> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ttapi.io/llms.txt
> Use this file to discover all available pages before exploring further.
# Gemini Generate Content
> Generates a Gemini response using the native generateContent REST request and response format.
Request and response fields follow the official Gemini API structure. See the
Google API reference
for the complete specification.
Use `contents` for text or multimodal conversation turns. The endpoint also
supports system instructions, tools, safety settings, cached content, structured
output, thinking configuration, and model-specific generation options.
## OpenAPI
````yaml openapi/en/llm.json POST /v1beta/models/{model}:generateContent
openapi: 3.1.0
info:
title: LLM API DOCS
version: 1.0.0
description: TTAPI LLM API service.
servers:
- url: https://api.ttapi.io
security: []
paths:
/v1beta/models/{model}:generateContent:
post:
summary: Generate Gemini content
description: >-
Generates a Gemini response using the native generateContent REST
request and response format.
operationId: generateGeminiContent
parameters:
- name: model
in: path
required: true
description: Gemini model ID.
schema:
type: string
example: gemini-3.5-flash
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/GeminiGenerateContentRequest'
responses:
'200':
description: Successful Gemini GenerateContentResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/GeminiGenerateContentResponse'
'400':
$ref: '#/components/responses/400Response'
'401':
$ref: '#/components/responses/401Response'
security:
- CustomApiKey: []
components:
schemas:
GeminiGenerateContentRequest:
type: object
description: Request body for the Gemini generateContent REST format.
properties:
contents:
type: array
description: >-
Current conversation content. Include the full history for
multi-turn requests.
items:
$ref: '#/components/schemas/GeminiContent'
minItems: 1
tools:
type: array
description: >-
Tools the model may use, such as function declarations, code
execution, or supported built-in tools.
items:
type: object
additionalProperties: true
toolConfig:
type: object
description: Configuration shared by the tools in this request.
additionalProperties: true
safetySettings:
type: array
description: Per-category safety blocking settings.
items:
$ref: '#/components/schemas/GeminiSafetySetting'
systemInstruction:
$ref: '#/components/schemas/GeminiContent'
generationConfig:
$ref: '#/components/schemas/GeminiGenerationConfig'
cachedContent:
type: string
example: cachedContents/abc123
description: >-
Cached content resource to use as context. Format:
cachedContents/{cachedContent}.
serviceTier:
type: string
enum:
- unspecified
- standard
- flex
- priority
description: Service tier for this request.
store:
type: boolean
description: Overrides the project-level request logging configuration.
required:
- contents
GeminiGenerateContentResponse:
type: object
properties:
candidates:
type: array
items:
$ref: '#/components/schemas/GeminiCandidate'
promptFeedback:
type: object
properties:
blockReason:
type: string
safetyRatings:
type: array
items:
type: object
additionalProperties: true
usageMetadata:
$ref: '#/components/schemas/GeminiUsageMetadata'
modelVersion:
type: string
responseId:
type: string
modelStatus:
type: object
additionalProperties: true
GeminiContent:
type: object
properties:
role:
type: string
enum:
- user
- model
- system
description: Content producer. Conversation turns normally use user or model.
parts:
type: array
items:
$ref: '#/components/schemas/GeminiPart'
minItems: 1
required:
- parts
GeminiSafetySetting:
type: object
properties:
category:
type: string
enum:
- HARM_CATEGORY_HARASSMENT
- HARM_CATEGORY_HATE_SPEECH
- HARM_CATEGORY_SEXUALLY_EXPLICIT
- HARM_CATEGORY_DANGEROUS_CONTENT
- HARM_CATEGORY_CIVIC_INTEGRITY
threshold:
type: string
enum:
- HARM_BLOCK_THRESHOLD_UNSPECIFIED
- BLOCK_LOW_AND_ABOVE
- BLOCK_MEDIUM_AND_ABOVE
- BLOCK_ONLY_HIGH
- BLOCK_NONE
- 'OFF'
required:
- category
- threshold
GeminiGenerationConfig:
type: object
description: Generation and output configuration. Availability varies by model.
properties:
stopSequences:
type: array
maxItems: 5
items:
type: string
responseMimeType:
type: string
enum:
- text/plain
- application/json
- text/x.enum
responseSchema:
type: object
additionalProperties: true
responseJsonSchema:
type: object
additionalProperties: true
responseModalities:
type: array
items:
type: string
enum:
- TEXT
- IMAGE
- AUDIO
candidateCount:
type: integer
minimum: 1
default: 1
maxOutputTokens:
type: integer
minimum: 1
temperature:
type: number
minimum: 0
maximum: 2
topP:
type: number
minimum: 0
maximum: 1
topK:
type: integer
minimum: 1
seed:
type: integer
presencePenalty:
type: number
frequencyPenalty:
type: number
responseLogprobs:
type: boolean
logprobs:
type: integer
minimum: 0
maximum: 20
enableEnhancedCivicAnswers:
type: boolean
thinkingConfig:
type: object
properties:
includeThoughts:
type: boolean
thinkingBudget:
type: integer
thinkingLevel:
type: string
enum:
- THINKING_LEVEL_UNSPECIFIED
- MINIMAL
- LOW
- MEDIUM
- HIGH
imageConfig:
type: object
properties:
aspectRatio:
type: string
imageSize:
type: string
enum:
- '512'
- 1K
- 2K
- 4K
mediaResolution:
type: string
enum:
- MEDIA_RESOLUTION_UNSPECIFIED
- MEDIA_RESOLUTION_LOW
- MEDIA_RESOLUTION_MEDIUM
- MEDIA_RESOLUTION_HIGH
responseFormat:
type: object
additionalProperties: true
GeminiCandidate:
type: object
properties:
content:
$ref: '#/components/schemas/GeminiContent'
finishReason:
type: string
enum:
- FINISH_REASON_UNSPECIFIED
- STOP
- MAX_TOKENS
- SAFETY
- RECITATION
- LANGUAGE
- OTHER
- BLOCKLIST
- PROHIBITED_CONTENT
- SPII
- MALFORMED_FUNCTION_CALL
- IMAGE_SAFETY
- UNEXPECTED_TOOL_CALL
finishMessage:
type: string
safetyRatings:
type: array
items:
type: object
additionalProperties: true
citationMetadata:
type: object
additionalProperties: true
groundingMetadata:
type: object
additionalProperties: true
avgLogprobs:
type: number
index:
type: integer
GeminiUsageMetadata:
type: object
properties:
promptTokenCount:
type: integer
cachedContentTokenCount:
type: integer
candidatesTokenCount:
type: integer
toolUsePromptTokenCount:
type: integer
thoughtsTokenCount:
type: integer
totalTokenCount:
type: integer
serviceTier:
type: string
GeminiPart:
type: object
description: >-
One content part. Set the field that matches the text, media, function,
or code payload.
properties:
text:
type: string
inlineData:
type: object
properties:
mimeType:
type: string
example: image/jpeg
data:
type: string
description: Base64-encoded data.
required:
- mimeType
- data
fileData:
type: object
properties:
mimeType:
type: string
fileUri:
type: string
required:
- fileUri
functionCall:
type: object
properties:
name:
type: string
args:
type: object
additionalProperties: true
functionResponse:
type: object
properties:
name:
type: string
response:
type: object
additionalProperties: true
executableCode:
type: object
additionalProperties: true
codeExecutionResult:
type: object
additionalProperties: true
thought:
type: boolean
thoughtSignature:
type: string
additionalProperties: true
responses:
400Response:
description: Parameter error
content:
application/json:
schema:
type: object
properties:
status:
type: string
example: FAILED
message:
type: string
example: '"prompt" cannot be empty.'
data:
type: object
required:
- status
- message
401Response:
description: Authorization failed
content:
application/json:
schema:
type: object
properties:
status:
type: string
example: FAILED
message:
type: string
example: Wrong TT-API-KEY or email is not activated.
required:
- status
- message
securitySchemes:
CustomApiKey:
type: apiKey
in: header
name: TT-API-KEY
description: >-
You can obtain your API key from the TTAPI Dashboard.
````