Generate Content

POST https://api.tikway.ai/v1beta/models/{model}:generateContent

cURL

Text input

curl --request POST \
  --url https://api.tikway.ai/v1beta/models/{model}:generateContent \
  --header 'Content-Type: application/json' \
  --header 'x-goog-api-key: <api-key>' \
  --data '
{
  "systemInstruction": {
    "parts": [
      {
        "text": "You are a helpful assistant."
      }
    ]
  },
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Write a short bedtime story about a unicorn."
        }
      ]
    }
  ],
  "generationConfig": {
    "maxOutputTokens": 1024
  }
}
'

200

{
  "candidates": [
    {
      "index": 0,
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "Once upon a time, a magic backpack..."
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 10,
    "candidatesTokenCount": 12,
    "totalTokenCount": 22
  },
  "modelVersion": "gemini-2.0-flash"
}

Authorizations

x-goog-api-key · string · header · required

Tikway API Key. Passed through the x-goog-api-key request header according to the Gemini native protocol.

Path Parameters

model · string · required

Model name, in the format models/{model}.

Body

application/json

contents · object[] · required

Current conversation content. A single-round request usually has only one Content; multi-round conversations include historical and latest requests in order.

Minimum array length: 1

Hide child attributes

contents. parts · object[] · required

List of content sections.

Minimum array length: 1

Hide child attributes

contents.parts. text · string

Text input.

contents.parts. inlineData · object

Inline Base64 file data.

Hide child attributes

contents.parts.inlineData. mimeType · string

MIME type, such as image/jpeg.

contents.parts.inlineData. data · string

Base64 encoded data.

contents.parts.inlineData. displayName · string

The display name of the inline media.

contents.parts. fileData · object

A reference to the uploaded file in the File API.

Hide child attributes

contents.parts.fileData. mimeType · string

File MIME type.

contents.parts.fileData. fileUri · string

File URI.

contents.parts.fileData. displayName · string

The display name of the file.

contents.parts. functionCall · object

Function calls generated by the previous round of models.

Hide child attributes

contents.parts.functionCall. name · string

function name.

contents.parts.functionCall. args · object

function parameters.

contents.parts. functionResponse · object

The execution result of the client's function call.

Hide child attributes

contents.parts.functionResponse. name · string

function name.

contents.parts.functionResponse. response · object

Function execution return value.

contents.parts. executableCode · object

Executable code.

Hide child attributes

contents.parts.executableCode. language · string

programming language.

contents.parts.executableCode. code · string

code content.

contents.parts.executableCode. id · string

Executable code block ID.

contents.parts. codeExecutionResult · object

Code execution results.

Hide child attributes

contents.parts.codeExecutionResult. outcome · string

Execution result status.

contents.parts.codeExecutionResult. output · string

Execute output.

contents.parts.codeExecutionResult. id · string

The corresponding code block ID.

contents.parts. thought · boolean

Does this part belong to model thinking content?

contents.parts. thoughtSignature · string

Think content signatures; keep them as is on postback.

contents.parts. partMetadata · object

Custom metadata associated with the content block.

contents.parts. mediaResolution · object

The resolution of this media content block.

Hide child attributes

contents.parts.mediaResolution. level · enum<string>

Available options: MEDIA_RESOLUTION_UNSPECIFIED, MEDIA_RESOLUTION_LOW, MEDIA_RESOLUTION_MEDIUM, MEDIA_RESOLUTION_HIGH

contents.parts. mediaProcessing · string

How video content is processed.

contents.parts. audioTranscription · object

Audio transcription information.

contents.parts. speechMetadata · object

Speech synthesis related metadata.

contents.parts. toolCall · object

Server-side tool calls that need to be returned by the client.

contents.parts. toolResponse · object

The execution result of the server tool call.

contents.parts. videoMetadata · object

Video content metadata.

contents. role · enum<string>

Content roles. When omitted, it is usually treated as user.

Available options: user, model

systemInstruction · object

System commands set by developers should currently use the plain text part.

Hide child attributes

systemInstruction. parts · object[] · required

Hide child attributes

systemInstruction.parts. text · string

System command text.

tools · object[]

A list of tools that the model can use, such as function calls or code execution.

Hide child attributes

tools. functionDeclarations · object[]

List of function declarations.

Hide child attributes

tools.functionDeclarations. name · string · required

function name.

tools.functionDeclarations. description · string · required

Description of function usage.

tools.functionDeclarations. parameters · object

Function parameters JSON Schema.

tools.functionDeclarations. response · object

Function responds to JSON Schema.

tools.functionDeclarations. behavior · enum<string>

Available options: UNSPECIFIED, BLOCKING, NON_BLOCKING

tools.functionDeclarations. parametersJsonSchema · any

JSON Schema of function parameters; mutually exclusive with parameters .

tools.functionDeclarations. responseJsonSchema · any

JSON Schema of the function response; mutually exclusive with response .

tools. codeExecution · object

Enable code execution tools.

tools. googleSearch · object

Enable Google search tools.

tools. urlContext · object

Enable the URL context tool.

tools. googleSearchRetrieval · object

Google Search retrieves the configuration.

tools. computerUse · object

Computer operating tool configuration.

tools. fileSearch · object

File search tool configuration.

tools. mcpServers · object[]

Connectable MCP server.

tools. googleMaps · object

Geolocation search tool configuration.

toolConfig · object

Tool call configuration.

Hide child attributes

toolConfig. functionCallingConfig · object

Hide child attributes

toolConfig.functionCallingConfig. mode · enum<string>

Function calling pattern.

Available options: AUTO, ANY, NONE, VALIDATED

toolConfig.functionCallingConfig. allowedFunctionNames · string[]

Function names that allow automatic calling.

safetySettings · object[]

Security filtering rules; the same category can be configured at most once, overriding the default threshold for that category.

Hide child attributes

safetySettings. category · enum<string> · required

Security Category.

Available options: HARM_CATEGORY_HATE_SPEECH, HARM_CATEGORY_SEXUALLY_EXPLICIT, HARM_CATEGORY_DANGEROUS_CONTENT, HARM_CATEGORY_HARASSMENT, HARM_CATEGORY_CIVIC_INTEGRITY, HARM_CATEGORY_JAILBREAK

safetySettings. threshold · enum<string> · required

Blocking threshold.

Available options: HARM_BLOCK_THRESHOLD_UNSPECIFIED, BLOCK_LOW_AND_ABOVE, BLOCK_MEDIUM_AND_ABOVE, BLOCK_ONLY_HIGH, BLOCK_NONE, OFF

generationConfig · object

Generate and output configurations.

Hide child attributes

generationConfig. temperature · number

Sampling temperature.

Required range: 0 <= x <= 2

generationConfig. topP · number

Kernel sampling threshold.

generationConfig. topK · integer

The number of highest probability candidates retained at each step.

generationConfig. candidateCount · integer

Returns the number of candidate replies.

Required range: x >= 1

generationConfig. maxOutputTokens · integer

The maximum number of output tokens.

generationConfig. stopSequences · string[]

Stop the sequence.

Maximum array length: 5

generationConfig. responseMimeType · enum<string>

Output MIME type.

Available options: text/plain, application/json, text/x.enum

generationConfig. responseSchema · object · deprecated

The JSON Schema that application/json output should follow.

generationConfig. responseJsonSchema · object

The raw JSON Schema of the JSON output.

generationConfig. responseModalities · enum<string>[]

The requested output modal.

Available options: MODALITY_UNSPECIFIED, TEXT, IMAGE, AUDIO

generationConfig. thinkingConfig · object

Hide child attributes

generationConfig.thinkingConfig. thinkingBudget · integer

Think about token budgeting.

generationConfig.thinkingConfig. includeThoughts · boolean

Whether to include a reflection summary in the response.

generationConfig.thinkingConfig. thinkingLevel · enum<string>

Model thinking depth.

Available options: THINKING_LEVEL_UNSPECIFIED, MINIMAL, LOW, MEDIUM, HIGH

generationConfig. mediaResolution · enum<string>

Media input resolution settings.

Available options: MEDIA_RESOLUTION_UNSPECIFIED, MEDIA_RESOLUTION_LOW, MEDIA_RESOLUTION_MEDIUM, MEDIA_RESOLUTION_HIGH

generationConfig. seed · integer

Decode the random seed.

generationConfig. presencePenalty · number

Existence penalty for existing tokens.

generationConfig. frequencyPenalty · number

Frequency penalty for existing tokens.

generationConfig. responseLogprobs · boolean

Whether to return the token log probability in the response.

generationConfig. logprobs · integer

The number of high-probability candidate tokens returned; only valid when responseLogprobs is true.

Required range: 0 <= x <= 20

generationConfig. enableEnhancedCivicAnswers · boolean

Enable enhanced citizen question answering.

generationConfig. speechConfig · object

Speech generation configuration.

Hide child attributes

generationConfig.speechConfig. voiceConfig · object

Single voice configuration.

generationConfig.speechConfig. multiSpeakerVoiceConfig · object

Multi-speaker sound configuration.

generationConfig.speechConfig. languageCode · string

BCP-47 language code for speech.

generationConfig. imageConfig · object

Image generation configuration.

Hide child attributes

generationConfig.imageConfig. aspectRatio · string

The aspect ratio of the generated image.

generationConfig.imageConfig. imageSize · enum<string>

Generate image dimensions.

Available options: 512, 1K, 2K, 4K

generationConfig. enableAffectiveDialog · boolean

Adjust responses based on detected emotions.

generationConfig. responseFormat · object

Configure text, audio and image output formats separately.

Hide child attributes

generationConfig.responseFormat. text · object

Hide child attributes

generationConfig.responseFormat.text. mimeType · enum<string>

Available options: MIME_TYPE_UNSPECIFIED, APPLICATION_JSON, TEXT_PLAIN

generationConfig.responseFormat.text. schema · any

The JSON Schema that the text output follows.

generationConfig.responseFormat. audio · object

Hide child attributes

generationConfig.responseFormat.audio. mimeType · string

Audio MIME type.

generationConfig.responseFormat.audio. delivery · string

Audio return method.

generationConfig.responseFormat.audio. sampleRate · integer

generationConfig.responseFormat.audio. bitRate · integer

generationConfig.responseFormat. image · object

Hide child attributes

generationConfig.responseFormat.image. mimeType · string

Image MIME type.

generationConfig.responseFormat.image. delivery · string

Image return method.

generationConfig.responseFormat.image. aspectRatio · string

Image aspect ratio.

generationConfig.responseFormat.image. imageSize · string

Image size.

generationConfig. translationConfig · object

Translation configuration.

Hide child attributes

generationConfig.translationConfig. targetLanguageCode · string · required

The BCP-47 code for the target language.

generationConfig.translationConfig. echoTargetLanguage · boolean

generationConfig. audioTranscriptionConfig · object

Audio transcription configuration.

Hide child attributes

generationConfig.audioTranscriptionConfig. languageCodes · string[]

Language tips.

generationConfig.audioTranscriptionConfig. adaptationPhrases · string[] · deprecated

Voice adaptation prompt phrase.

generationConfig.audioTranscriptionConfig. customVocabulary · string[]

Custom terms.

generationConfig.audioTranscriptionConfig. wordTimestamp · boolean

generationConfig.audioTranscriptionConfig. diarization · boolean

generationConfig.audioTranscriptionConfig. mode · enum<string>

Available options: VERBATIM, SMART

generationConfig.audioTranscriptionConfig. languageAuto · object · deprecated

Deprecated; use languageCodes.

generationConfig.audioTranscriptionConfig. languageHints · object · deprecated

Deprecated; use languageCodes.

Hide child attributes

generationConfig.audioTranscriptionConfig.languageHints. languageCodes · string[]

cachedContent · string

The cached content name to use as context, in the format cachedContents/{cachedContent}.

serviceTier · enum<string>

Request service level.

Available options: unspecified, standard, flex, priority

store · boolean

Whether to log this request; if set, it will override the project-level log configuration.

labels · object

Request tags; keys such as safety_identifier can be used.

Hide child attributes

labels. {key} · string

Response

200 - application/json

Gemini API: models.generateContent normal response. Fully inline and suitable for importing into Apifox.

candidates · object[]

A list of candidate responses generated by the model.

Hide child attributes

candidates. index · integer

Candidate reply index.

candidates. content · object

Candidate reply content.

Hide child attributes

candidates.content. role · enum<string>

Role, fixed as model.

Available options: model

candidates.content. parts · object[]

Reply content part.

Hide child attributes

candidates.content.parts. text · string

Generated text.

candidates.content.parts. inlineData · object

Media data generated inline.

Hide child attributes

candidates.content.parts.inlineData. mimeType · string

candidates.content.parts.inlineData. data · string

Base64 encoded data.

candidates.content.parts.inlineData. displayName · string

The display name of the inline media.

candidates.content.parts. fileData · object

Hide child attributes

candidates.content.parts.fileData. mimeType · string

candidates.content.parts.fileData. fileUri · string

candidates.content.parts.fileData. displayName · string

The display name of the file.

candidates.content.parts. functionCall · object

The model request calls the function.

Hide child attributes

candidates.content.parts.functionCall. name · string

function name.

candidates.content.parts.functionCall. args · object

function parameters.

candidates.content.parts.functionCall. id · string

Function call ID.

candidates.content.parts. executableCode · object

Hide child attributes

candidates.content.parts.executableCode. language · string

candidates.content.parts.executableCode. code · string

candidates.content.parts.executableCode. id · string

Executable code block ID.

candidates.content.parts. codeExecutionResult · object

Hide child attributes

candidates.content.parts.codeExecutionResult. outcome · string

candidates.content.parts.codeExecutionResult. output · string

candidates.content.parts.codeExecutionResult. id · string

The corresponding code block ID.

candidates.content.parts. thought · boolean

Whether it is the content of thinking.

candidates.content.parts. thoughtSignature · string

Think about signing.

candidates.content.parts. partMetadata · object

Custom metadata associated with the content block.

candidates.content.parts. mediaResolution · object

The resolution of this media content block.

Hide child attributes

candidates.content.parts.mediaResolution. level · enum<string>

Available options: MEDIA_RESOLUTION_UNSPECIFIED, MEDIA_RESOLUTION_LOW, MEDIA_RESOLUTION_MEDIUM, MEDIA_RESOLUTION_HIGH

candidates.content.parts. mediaProcessing · string

How video content is processed.

candidates.content.parts. audioTranscription · object

Audio transcription information.

candidates.content.parts. speechMetadata · object

Speech synthesis related metadata.

candidates.content.parts. toolCall · object

Server-side tool calls that need to be returned by the client.

candidates.content.parts. toolResponse · object

The execution result of the server tool call.

candidates.content.parts. videoMetadata · object

Video content metadata.

candidates. finishReason · string

The ending reason for the candidate reply.

candidates. finishMessage · string

A description of the reason for ending.

candidates. safetyRatings · object[]

The security rating of the candidate reply.

Hide child attributes

candidates.safetyRatings. category · string

candidates.safetyRatings. probability · string

candidates.safetyRatings. blocked · boolean

candidates. citationMetadata · object

Reference metadata.

candidates. tokenCount · integer

Number of candidate reply tokens.

candidates. avgLogprobs · number

Average log probability of candidate responses.

candidates. logprobsResult · object

Term log probability results.

candidates. urlContextMetadata · object

URL context metadata.

promptFeedback · object

Feedback when prompt words are blocked or filtered.

Hide child attributes

promptFeedback. blockReason · string

Blocking reasons.

promptFeedback. blockReasonMessage · string

Description of the reason for blocking.

promptFeedback. safetyRatings · string[]

Prompt word safety rating.

usageMetadata · object

Word usage statistics.

Hide child attributes

usageMetadata. promptTokenCount · integer

Prompt word number.

usageMetadata. candidatesTokenCount · integer

Number of candidate reply tokens.

usageMetadata. totalTokenCount · integer

The total number of tokens.

usageMetadata. cachedContentTokenCount · integer

The number of cached content tokens.

usageMetadata. thoughtsTokenCount · integer

Think about word count.

usageMetadata. toolUsePromptTokenCount · integer

Tool usage hint word token number.

modelVersion · string

The actual model version used.

responseId · string

Response unique ID.