GET
/v1/schemas/gemini/chat/v1beta/models/{modelsId}:streamGenerateContent?kind=output
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace343ff1b68827292bea63e0965dec5cfd8c97953c3345c7c552e91fce8bb4ab90{
"fetchedAt": 1794375004,
"extractorVersion": "2",
"verifiedAt": null
} |
Response body
6 properties · 0 required · 49 $defs| property | type | description | constraints |
|---|---|---|---|
| responseId | string | Output only. response_id is used to identify each response. | |
| usageMetadata | UsageMetadata | Metadata on the generation request's token usage. | |
| modelVersion | string | Output only. The model version used to generate the response. | |
| modelStatus | ModelStatus | The status of the underlying model. This is used to indicate the stage of the underlying model and the retirement time if applicable. | |
| candidates | Candidate[] | Candidate responses from the model. | |
| promptFeedback | PromptFeedback | A set of the feedback metadata the prompt specified in `GenerateContentRequest.content`. |
Types
49 $defsAttributionSourceIdobject
Identifier for the source contributing to this attribution.
| semanticRetrieverChunk | SemanticRetrieverChunk | Identifier for a `Chunk` retrieved via Semantic Retriever specified in the `GenerateAnswerRequest` using `SemanticRetrieverConfig`. | |
| groundingPassage | GroundingPassageId | Identifier for a part within a `GroundingPassage`. |
AudioTranscriptionobject
The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label.
| speakerLabel | string | Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set. | |
| words | WordInfo[] | Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set. | |
| text | string | Required. The transcription text of this audio segment. |
Blobobject
Raw media bytes. Text should not be sent as raw bytes, use the 'text' field.
| mimeType | string | The IANA standard MIME type of the source data. Examples of supported types: - Images: image/png, image/jpeg, image/jpg, image/webp, image/heic, image/heif, image/gif, image/avif - Audio: audio/*, video/audio/s16le, video/audio/wav - Video: video/* - Text: tex… | |
| data | string | Raw bytes for media formats. | format: byte |
| displayName | string | Optional. Specifies the name used to refer to this blob to the model (e.g. "my_blob.png"). Used as the blob reference identifier when `verbalization_mode` is set to `REFERENCE_ONLY`. |
Candidateobject
A response candidate generated from the model.
| content | Content | The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn. | |
| groundingMetadata | GroundingMetadata | Metadata returned to client when grounding is enabled. | |
| index | integer | Output only. Index of the candidate in the list of response candidates. | format: int32 |
| finishReason | enum | Optional. Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating tokens. | FINISH_REASON_UNSPECIFIED | STOP | MAX_TOKENS | SAFETY | RECITATION | LANGUAGE · +17 more |
| tokenCount | integer | Output only. Token count for this candidate. | format: int32 |
| avgLogprobs | number | Output only. Average log probability score of the candidate. | format: double |
| safetyRatings | SafetyRating[] | List of ratings for the safety of a response candidate. There is at most one rating per category. | |
| finishMessage | string | Optional. Output only. Details the reason why the model stopped generating tokens. This is populated only when `finish_reason` is set. | |
| urlContextMetadata | UrlContextMetadata | Metadata related to url context retrieval tool. | |
| citationMetadata | CitationMetadata | A collection of source attributions for a piece of content. | |
| continuationToken | string | An optional opaque continuation token returned when `finish_reason` is `CONTINUATION`. Clients can pass this token in a subsequent `GenerateContentRequest` to continue generation. | format: byte |
| groundingAttributions | GroundingAttribution[] | Output only. Attribution information for sources that contributed to a grounded answer. This field is populated for `GenerateAnswer` calls. | |
| logprobsResult | LogprobsResult | Logprobs Result |
CitationMetadataobject
A collection of source attributions for a piece of content.
| citationSources | CitationSource[] | Citations to sources for a specific response. |
CitationSourceobject
A citation to a source for a portion of a specific response.
| endIndex | integer | Optional. End of the attributed segment, exclusive. | format: int32 |
| uri | string | Optional. URI that is attributed as a source for a portion of the text. | |
| license | string | Optional. License for the GitHub project that is attributed as a source for segment. License info is required for code citations. | |
| startIndex | integer | Optional. Start of segment of the response that is attributed to this source. Index indicates the start of the segment, measured in bytes. | format: int32 |
CodeExecutionResultobject
Result of executing the `ExecutableCode`. Generated only when the `CodeExecution` tool is used.
| output | string | Optional. Contains stdout when code execution is successful, stderr or other description otherwise. | |
| outcome | enum | Required. Outcome of the code execution. | OUTCOME_UNSPECIFIED | OUTCOME_OK | OUTCOME_FAILED | OUTCOME_DEADLINE_EXCEEDED |
| id | string | Optional. The identifier of the `ExecutableCode` part this result is for. Only populated if the corresponding `ExecutableCode` has an id. |
Contentobject
The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn.
| role | string | Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset. | |
| parts | Part[] | Ordered `Parts` that constitute a single message. Parts may have different MIME types. |
ExecutableCodeobject
Code generated by the model that is meant to be executed, and the result returned to the model. Only generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding `CodeExecutionResult` will also be generat…
| language | enum | Required. Programming language of the `code`. | LANGUAGE_UNSPECIFIED | PYTHON |
| code | string | Required. The code to be executed. | |
| id | string | Optional. Unique identifier of the `ExecutableCode` part. The server returns the `CodeExecutionResult` with the matching `id`. |
FileDataobject
URI based data.
| displayName | string | Optional. Specifies the name used to refer to this file to the model (e.g. "my_file.pdf"). Used as the file reference identifier when `verbalization_mode` is set to `REFERENCE_ONLY`. | |
| fileUri | string | Required. URI. | |
| mimeType | string | Optional. The IANA standard MIME type of the source data. |
FunctionCallobject
A predicted `FunctionCall` returned from the model that contains a string representing the `FunctionDeclaration.name` with the arguments and their values.
| id | string | Optional. Unique identifier of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. | |
| args | object | Optional. The function parameters and values in JSON object format. | |
| name | string | Required. The name of the function to call. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 128. |
FunctionResponseobject
The result output from a `FunctionCall` that contains a string representing the `FunctionDeclaration.name` and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a`FunctionCall` m…
| name | string | Required. The name of the function to call. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 128. | |
| scheduling | enum | Optional. Specifies how the response should be scheduled in the conversation. Only applicable to NON_BLOCKING function calls, is ignored otherwise. Defaults to WHEN_IDLE. | SCHEDULING_UNSPECIFIED | SILENT | WHEN_IDLE | INTERRUPT |
| response | object | Required. The function response in JSON object format. Callers can use any keys of their choice that fit the function's syntax to return the function output, e.g. "output", "result", etc. In particular, if the function call failed to execute, the response can … | |
| parts | FunctionResponsePart[] | Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. | |
| willContinue | boolean | Optional. Signals that function call continues, and more responses will be returned, turning the function call into a generator. Is only applicable to NON_BLOCKING function calls, is ignored otherwise. If set to false, future responses will not be considered. … | |
| id | string | Optional. The identifier of the function call this response is for. Populated by the client to match the corresponding function call `id`. |
FunctionResponseBlobobject
Raw media bytes for function response. Text should not be sent as raw bytes, use the 'FunctionResponse.response' field.
| mimeType | string | The IANA standard MIME type of the source data. Examples: - image/png - image/jpeg If an unsupported MIME type is provided, an error will be returned. For a complete list of supported types, see [Supported file formats](https://aistudio.google.com/docs/file-in… | |
| displayName | string | Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs, and to reference the blob from `FunctionResponse.response` (for example, via `{"$ref": "DISPLAY_NAME"}`). | |
| data | string | Raw bytes for media formats. | format: byte |
FunctionResponseFileDataobject
URI based data for function response.
| mimeType | string | The IANA standard MIME type of the source data. If an unsupported MIME type is provided, an error will be returned. For a complete list of supported types, see [Multimodal function responses](https://aistudio.google.com/docs/function-calling#multimodal) and [S… | |
| fileUri | string | Required. URI. | |
| displayName | string | Optional. Display name of the file. Used to provide a label or filename to distinguish file data, and to reference the file from `FunctionResponse.response` (for example, via `{"$ref": "DISPLAY_NAME"}`). |
FunctionResponsePartobject
A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. Media can …
| fileData | FunctionResponseFileData | URI based data for function response. | |
| inlineData | FunctionResponseBlob | Raw media bytes for function response. Text should not be sent as raw bytes, use the 'FunctionResponse.response' field. | |
| mediaProcessing | enum | Optional. How the model processes this part's media for understanding. Only meaningful for video parts (`inline_data` or `file_data` with video mime). Non-video parts ignore this field. | MEDIA_PROCESSING_UNSPECIFIED | STATIC | AGENTIC |
GoogleAiGenerativelanguageV1betaGroundingSupportobject
Grounding support.
| groundingChunkIndices | integer[] | Optional. A list of indices (into 'grounding_chunk' in `response.candidate.grounding_metadata`) specifying the citations associated with the claim. For instance [1,3,4] means that grounding_chunk[1], grounding_chunk[3], grounding_chunk[4] are the retrieved con… | |
| renderedParts | integer[] | Output only. Indices into the `parts` field of the candidate's content. These indices specify which rendered parts are associated with this support source. | |
| confidenceScores | number[] | Optional. Confidence score of the support references. Ranges from 0 to 1. 1 is the most confident. This list must have the same size as the grounding_chunk_indices. | |
| segment | GoogleAiGenerativelanguageV1betaSegment | Segment of the content. |
GoogleAiGenerativelanguageV1betaSegmentobject
Segment of the content.
| text | string | The text corresponding to the segment from the response. | |
| endIndex | integer | End index in the given Part, measured in bytes. Offset from the start of the Part, exclusive, starting at zero. | format: int32 |
| startIndex | integer | Start index in the given Part, measured in bytes. Offset from the start of the Part, inclusive, starting at zero. | format: int32 |
| partIndex | integer | The index of a Part object within its parent Content object. | format: int32 |
GroundingAttributionobject
Attribution for a source that contributed to an answer.
| sourceId | AttributionSourceId | Identifier for the source contributing to this attribution. | |
| content | Content | The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn. |
GroundingChunkobject
A `GroundingChunk` represents a segment of supporting evidence that grounds the model's response. It can be a chunk from the web, a retrieved context from a file, or information from Google Maps.
| maps | Maps | A grounding chunk from Google Maps. A Maps chunk corresponds to a single place. | |
| image | Image | Chunk from image search. | |
| web | Web | Chunk from the web. | |
| retrievedContext | RetrievedContext | Chunk from context retrieved by the file search tool. |
GroundingChunkCustomMetadataobject
User provided metadata about the GroundingFact.
| stringValue | string | Optional. The string value of the metadata. | |
| key | string | The key of the metadata. | |
| numericValue | number | Optional. The numeric value of the metadata. The expected range for this value depends on the specific `key` used. | format: float |
| stringListValue | GroundingChunkStringList | A list of string values. |
GroundingChunkStringListobject
A list of string values.
| values | string[] | The string values of the list. |
GroundingMetadataobject
Metadata returned to client when grounding is enabled.
| groundingChunks | GroundingChunk[] | List of supporting references retrieved from specified grounding source. When streaming, this only contains the grounding chunks that have not been included in the grounding metadata of previous responses. | |
| googleMapsWidgetContextToken | string | Optional. Resource name of the Google Maps widget context token that can be used with the PlacesContextElement widget in order to render contextual data. Only populated in the case that grounding with Google Maps is enabled. | |
| retrievalMetadata | RetrievalMetadata | Metadata related to retrieval in the grounding flow. | |
| webSearchQueries | string[] | Web search queries for the following-up web search. | |
| groundingSupports | GoogleAiGenerativelanguageV1betaGroundingSupport[] | List of grounding support. | |
| searchEntryPoint | SearchEntryPoint | Google search entry point. | |
| imageSearchQueries | string[] | Image search queries used for grounding. |
GroundingPassageIdobject
Identifier for a part within a `GroundingPassage`.
| passageId | string | Output only. ID of the passage matching the `GenerateAnswerRequest`'s `GroundingPassage.id`. | |
| partIndex | integer | Output only. Index of the part within the `GenerateAnswerRequest`'s `GroundingPassage.content`. | format: int32 |
Imageobject
Chunk from image search.
| domain | string | The root domain of the web page that the image is from, e.g. "example.com". | |
| imageUri | string | The image asset URL. | |
| title | string | The title of the web page that the image is from. | |
| sourceUri | string | The web page URI for attribution. |
LogprobsResultobject
Logprobs Result
| logProbabilitySum | number | Sum of log probabilities for all tokens. | format: float |
| topCandidates | TopCandidates[] | Length = total number of decoding steps. | |
| chosenCandidates | LogprobsResultCandidate[] | Length = total number of decoding steps. The chosen candidates may or may not be in top_candidates. |
LogprobsResultCandidateobject
Candidate for the logprobs token and score.
| token | string | The candidate’s token string value. | |
| tokenId | integer | The candidate’s token id value. | format: int32 |
| logProbability | number | The candidate's log probability. | format: float |
Mapsobject
A grounding chunk from Google Maps. A Maps chunk corresponds to a single place.
| placeId | string | The ID of the place, in `places/{place_id}` format. A user can use this ID to look up that place. | |
| uri | string | URI reference of the place. | |
| title | string | Title of the place. | |
| text | string | Text description of the place answer. | |
| placeAnswerSources | PlaceAnswerSources | Collection of sources that provide answers about the features of a given place in Google Maps. Each PlaceAnswerSources message corresponds to a specific place in Google Maps. The Google Maps tool used these sources in order to answer questions about features o… |
ModalityTokenCountobject
Represents token counting info for a single modality.
| modality | enum | The modality associated with this token count. | MODALITY_UNSPECIFIED | TEXT | IMAGE | VIDEO | AUDIO | DOCUMENT |
| tokenCount | integer | Number of tokens. | format: int32 |
ModelStatusobject
The status of the underlying model. This is used to indicate the stage of the underlying model and the retirement time if applicable.
| retirementTime | string | The time at which the model will be retired. | format: google-datetime |
| message | string | A message explaining the model status. | |
| modelStage | enum | The stage of the underlying model. | MODEL_STAGE_UNSPECIFIED | UNSTABLE_EXPERIMENTAL | EXPERIMENTAL | PREVIEW | STABLE | LEGACY · +2 more |
Partobject
A datatype containing media that is part of a multi-part `Content` message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. A `Part` must have a fixed IANA MIME type identifying th…
| videoMetadata | VideoMetadata | Metadata describes the input video content. Set this in `Part.video_metadata` or `FunctionResponsePart.video_metadata` when `inline_data` or `file_data` contains video to configure static video preprocessing (such as time clipping, frame rate, maximum frame co… | |
| partMetadata | object | Custom metadata associated with the Part. Agents using genai.Part as content representation may need to keep track of the additional information. For example it can be name of a file/source from which the Part originates or a way to multiplex multiple Part str… | |
| speechMetadata | SpeechMetadata | Speech metadata for `text` parts. | |
| codeExecutionResult | CodeExecutionResult | Result of executing the `ExecutableCode`. Generated only when the `CodeExecution` tool is used. | |
| inlineData | Blob | Raw media bytes. Text should not be sent as raw bytes, use the 'text' field. | |
| text | string | Inline text. | |
| executableCode | ExecutableCode | Code generated by the model that is meant to be executed, and the result returned to the model. Only generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding `CodeExecutionResult` will also be generat… | |
| thought | boolean | Optional. Indicates if the part is thought from the model. | |
| mediaProcessing | enum | Optional. How the model processes this part's media for understanding. Only meaningful for video parts (`inline_data` or `file_data` with video mime). Non-video parts ignore this field. | MEDIA_PROCESSING_UNSPECIFIED | STATIC | AGENTIC |
| toolCall | ToolCall | A predicted server-side `ToolCall` returned from the model. This message contains information about a tool that the model wants to invoke. The client is NOT expected to execute this `ToolCall`. Instead, the client should pass this `ToolCall` back to the API in… | |
| toolResponse | ToolResponse | The output from a server-side `ToolCall` execution. This message contains the results of a tool invocation that was initiated by a `ToolCall` from the model. The client should pass this `ToolResponse` back to the API in a subsequent turn within a `Content` mes… | |
| functionCall | FunctionCall | A predicted `FunctionCall` returned from the model that contains a string representing the `FunctionDeclaration.name` with the arguments and their values. | |
| audioTranscription | AudioTranscription | The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. | |
| fileData | FileData | URI based data. | |
| functionResponse | FunctionResponse | The result output from a `FunctionCall` that contains a string representing the `FunctionDeclaration.name` and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a`FunctionCall` m… | |
| mediaResolution | V1mainMediaResolution | Media resolution for tokenization. | |
| thoughtSignature | string | Optional. An opaque signature for the thought so it can be reused in subsequent requests. | format: byte |
PlaceAnswerSourcesobject
Collection of sources that provide answers about the features of a given place in Google Maps. Each PlaceAnswerSources message corresponds to a specific place in Google Maps. The Google Maps tool used these sources in order to answer questions about features o…
| reviewSnippets | ReviewSnippet[] | Snippets of reviews that are used to generate answers about the features of a given place in Google Maps. |
PromptFeedbackobject
A set of the feedback metadata the prompt specified in `GenerateContentRequest.content`.
| blockReason | enum | Optional. If set, the prompt was blocked and no candidates are returned. Rephrase the prompt. | BLOCK_REASON_UNSPECIFIED | SAFETY | OTHER | BLOCKLIST | PROHIBITED_CONTENT | IMAGE_SAFETY |
| safetyRatings | SafetyRating[] | Ratings for safety of the prompt. There is at most one rating per category. |
RetrievalMetadataobject
Metadata related to retrieval in the grounding flow.
| googleSearchDynamicRetrievalScore | number | Optional. Score indicating how likely information from google search could help answer the prompt. The score is in the range [0, 1], where 0 is the least likely and 1 is the most likely. This score is only populated when google search grounding and dynamic ret… | format: float |
RetrievedContextobject
Chunk from context retrieved by the file search tool.
| mediaId | string | Optional. The media blob resource name for multimodal file search results. Format: fileSearchStores/{file_search_store_id}/media/{blob_id} | |
| fileSearchStore | string | Optional. Name of the `FileSearchStore` containing the document. Example: `fileSearchStores/123` | |
| title | string | Optional. Title of the document. | |
| text | string | Optional. Text of the chunk. | |
| uri | string | Optional. URI reference of the semantic retrieval document. | |
| pageNumber | integer | Optional. Page number of the retrieved context, if applicable. | format: int32 |
| customMetadata | GroundingChunkCustomMetadata[] | Optional. User-provided metadata about the retrieved context. |
ReviewSnippetobject
Encapsulates a snippet of a user review that answers a question about the features of a specific place in Google Maps.
| reviewId | string | The ID of the review snippet. | |
| googleMapsUri | string | A link that corresponds to the user review on Google Maps. | |
| title | string | Title of the review. |
SafetyRatingobject
Safety rating for a piece of content. The safety rating contains the category of harm and the harm probability level in that category for a piece of content. Content is classified for safety across a number of harm categories and the probability of the harm cl…
| blocked | boolean | Was this content blocked because of this rating? | |
| probability | enum | Required. The probability of harm for this content. | HARM_PROBABILITY_UNSPECIFIED | NEGLIGIBLE | LOW | MEDIUM | HIGH |
| category | enum | Required. The category for this rating. | HARM_CATEGORY_UNSPECIFIED | HARM_CATEGORY_DEROGATORY | HARM_CATEGORY_TOXICITY | HARM_CATEGORY_VIOLENCE | HARM_CATEGORY_SEXUAL | HARM_CATEGORY_MEDICAL · +7 more |
SearchEntryPointobject
Google search entry point.
| renderedContent | string | Optional. Web content snippet that can be embedded in a web page or an app webview. | |
| sdkBlob | string | Optional. Base64 encoded JSON representing array of tuple. | format: byte |
SemanticRetrieverChunkobject
Identifier for a `Chunk` retrieved via Semantic Retriever specified in the `GenerateAnswerRequest` using `SemanticRetrieverConfig`.
| chunk | string | Output only. Name of the `Chunk` containing the attributed text. Example: `corpora/123/documents/abc/chunks/xyz` | |
| source | string | Output only. Name of the source matching the request's `SemanticRetrieverConfig.source`. Example: `corpora/123` or `corpora/123/documents/abc` |
SpeechMetadataobject
Speech metadata for `text` parts.
| style | string | Optional. Optional style instruction for the speech synthesis. | |
| speaker | string | Optional. Optional speaker name for multi-speaker synthesis. |
ToolCallobject
A predicted server-side `ToolCall` returned from the model. This message contains information about a tool that the model wants to invoke. The client is NOT expected to execute this `ToolCall`. Instead, the client should pass this `ToolCall` back to the API in…
| args | object | Optional. The tool call arguments. Example: {"arg1" : "value1", "arg2" : "value2" , ...} | |
| id | string | Optional. Unique identifier of the tool call. The server returns the tool response with the matching `id`. | |
| toolName | string | Optional. The name of the tool that was called. | |
| toolType | enum | Required. The type of tool that was called. | TOOL_TYPE_UNSPECIFIED | GOOGLE_SEARCH_WEB | GOOGLE_SEARCH_IMAGE | URL_CONTEXT | GOOGLE_MAPS | FILE_SEARCH · +1 more |
ToolResponseobject
The output from a server-side `ToolCall` execution. This message contains the results of a tool invocation that was initiated by a `ToolCall` from the model. The client should pass this `ToolResponse` back to the API in a subsequent turn within a `Content` mes…
| id | string | Optional. The identifier of the tool call this response is for. | |
| toolType | enum | Required. The type of tool that was called, matching the `tool_type` in the corresponding `ToolCall`. | TOOL_TYPE_UNSPECIFIED | GOOGLE_SEARCH_WEB | GOOGLE_SEARCH_IMAGE | URL_CONTEXT | GOOGLE_MAPS | FILE_SEARCH · +1 more |
| response | object | Optional. The tool response. |
TopCandidatesobject
Candidates with top log probabilities at each decoding step.
| candidates | LogprobsResultCandidate[] | Sorted by log probability in descending order. |
UrlContextMetadataobject
Metadata related to url context retrieval tool.
| urlMetadata | UrlMetadata[] | List of url context. |
UrlMetadataobject
Context of the a single url retrieval.
| urlRetrievalStatus | enum | Status of the url retrieval. | URL_RETRIEVAL_STATUS_UNSPECIFIE… | URL_RETRIEVAL_STATUS_SUCCESS | URL_RETRIEVAL_STATUS_ERROR | URL_RETRIEVAL_STATUS_PAYWALL | URL_RETRIEVAL_STATUS_UNSAFE |
| retrievedUrl | string | Retrieved url by the tool. |
UsageMetadataobject
Metadata on the generation request's token usage.
| promptTokenCount | integer | Number of tokens in the prompt. When `cached_content` is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content. | format: int32 |
| toolUsePromptTokenCount | integer | Output only. Number of tokens present in tool-use prompt(s). | format: int32 |
| promptTokensDetails | ModalityTokenCount[] | Output only. List of modalities that were processed in the request input. | |
| totalTokenCount | integer | Total token count for the generation request (prompt + tool-use prompt + thoughts + response candidates). | format: int32 |
| cachedContentTokenCount | integer | Number of tokens in the cached part of the prompt (the cached content) | format: int32 |
| candidatesTokensDetails | ModalityTokenCount[] | Output only. List of modalities that were returned in the response. | |
| candidatesTokenCount | integer | Total number of tokens across all the generated response candidates. | format: int32 |
| cacheTokensDetails | ModalityTokenCount[] | Output only. List of modalities of the cached content in the request input. | |
| toolUsePromptTokensDetails | ModalityTokenCount[] | Output only. List of modalities that were processed for tool-use request inputs. | |
| serviceTier | enum | Output only. Service tier of the request. | unspecified | standard | flex | priority |
| thoughtsTokenCount | integer | Output only. Number of tokens of thoughts for thinking models. | format: int32 |
V1mainMediaResolutionobject
Media resolution for tokenization.
| level | enum | The tokenization quality used for given media. for Gemini API support . | MEDIA_RESOLUTION_UNSPECIFIED | MEDIA_RESOLUTION_LOW | MEDIA_RESOLUTION_MEDIUM | MEDIA_RESOLUTION_HIGH | MEDIA_RESOLUTION_ULTRA_HIGH |
VideoMetadataobject
Metadata describes the input video content. Set this in `Part.video_metadata` or `FunctionResponsePart.video_metadata` when `inline_data` or `file_data` contains video to configure static video preprocessing (such as time clipping, frame rate, maximum frame co…
| endOffset | string | Optional. The end offset of the video. | format: google-duration |
| startOffset | string | Optional. The start offset of the video. | format: google-duration |
| fps | number | Optional. The frame rate of the video sent to the model. If not specified, the default value will be 1.0. The fps range is (0.0, 24.0]. | format: double |
Webobject
Chunk from the web.
| uri | string | Output only. URI reference of the chunk. | |
| title | string | Output only. Title of the chunk. |
WordInfoobject
Information about a single recognized word.
| word | string | Required. Transcript of the word. | |
| endOffset | string | Optional. End offset in time of the word relative to the start of the audio. | format: google-duration |
| startOffset | string | Optional. Start offset in time of the word relative to the start of the audio. | format: google-duration |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"gemini","endpointId":"v1beta/models/{modelsId}:streamGenerateContent","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}