type":"object","description":"A document you sent as a plain string, returned as sent.","required":["text"],"properties":{"text":{"type":"string","description":"The document string, exactly as sent."}}},"RerankResultContent":{"type":"object","description":"A document you sent as a `content` array, returned with the same parts in the same\norder, whether they are text, images, or video.\n","required":["content"],"properties":{"content":{"type":"array","minItems":1,"items":{"$ref":"#/components/schemas/RerankContentPart"}}}},"RerankContentPart":{"type":"object","description":"A single content part of a rerank query or document: text, an image reference, or a\nvideo reference. Uses the same part names as Chat Completions.\n","required":["type"],"properties":{"type":{"type":"string","description":"Discriminator for the content type.","enum":["text","image_url","video_url"]},"text":{"type":"string","description":"Text content when `type` is `text`."},"image_url":{"$ref":"#/components/schemas/RerankMediaURL"},"video_url":{"$ref":"#/components/schemas/RerankMediaURL"}}},"RerankMediaURL":{"type":"object","description":"Media reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI of at most 12 MiB decoded.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI."}}}}}}
```

## The RerankUsage object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"RerankUsage":{"type":"object","properties":{"prompt_tokens":{"type":"integer","description":"Number of tokens consumed by the query and documents.","minimum":0},"total_tokens":{"type":"integer","description":"Total tokens consumed by the request. Equal to `prompt_tokens` for rerank.","minimum":0}},"description":"Token-based usage statistics for the rerank request.","required":["prompt_tokens","total_tokens"]}}}}
```

## The ResponseFormatText object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponseFormatText":{"type":"object","properties":{"type":{"type":"string","enum":["text"]}},"required":["type"]}}}}
```

## The ListModelsResponse object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ListModelsResponse":{"type":"object","required":["object","data"],"properties":{"object":{"type":"string","description":"Always `list`.","enum":["list"]},"data":{"type":"array","description":"The available models.","items":{"$ref":"#/components/schemas/Model"}}}},"Model":{"type":"object","description":"A model available through this API.","required":["id","object","created","owned_by"],"properties":{"id":{"type":"string","description":"The model identifier, which can be referenced in the API endpoints."},"object":{"type":"string","enum":["model"],"description":"Always `model`."},"created":{"type":"integer","description":"The Unix timestamp (in seconds) when the model was created."},"owned_by":{"type":"string","description":"The organization that owns the model."}}}}}}
```

## The Model object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"Model":{"type":"object","description":"A model available through this API.","required":["id","object","created","owned_by"],"properties":{"id":{"type":"string","description":"The model identifier, which can be referenced in the API endpoints."},"object":{"type":"string","enum":["model"],"description":"Always `model`."},"created":{"type":"integer","description":"The Unix timestamp (in seconds) when the model was created."},"owned_by":{"type":"string","description":"The organization that owns the model."}}}}}}
```

## The OpenAIError object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"OpenAIError":{"type":"object","description":"OpenAI-compatible error response.","required":["error"],"properties":{"error":{"type":"object","description":"The error details.","required":["message","type"],"properties":{"message":{"type":"string","description":"Human-readable explanation of the error."},"type":{"type":"string","description":"Error category, for example `invalid_request_error`."},"code":{"type":"string","description":"Machine-readable sub-classification of `type`. Used by the 529 overload\nresponse to distinguish a per-user throttle (`user_overloaded`) from a\nsystem-wide capacity shortage (`server_overloaded`), so you do not have to\nparse the `message` text.\n"}}}}}}}}
```

## The EmbeddingMessage object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"EmbeddingMessage":{"type":"object","description":"A multi-modal conversation turn.","required":["role","content"],"properties":{"role":{"type":"string","description":"Author of the message. Must be `user`.","enum":["user"]},"content":{"type":"array","description":"Ordered list of content parts.","minItems":1,"maxItems":2048,"items":{"$ref":"#/components/schemas/EmbeddingContent"}}}},"EmbeddingContent":{"type":"object","description":"A single content part: text, an image reference, or a video reference.","required":["type"],"properties":{"type":{"type":"string","description":"Discriminator for the content type.","enum":["text","image_url","video_url"]},"text":{"type":"string","description":"Text content when `type` is `text`. The text is embedded, not answered: write it as\ncontent to embed, such as a caption, a title or a search query, rather than as an\ninstruction or a question about the image. It is embedded together with the other\nparts of the request into the single returned vector.\n"},"image_url":{"$ref":"#/components/schemas/EmbeddingImageURL"},"video_url":{"$ref":"#/components/schemas/EmbeddingVideoURL"}}},"EmbeddingImageURL":{"type":"object","description":"Image reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI (`data:image/...;base64,...`) of at most 12 MiB\ndecoded.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the image."}}},"EmbeddingVideoURL":{"type":"object","description":"Video reference, for models advertising video input. Either a public HTTP or HTTPS\nURL, which must be reachable from the internet, or an inline base64 data URI\n(`data:video/...;base64,...`) of at most 12 MiB decoded. Prefer a remote URL for long\nclips: the whole request body is limited to 16 MiB, and a base64 payload is about 4/3\nthe size of the media it carries.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the video."}}}}}}
```

## The EmbeddingContent object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"EmbeddingContent":{"type":"object","description":"A single content part: text, an image reference, or a video reference.","required":["type"],"properties":{"type":{"type":"string","description":"Discriminator for the content type.","enum":["text","image_url","video_url"]},"text":{"type":"string","description":"Text content when `type` is `text`. The text is embedded, not answered: write it as\ncontent to embed, such as a caption, a title or a search query, rather than as an\ninstruction or a question about the image. It is embedded together with the other\nparts of the request into the single returned vector.\n"},"image_url":{"$ref":"#/components/schemas/EmbeddingImageURL"},"video_url":{"$ref":"#/components/schemas/EmbeddingVideoURL"}}},"EmbeddingImageURL":{"type":"object","description":"Image reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI (`data:image/...;base64,...`) of at most 12 MiB\ndecoded.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the image."}}},"EmbeddingVideoURL":{"type":"object","description":"Video reference, for models advertising video input. Either a public HTTP or HTTPS\nURL, which must be reachable from the internet, or an inline base64 data URI\n(`data:video/...;base64,...`) of at most 12 MiB decoded. Prefer a remote URL for long\nclips: the whole request body is limited to 16 MiB, and a base64 payload is about 4/3\nthe size of the media it carries.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the video."}}}}}}
```

## The EmbeddingVideoURL object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"EmbeddingVideoURL":{"type":"object","description":"Video reference, for models advertising video input. Either a public HTTP or HTTPS\nURL, which must be reachable from the internet, or an inline base64 data URI\n(`data:video/...;base64,...`) of at most 12 MiB decoded. Prefer a remote URL for long\nclips: the whole request body is limited to 16 MiB, and a base64 payload is about 4/3\nthe size of the media it carries.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the video."}}}}}}
```

## The EmbeddingImageURL object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"EmbeddingImageURL":{"type":"object","description":"Image reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI (`data:image/...;base64,...`) of at most 12 MiB\ndecoded.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the image."}}}}}}
```

## The EmbeddingObject object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"EmbeddingObject":{"type":"object","description":"A single embedding result.","required":["object","index","embedding"],"properties":{"object":{"type":"string","description":"Always `embedding`.","enum":["embedding"]},"index":{"type":"integer","description":"Zero-based index matching the position of the input that produced this embedding.","minimum":0},"embedding":{"description":"Embedding vector. When `encoding_format` is `float`, an array of floating-point numbers.\nWhen `encoding_format` is `base64`, a base64-encoded little-endian float32 byte string.\n","oneOf":[{"type":"array","items":{"type":"number"}},{"type":"string"}]}}}}}}
```

## The RerankContentPart object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"RerankContentPart":{"type":"object","description":"A single content part of a rerank query or document: text, an image reference, or a\nvideo reference. Uses the same part names as Chat Completions.\n","required":["type"],"properties":{"type":{"type":"string","description":"Discriminator for the content type.","enum":["text","image_url","video_url"]},"text":{"type":"string","description":"Text content when `type` is `text`."},"image_url":{"$ref":"#/components/schemas/RerankMediaURL"},"video_url":{"$ref":"#/components/schemas/RerankMediaURL"}}},"RerankMediaURL":{"type":"object","description":"Media reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI of at most 12 MiB decoded.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI."}}}}}}
```

## The RerankMediaURL object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"RerankMediaURL":{"type":"object","description":"Media reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI of at most 12 MiB decoded.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI."}}}}}}
```

## The RerankResultText object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"RerankResultText":{"type":"object","description":"A document you sent as a plain string, returned as sent.","required":["text"],"properties":{"text":{"type":"string","description":"The document string, exactly as sent."}}}}}}
```

## The RerankResultContent object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"RerankResultContent":{"type":"object","description":"A document you sent as a `content` array, returned with the same parts in the same\norder, whether they are text, images, or video.\n","required":["content"],"properties":{"content":{"type":"array","minItems":1,"items":{"$ref":"#/components/schemas/RerankContentPart"}}}},"RerankContentPart":{"type":"object","description":"A single content part of a rerank query or document: text, an image reference, or a\nvideo reference. Uses the same part names as Chat Completions.\n","required":["type"],"properties":{"type":{"type":"string","description":"Discriminator for the content type.","enum":["text","image_url","video_url"]},"text":{"type":"string","description":"Text content when `type` is `text`."},"image_url":{"$ref":"#/components/schemas/RerankMediaURL"},"video_url":{"$ref":"#/components/schemas/RerankMediaURL"}}},"RerankMediaURL":{"type":"object","description":"Media reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI of at most 12 MiB decoded.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI."}}}}}}
```

## The ImageOutputFormat object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ImageOutputFormat":{"type":"string","description":"File format of the returned image, for example `png` or `jpeg`. Distinct from\n`response_format`, which controls how the image is delivered rather than what it\nis encoded as. Supported formats are model-specific. An unsupported value is rejected\nwith a 400 whose message states the supported formats.\n"}}}}
```

## The ImageSize object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ImageSize":{"type":"string","description":"Size of the generated images as `WIDTHxHEIGHT` in pixels, for example `1024x1024`. A\nside smaller than 1 or larger than 8192 pixels is rejected with a 413.\n\nWithin that, the sizes served are model-specific: a model may accept only a range of\nsizes, round each side to a step of its own, and limit the pixels one request may\nproduce (`n` times width times height). A request outside a model's limits is\nrejected with a 400 whose message states the limit.\n\nWhen omitted, the model chooses the size.\n"}}}}
```

## The ImageRef object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ImageRef":{"type":"object","description":"Reference to an input image. Provide the image either as a public HTTP or HTTPS URL or\nas an inline base64 `data:` URL (for example `data:image/png;base64,iVBORw0KGgo...`).\n\nA remote URL must be reachable from the internet, not only from your network, the same\nas for the image inputs on `/v1/chat/completions` and `/v1/embeddings`.\n","required":["image_url"],"properties":{"image_url":{"type":"string","description":"A fully qualified HTTP or HTTPS URL, or a base64-encoded `data:` URL.","minLength":1}}}}}}
```

## The ImageEditJSONRequest object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ImageEditJSONRequest":{"type":"object","description":"JSON request body for editing an image. Uses `images` (an array of references) in place\nof the multipart `image` upload. Send this with `Content-Type: application/json`.\n","required":["model","images","prompt"],"properties":{"model":{"type":"string","description":"ID of the model to use.","minLength":1},"images":{"type":"array","description":"Input image references to edit. At most 16. More are rejected with a 413. Within\nthat, how many images a model accepts, and which ones, is model-specific. A request\noutside a model's limits is rejected with a 400 whose message states the limit.\n","minItems":1,"maxItems":16,"items":{"$ref":"#/components/schemas/ImageRef"}},"mask":{"$ref":"#/components/schemas/ImageRef"},"prompt":{"type":"string","description":"Text description of the desired edit.","minLength":1},"n":{"type":"integer","description":"Number of edited images to generate, at most 10. A larger value is rejected with a\n413. A model may also limit the total pixels one request may produce. See `size`.\nWhen omitted, the model chooses.\n","minimum":1,"maximum":10},"size":{"$ref":"#/components/schemas/ImageSize"},"output_format":{"$ref":"#/components/schemas/ImageOutputFormat"},"response_format":{"type":"string","description":"Format of the returned images. `b64_json` returns the image data inline and is\nthe only format this API serves. Images are not published at a fetchable address,\nso OpenAI's `url` is rejected with a 400.\n","enum":["b64_json"],"default":"b64_json"}}},"ImageRef":{"type":"object","description":"Reference to an input image. Provide the image either as a public HTTP or HTTPS URL or\nas an inline base64 `data:` URL (for example `data:image/png;base64,iVBORw0KGgo...`).\n\nA remote URL must be reachable from the internet, not only from your network, the same\nas for the image inputs on `/v1/chat/completions` and `/v1/embeddings`.\n","required":["image_url"],"properties":{"image_url":{"type":"string","description":"A fully qualified HTTP or HTTPS URL, or a base64-encoded `data:` URL.","minLength":1}}},"ImageSize":{"type":"string","description":"Size of the generated images as `WIDTHxHEIGHT` in pixels, for example `1024x1024`. A\nside smaller than 1 or larger than 8192 pixels is rejected with a 413.\n\nWithin that, the sizes served are model-specific: a model may accept only a range of\nsizes, round each side to a step of its own, and limit the pixels one request may\nproduce (`n` times width times height). A request outside a model's limits is\nrejected with a 400 whose message states the limit.\n\nWhen omitted, the model chooses the size.\n"},"ImageOutputFormat":{"type":"string","description":"File format of the returned image, for example `png` or `jpeg`. Distinct from\n`response_format`, which controls how the image is delivered rather than what it\nis encoded as. Supported formats are model-specific. An unsupported value is rejected\nwith a 400 whose message states the supported formats.\n"}}}}
```

## The ImageResponse object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ImageResponse":{"type":"object","description":"Response containing one or more generated or edited images.","required":["created","data"],"properties":{"created":{"type":"integer","description":"Unix timestamp (in seconds) of when the images were created."},"data":{"type":"array","description":"One `ImageData` object per generated image.","items":{"$ref":"#/components/schemas/ImageData"}}}},"ImageData":{"type":"object","description":"A single generated image.","properties":{"url":{"type":"string","description":"Reserved for OpenAI compatibility and never returned by this API, which serves\n`b64_json` only. Read `b64_json` instead.\n","format":"uri"},"b64_json":{"type":"string","description":"Base64-encoded image data. Present when `response_format` is `b64_json`."},"revised_prompt":{"type":"string","description":"The prompt actually used to generate the image, if the model revised it."}}}}}}
```

## The ImageData object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ImageData":{"type":"object","description":"A single generated image.","properties":{"url":{"type":"string","description":"Reserved for OpenAI compatibility and never returned by this API, which serves\n`b64_json` only. Read `b64_json` instead.\n","format":"uri"},"b64_json":{"type":"string","description":"Base64-encoded image data. Present when `response_format` is `b64_json`."},"revised_prompt":{"type":"string","description":"The prompt actually used to generate the image, if the model revised it."}}}}}}
```

## The CompletionResponse object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"CompletionResponse":{"type":"object","description":"Response body for a non-streaming `POST /v1/completions` request.","required":["id","object","created","model","choices"],"properties":{"id":{"type":"string","description":"Unique identifier for this completion."},"object":{"type":"string","description":"Always `text_completion`."},"created":{"type":"integer","description":"Unix timestamp of when the completion was created."},"model":{"type":"string","description":"Model used to generate the completion."},"choices":{"type":"array","description":"List of generated completions.","items":{"$ref":"#/components/schemas/CompletionChoice"}},"usage":{"$ref":"#/components/schemas/CompletionUsage"}}},"CompletionChoice":{"type":"object","description":"A single generated completion.","required":["finish_reason","logprobs"],"properties":{"text":{"type":"string","description":"The generated text."},"index":{"type":"integer","description":"Index of this choice in the list."},"finish_reason":{"type":"string","nullable":true,"description":"Reason the generation stopped, for example `stop` or `length`. Null while a streamed\nchoice is still generating, and on the rare completion for which no reason is\navailable.\n"},"logprobs":{"type":"object","nullable":true,"additionalProperties":true,"description":"Log-probability information for the choice, when requested."}}},"CompletionUsage":{"type":"object","description":"Token usage statistics for the completion request.","required":["prompt_tokens","completion_tokens","total_tokens"],"properties":{"prompt_tokens":{"type":"integer","description":"Number of tokens in the prompt.","minimum":0},"completion_tokens":{"type":"integer","description":"Number of tokens in the generated completion.","minimum":0},"total_tokens":{"type":"integer","description":"Total tokens consumed by the request.","minimum":0},"completion_tokens_details":{"$ref":"#/components/schemas/CompletionTokensDetails"}}},"CompletionTokensDetails":{"type":"object","description":"Breakdown of `completion_tokens`, present when the model reports one.","properties":{"reasoning_tokens":{"type":"integer","description":"Tokens the model spent reasoning before its answer. They are already counted in\n`completion_tokens`.\n","minimum":0}}}}}}
```

## The CompletionChoice object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"CompletionChoice":{"type":"object","description":"A single generated completion.","required":["finish_reason","logprobs"],"properties":{"text":{"type":"string","description":"The generated text."},"index":{"type":"integer","description":"Index of this choice in the list."},"finish_reason":{"type":"string","nullable":true,"description":"Reason the generation stopped, for example `stop` or `length`. Null while a streamed\nchoice is still generating, and on the rare completion for which no reason is\navailable.\n"},"logprobs":{"type":"object","nullable":true,"additionalProperties":true,"description":"Log-probability information for the choice, when requested."}}}}}}
```

## The CompletionUsage object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"CompletionUsage":{"type":"object","description":"Token usage statistics for the completion request.","required":["prompt_tokens","completion_tokens","total_tokens"],"properties":{"prompt_tokens":{"type":"integer","description":"Number of tokens in the prompt.","minimum":0},"completion_tokens":{"type":"integer","description":"Number of tokens in the generated completion.","minimum":0},"total_tokens":{"type":"integer","description":"Total tokens consumed by the request.","minimum":0},"completion_tokens_details":{"$ref":"#/components/schemas/CompletionTokensDetails"}}},"CompletionTokensDetails":{"type":"object","description":"Breakdown of `completion_tokens`, present when the model reports one.","properties":{"reasoning_tokens":{"type":"integer","description":"Tokens the model spent reasoning before its answer. They are already counted in\n`completion_tokens`.\n","minimum":0}}}}}}
```

## The CompletionTokensDetails object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"CompletionTokensDetails":{"type":"object","description":"Breakdown of `completion_tokens`, present when the model reports one.","properties":{"reasoning_tokens":{"type":"integer","description":"Tokens the model spent reasoning before its answer. They are already counted in\n`completion_tokens`.\n","minimum":0}}}}}}
```

## The ChatCompletionImageURL object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ChatCompletionImageURL":{"type":"object","description":"Image reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI (`data:image/...;base64,...`) of at most 12 MiB\ndecoded.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the image."},"detail":{"type":"string","description":"Fidelity hint for image processing. Both its effect and whether it is honored at\nall are model-specific. Omit it to leave the choice to the model.\n","enum":["auto","low","high"]}}}}}}
```

## The ChatCompletionVideoURL object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ChatCompletionVideoURL":{"type":"object","description":"Video reference. Either a public HTTP or HTTPS URL, which must be reachable from the\ninternet, or an inline base64 data URI (`data:video/...;base64,...`) of at most 12 MiB\ndecoded. Prefer a remote URL for long clips: the whole request body is limited to\n16 MiB, and a base64 payload is about 4/3 the size of the media it carries.\n","required":["url"],"properties":{"url":{"type":"string","description":"HTTP or HTTPS URL, or base64 data URI, of the video."}}}}}}
```

## The ChatCompletionTool object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ChatCompletionTool":{"type":"object","description":"A tool the model may call.","required":["type","function"],"properties":{"type":{"type":"string","description":"Always `function`. The value is not checked, and how another type is answered is\nmodel-specific.\n","enum":["function"]},"function":{"type":"object","description":"The function the model may call.","required":["name"],"properties":{"name":{"type":"string","description":"The name of the function to call."},"description":{"type":"string","description":"Description of what the function does."},"parameters":{"type":"object","additionalProperties":true,"description":"The parameters the function accepts, described as a JSON Schema object."}}}}}}}}
```

## The ChatCompletionNamedToolChoice object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ChatCompletionNamedToolChoice":{"type":"object","description":"Forces the model to call a specific function.","required":["type","function"],"properties":{"type":{"type":"string","description":"Always `function`.","enum":["function"]},"function":{"type":"object","description":"The function to call.","required":["name"],"properties":{"name":{"type":"string","description":"The name of the function to call."}}}}}}}}
```

## The ResponseFormatJsonObject object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponseFormatJsonObject":{"type":"object","required":["type"],"properties":{"type":{"type":"string","enum":["json_object"]}}}}}}
```

## The ResponseFormatJsonSchema object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponseFormatJsonSchema":{"type":"object","required":["type","json_schema"],"properties":{"type":{"type":"string","enum":["json_schema"]},"json_schema":{"type":"object","additionalProperties":true,"description":"The JSON schema the model must conform to.","required":["name","schema"],"properties":{"name":{"type":"string","description":"Identifier for the schema definition."},"schema":{"type":"object","additionalProperties":true,"description":"The JSON Schema object the output must conform to."},"strict":{"type":"boolean","description":"Whether the model must follow the schema exactly. Whether it is honored, and\nits default when omitted, are model-specific.\n"}}}}}}}}
```

## The ChatCompletionResponse object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ChatCompletionResponse":{"type":"object","description":"Response body for a non-streaming `POST /v1/chat/completions` request.","required":["id","object","created","model","choices"],"properties":{"id":{"type":"string","description":"Unique identifier for this chat completion."},"object":{"type":"string","description":"Always `chat.completion`."},"created":{"type":"integer","description":"Unix timestamp of when the completion was created."},"model":{"type":"string","description":"Model used to generate the completion."},"choices":{"type":"array","description":"List of generated chat completion choices.","items":{"$ref":"#/components/schemas/ChatCompletionChoice"}},"usage":{"$ref":"#/components/schemas/CompletionUsage"}}},"ChatCompletionChoice":{"type":"object","description":"A single generated chat completion choice.","required":["finish_reason","logprobs"],"properties":{"index":{"type":"integer","description":"Index of this choice in the list."},"message":{"$ref":"#/components/schemas/ChatCompletionResponseMessage"},"finish_reason":{"type":"string","nullable":true,"description":"Reason the generation stopped, for example `stop`, `length`, or `tool_calls`. Null while a\nstreamed choice is still generating, and on the rare completion for which no\nreason is available.\n"},"logprobs":{"type":"object","nullable":true,"additionalProperties":true,"description":"Log-probability information for the choice, when requested."}}},"ChatCompletionResponseMessage":{"type":"object","description":"The message generated by the model.","required":["role","content"],"properties":{"role":{"type":"string","description":"Always `assistant`.","enum":["assistant"]},"content":{"type":"string","nullable":true,"description":"The text content of the message. Null when the model answers with `tool_calls` or\na `refusal` only. Empty when it writes no answer, for example when a reasoning\nmodel reaches `max_tokens` before it finishes reasoning.\n"},"reasoning":{"type":"string","nullable":true,"description":"Reasoning trace emitted by reasoning-capable models, when present."},"refusal":{"type":"string","nullable":true,"description":"Refusal message emitted by the model, when it declines to answer."},"tool_calls":{"type":"array","nullable":true,"description":"Tool calls generated by the model, if any.","items":{"$ref":"#/components/schemas/ChatCompletionToolCall"}}}},"ChatCompletionToolCall":{"type":"object","description":"A tool call generated by the model.","required":["id","type","function"],"properties":{"id":{"type":"string","description":"Unique identifier for this tool call."},"type":{"type":"string","description":"Always `function`.","enum":["function"]},"function":{"type":"object","description":"The function the model called.","required":["name","arguments"],"properties":{"name":{"type":"string","description":"The name of the function to call."},"arguments":{"type":"string","description":"JSON-encoded arguments to pass to the function."}}}}},"CompletionUsage":{"type":"object","description":"Token usage statistics for the completion request.","required":["prompt_tokens","completion_tokens","total_tokens"],"properties":{"prompt_tokens":{"type":"integer","description":"Number of tokens in the prompt.","minimum":0},"completion_tokens":{"type":"integer","description":"Number of tokens in the generated completion.","minimum":0},"total_tokens":{"type":"integer","description":"Total tokens consumed by the request.","minimum":0},"completion_tokens_details":{"$ref":"#/components/schemas/CompletionTokensDetails"}}},"CompletionTokensDetails":{"type":"object","description":"Breakdown of `completion_tokens`, present when the model reports one.","properties":{"reasoning_tokens":{"type":"integer","description":"Tokens the model spent reasoning before its answer. They are already counted in\n`completion_tokens`.\n","minimum":0}}}}}}
```

## The ChatCompletionChoice object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ChatCompletionChoice":{"type":"object","description":"A single generated chat completion choice.","required":["finish_reason","logprobs"],"properties":{"index":{"type":"integer","description":"Index of this choice in the list."},"message":{"$ref":"#/components/schemas/ChatCompletionResponseMessage"},"finish_reason":{"type":"string","nullable":true,"description":"Reason the generation stopped, for example `stop`, `length`, or `tool_calls`. Null while a\nstreamed choice is still generating, and on the rare completion for which no\nreason is available.\n"},"logprobs":{"type":"object","nullable":true,"additionalProperties":true,"description":"Log-probability information for the choice, when requested."}}},"ChatCompletionResponseMessage":{"type":"object","description":"The message generated by the model.","required":["role","content"],"properties":{"role":{"type":"string","description":"Always `assistant`.","enum":["assistant"]},"content":{"type":"string","nullable":true,"description":"The text content of the message. Null when the model answers with `tool_calls` or\na `refusal` only. Empty when it writes no answer, for example when a reasoning\nmodel reaches `max_tokens` before it finishes reasoning.\n"},"reasoning":{"type":"string","nullable":true,"description":"Reasoning trace emitted by reasoning-capable models, when present."},"refusal":{"type":"string","nullable":true,"description":"Refusal message emitted by the model, when it declines to answer."},"tool_calls":{"type":"array","nullable":true,"description":"Tool calls generated by the model, if any.","items":{"$ref":"#/components/schemas/ChatCompletionToolCall"}}}},"ChatCompletionToolCall":{"type":"object","description":"A tool call generated by the model.","required":["id","type","function"],"properties":{"id":{"type":"string","description":"Unique identifier for this tool call."},"type":{"type":"string","description":"Always `function`.","enum":["function"]},"function":{"type":"object","description":"The function the model called.","required":["name","arguments"],"properties":{"name":{"type":"string","description":"The name of the function to call."},"arguments":{"type":"string","description":"JSON-encoded arguments to pass to the function."}}}}}}}}
```

## The ChatCompletionResponseMessage object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ChatCompletionResponseMessage":{"type":"object","description":"The message generated by the model.","required":["role","content"],"properties":{"role":{"type":"string","description":"Always `assistant`.","enum":["assistant"]},"content":{"type":"string","nullable":true,"description":"The text content of the message. Null when the model answers with `tool_calls` or\na `refusal` only. Empty when it writes no answer, for example when a reasoning\nmodel reaches `max_tokens` before it finishes reasoning.\n"},"reasoning":{"type":"string","nullable":true,"description":"Reasoning trace emitted by reasoning-capable models, when present."},"refusal":{"type":"string","nullable":true,"description":"Refusal message emitted by the model, when it declines to answer."},"tool_calls":{"type":"array","nullable":true,"description":"Tool calls generated by the model, if any.","items":{"$ref":"#/components/schemas/ChatCompletionToolCall"}}}},"ChatCompletionToolCall":{"type":"object","description":"A tool call generated by the model.","required":["id","type","function"],"properties":{"id":{"type":"string","description":"Unique identifier for this tool call."},"type":{"type":"string","description":"Always `function`.","enum":["function"]},"function":{"type":"object","description":"The function the model called.","required":["name","arguments"],"properties":{"name":{"type":"string","description":"The name of the function to call."},"arguments":{"type":"string","description":"JSON-encoded arguments to pass to the function."}}}}}}}}
```

## The ChatCompletionToolCall object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ChatCompletionToolCall":{"type":"object","description":"A tool call generated by the model.","required":["id","type","function"],"properties":{"id":{"type":"string","description":"Unique identifier for this tool call."},"type":{"type":"string","description":"Always `function`.","enum":["function"]},"function":{"type":"object","description":"The function the model called.","required":["name","arguments"],"properties":{"name":{"type":"string","description":"The name of the function to call."},"arguments":{"type":"string","description":"JSON-encoded arguments to pass to the function."}}}}}}}}
```

## The ResponsesUsage object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesUsage":{"type":"object","description":"Token usage for the response.","properties":{"input_tokens":{"type":"integer","description":"Number of tokens in the input."},"output_tokens":{"type":"integer","description":"Number of tokens generated."},"total_tokens":{"type":"integer","description":"Total tokens consumed by the request."},"output_tokens_details":{"$ref":"#/components/schemas/ResponsesOutputTokensDetails"}}},"ResponsesOutputTokensDetails":{"type":"object","description":"Breakdown of `output_tokens`, present when the model reports one.","properties":{"reasoning_tokens":{"type":"integer","description":"Tokens the model spent reasoning. They are already counted in `output_tokens`."}}}}}}
```

## The ResponsesOutputTokensDetails object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesOutputTokensDetails":{"type":"object","description":"Breakdown of `output_tokens`, present when the model reports one.","properties":{"reasoning_tokens":{"type":"integer","description":"Tokens the model spent reasoning. They are already counted in `output_tokens`."}}}}}}
```

## The ResponsesIncompleteDetails object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"ResponsesIncompleteDetails":{"type":"object","description":"Why the response is incomplete.","required":["reason"],"properties":{"reason":{"type":"string","description":"`max_output_tokens` when the output reaches `max_output_tokens` before it is\nfinished.\n","enum":["max_output_tokens","content_filter"]}}}}}}
```

## The TranscriptionRequest object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"TranscriptionRequest":{"type":"object","description":"Request payload for transcribing audio. Sent as `multipart/form-data`, with the\naudio itself as the binary file part `file`.\n","required":["model","file"],"properties":{"model":{"type":"string","description":"Model identifier to use for transcription.","minLength":1,"maxLength":128,"pattern":"^[a-zA-Z0-9._/-]+$"},"file":{"type":"string","format":"binary","description":"The audio to transcribe, uploaded as a file part, of at most 15 MiB. A larger file is rejected with a 413. FLAC, MP3, MP4, MPEG, M4A, Ogg, WAV and WebM are accepted."},"language":{"type":"string","description":"Language of the input audio as an ISO-639-1 code, such as `en` or `de`. Supplying it improves accuracy and latency. Omit it to have the language detected."},"prompt":{"type":"string","description":"Text to guide the transcript's style, or to supply vocabulary the audio is likely to contain. How much it changes the result is model-specific."},"response_format":{"type":"string","description":"Format of the transcript. `json` wraps the text in an object, `text` returns\nit as a plain body, and `verbose_json` adds the duration and per-segment\ntimings. `verbose_json` is model-specific and is rejected with a `400` for\nmodels that cannot produce timings.\n","enum":["json","text","verbose_json"],"default":"json"},"temperature":{"type":"number","format":"double","description":"Sampling temperature. Higher values make the transcript more varied, lower values more deterministic.","minimum":0,"maximum":1,"default":0},"seed":{"type":"integer","description":"Seed for deterministic sampling. Repeated requests with the same seed and\nparameters return the same transcript on a best-effort basis. It only has\nan effect when `temperature` is above 0: at the default of 0 decoding is\ngreedy and already deterministic.\n\nThis is an extension, not part of the OpenAI Audio API. OpenAI SDK clients\nsend it through `extra_body` (for example `extra_body={\"seed\": 42}` in\nPython), which for this multipart endpoint arrives as the form field `seed`.\n"},"stream":{"type":"boolean","description":"If true, stream the transcript as Server-Sent Events. Not supported: a request\nwith `stream` set to true is rejected with a 400. Omit the field or set it to\n`false`.\n","default":false}}}}}}
```

## The TranscriptionResponse object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"TranscriptionResponse":{"type":"object","description":"Transcript of the supplied audio. Which fields are present depends on the\nrequest's `response_format`: `json` returns `text` and `usage`, and\n`verbose_json` returns `text` with `duration`, `language` and `segments`.\n","required":["text"],"properties":{"text":{"type":"string","description":"The transcribed text."},"usage":{"$ref":"#/components/schemas/TranscriptionUsage"},"language":{"type":"string","description":"Language of the input audio, detected when it was not supplied. Present\nonly for `verbose_json`, when the model reports it.\n"},"duration":{"type":"number","format":"double","description":"Length of the input audio in seconds. Present, and always set, for\n`verbose_json`.\n"},"segments":{"type":"array","description":"The transcript split into timed segments. Present only for `verbose_json`,\nand absent there too for models that do not report timings.\n","items":{"$ref":"#/components/schemas/TranscriptionSegment"}}}},"TranscriptionUsage":{"type":"object","description":"How much audio was transcribed, which is what the request is billed on.","required":["type","seconds"],"properties":{"type":{"type":"string","description":"The quantity `seconds` measures.","enum":["duration"]},"seconds":{"type":"integer","description":"Length of the input audio in seconds, rounded up to a whole second."}}},"TranscriptionSegment":{"type":"object","description":"One timed span of the transcript.","required":["id","start","end","text"],"properties":{"id":{"type":"integer","description":"Position of the segment in the transcript, starting at zero."},"seek":{"type":"integer","description":"Offset the decoder seeked to for this segment."},"start":{"type":"number","format":"double","description":"Start time of the segment in seconds."},"end":{"type":"number","format":"double","description":"End time of the segment in seconds."},"text":{"type":"string","description":"Text of the segment."},"tokens":{"type":"array","description":"Token ids the segment's text decoded from.","items":{"type":"integer"}},"temperature":{"type":"number","format":"double","description":"Sampling temperature the segment was produced with."},"avg_logprob":{"type":"number","format":"double","description":"Average log probability of the segment. Values below -1 indicate the transcript for this span is unreliable."},"compression_ratio":{"type":"number","format":"double","description":"Compression ratio of the segment's text. Values above 2.4 indicate repetitive output."},"no_speech_prob":{"type":"number","format":"double","description":"Probability that the segment contains no speech. Reported only by models that measure it."}}}}}}
```

## The TranscriptionUsage object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"TranscriptionUsage":{"type":"object","description":"How much audio was transcribed, which is what the request is billed on.","required":["type","seconds"],"properties":{"type":{"type":"string","description":"The quantity `seconds` measures.","enum":["duration"]},"seconds":{"type":"integer","description":"Length of the input audio in seconds, rounded up to a whole second."}}}}}}
```

## The TranscriptionSegment object

```json
{"openapi":"3.0.3","info":{"title":"IONOS CLOUD - OpenAI compatible AI Model Hub API","version":"1.0.0"},"components":{"schemas":{"TranscriptionSegment":{"type":"object","description":"One timed span of the transcript.","required":["id","start","end","text"],"properties":{"id":{"type":"integer","description":"Position of the segment in the transcript, starting at zero."},"seek":{"type":"integer","description":"Offset the decoder seeked to for this segment."},"start":{"type":"number","format":"double","description":"Start time of the segment in seconds."},"end":{"type":"number","format":"double","description":"End time of the segment in seconds."},"text":{"type":"string","description":"Text of the segment."},"tokens":{"type":"array","description":"Token ids the segment's text decoded from.","items":{"type":"integer"}},"temperature":{"type":"number","format":"double","description":"Sampling temperature the segment was produced with."},"avg_logprob":{"type":"number","format":"double","description":"Average log probability of the segment. Values below -1 indicate the transcript for this span is unreliable."},"compression_ratio":{"type":"number","format":"double","description":"Compression ratio of the segment's text. Values above 2.4 indicate repetitive output."},"no_speech_prob":{"type":"number","format":"double","description":"Probability that the segment contains no speech. Reported only by models that measure it."}}}}}}
```


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.ionos.com/cloud/api-reference/ai/ai-model-hub/models-1.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
