GenAI Integration
Generate image (Gemini format)
For Imagen models, use the :predict suffix (e.g., imagen-3.0-generate-001:predict).
For Gemini models, use :generateContent with generationConfig.responseModalities: ["IMAGE"] in the request body.
AuthorizationBearer <token>
Bearer token authentication. Use your provider API key or Bifrost authentication token.
Virtual keys (prefixed with sk-bf-) can also be passed here.
In: header
Path Parameters
modelstring
Model name with action suffix. For Imagen models, use :predict (e.g., imagen-3.0-generate-001:predict).
For Gemini models with image generation, use :generateContent (e.g., gemini-1.5-pro:generateContent).
model?string
Model field for explicit model specification
contents?array<GeminiContent>
Content for the model to process
systemInstruction?GeminiContent
System instruction for the model
generationConfig?object
safetySettings?array<object>
tools?array<object>
toolConfig?object
cachedContent?string
Cached content resource name
labels?object
Labels for the request
Empty Object
requests?array<GeminiEmbeddingRequest>
Batch embedding requests
fallbacks?array<string>
Response Body
curl -X POST "http://localhost:8080/genai/v1beta/models/string:predict" \ -H "Content-Type: application/json" \ -d '{}'{
"candidates": [
{
"content": {
"role": "user",
"parts": [
{
"text": "string",
"thought": true,
"thoughtSignature": "string",
"inlineData": {
"mimeType": "string",
"data": "string",
"displayName": "string"
},
"fileData": {
"mimeType": "string",
"fileUri": "string",
"displayName": "string"
},
"functionCall": {
"id": "string",
"name": "string",
"args": {}
},
"functionResponse": {
"id": "string",
"name": "string",
"response": {},
"willContinue": true,
"scheduling": "string"
},
"executableCode": {
"language": "string",
"code": "string"
},
"codeExecutionResult": {
"outcome": "OUTCOME_UNSPECIFIED",
"output": "string"
},
"videoMetadata": {
"fps": 0,
"startOffset": "string",
"endOffset": "string"
}
}
]
},
"finishReason": "FINISH_REASON_UNSPECIFIED",
"finishMessage": "string",
"tokenCount": 0,
"safetyRatings": [
{
"category": "string",
"probability": "string",
"probabilityScore": 0,
"severity": "string",
"severityScore": 0,
"blocked": true,
"overwrittenThreshold": "string"
}
],
"citationMetadata": {},
"index": 0,
"groundingMetadata": {},
"urlContextMetadata": {
"urlMetadata": [
{
"retrievedUrl": "string",
"urlRetrievalStatus": "string"
}
]
},
"avgLogprobs": 0,
"logprobsResult": {
"chosenCandidates": [
{
"token": "string",
"tokenId": 0,
"logProbability": 0
}
],
"topCandidates": [
{
"candidates": [
{
"token": "string",
"tokenId": 0,
"logProbability": 0
}
]
}
]
}
}
],
"promptFeedback": {
"blockReason": "string",
"blockReasonMessage": "string",
"safetyRatings": [
{
"category": "string",
"probability": "string",
"probabilityScore": 0,
"severity": "string",
"severityScore": 0,
"blocked": true,
"overwrittenThreshold": "string"
}
]
},
"usageMetadata": {
"promptTokenCount": 0,
"candidatesTokenCount": 0,
"totalTokenCount": 0,
"cachedContentTokenCount": 0,
"thoughtsTokenCount": 0,
"toolUsePromptTokenCount": 0,
"trafficType": "string",
"cacheTokensDetails": [
{
"modality": "string",
"tokenCount": 0
}
],
"candidatesTokensDetails": [
{
"modality": "string",
"tokenCount": 0
}
],
"promptTokensDetails": [
{
"modality": "string",
"tokenCount": 0
}
],
"toolUsePromptTokensDetails": [
{
"modality": "string",
"tokenCount": 0
}
]
},
"modelVersion": "string",
"responseId": "string",
"createTime": "2019-08-24T14:15:22Z"
}{
"error": {
"code": 0,
"message": "string",
"status": "string",
"details": [
{
"@type": "string",
"fieldViolations": [
{
"description": "string"
}
]
}
]
}
}{
"error": {
"code": 0,
"message": "string",
"status": "string",
"details": [
{
"@type": "string",
"fieldViolations": [
{
"description": "string"
}
]
}
]
}
}