## Generate content
`POST /v1beta/models/gemini-4-argon:generateContent`
```bash cURL theme={null}
curl --request POST \
--url 'https://www.anyfast.ai/v1beta/models/gemini-4-argon:generateContent?key=YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"contents": [{
"role": "user",
"parts": [{
"text": "Review this retry design, identify race conditions, and propose a safe implementation plan."
}]
}],
"generationConfig": {
"thinkingConfig": {"thinkingLevel": "medium"},
"maxOutputTokens": 2048
}
}'
```
## Authentication and headers
AnyFast API key.
Request media type.
## Request body
Conversation history and the current user request. The final item must be a non-empty `user` turn.
Conversation role: `user` or `model`. Do not end the request with a `model` turn.
Content parts for the turn.
Text prompt or conversation content.
Thinking level: `low`, `medium`, or `high`.
Maximum generated tokens for a synchronous request, from 1 through 32,768.
## Successful response
```json 200 theme={null}
{
"candidates": [{
"content": {
"parts": [{"text": "The design has a race between timeout handling and retry scheduling..."}],
"role": "model"
},
"finishReason": "STOP",
"index": 0,
"safetyRatings": []
}],
"usageMetadata": {
"promptTokenCount": 18,
"candidatesTokenCount": 121,
"thoughtsTokenCount": 86,
"totalTokenCount": 225,
"trafficType": "ON_DEMAND"
},
"modelVersion": "gemini-4-argon",
"responseId": "response-example-001"
}
```
Generated candidates.
Model response turn.
Generated text.
Why generation stopped, such as `STOP`, `MAX_TOKENS`, or `SAFETY`.
Safety assessments returned when the candidate is evaluated.
Input, output, reasoning, tool, cache, and total token counts.
Model version that produced the response.
Response identifier.
## Generate content
`POST /v1beta/models/gemini-4-argon:generateContent`
```bash cURL theme={null}
curl --request POST \
--url 'https://www.anyfast.ai/v1beta/models/gemini-4-argon:generateContent?key=YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"contents": [{
"role": "user",
"parts": [
{"text": "Summarize this architecture and identify the likely bottleneck."},
{
"fileData": {
"mimeType": "image/png",
"fileUri": "https://example.com/architecture.png"
}
}
]
}]
}'
```
## Authentication and headers
AnyFast API key.
Request media type.
## Request body
Conversation turns containing text and media.
Conversation role: `user` or `model`.
One or more text or media parts.
Instruction or question about the media.
Inline image, audio, video, or document data.
Media MIME type, such as `image/jpeg`, `audio/mpeg`, `video/mp4`, or `application/pdf`.
Base64-encoded media bytes.
Media or document supplied by URI.
Media MIME type.
Accessible media or document URI.
## Successful response
```json 200 theme={null}
{
"candidates": [{
"content": {
"parts": [{"text": "The diagram shows a queue-backed worker tier. The database connection pool is the likely bottleneck..."}],
"role": "model"
},
"finishReason": "STOP",
"index": 0
}],
"usageMetadata": {
"promptTokenCount": 846,
"candidatesTokenCount": 94,
"totalTokenCount": 940,
"promptTokensDetails": [
{"modality": "TEXT", "tokenCount": 18},
{"modality": "IMAGE", "tokenCount": 828}
]
},
"modelVersion": "gemini-4-argon",
"responseId": "response-example-002"
}
```
Text analysis of the supplied media.
Reason generation stopped.
Input token counts grouped by modality.
Output token counts grouped by modality when returned.
Model version that produced the response.
Response identifier.
## Generate content
`POST /v1beta/models/gemini-4-argon:generateContent`
```bash cURL theme={null}
curl --request POST \
--url 'https://www.anyfast.ai/v1beta/models/gemini-4-argon:generateContent?key=YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"contents": [{
"role": "user",
"parts": [{"text": "Extract the service, severity, and action: checkout-api is timing out and requires immediate rollback."}]
}],
"generationConfig": {
"responseMimeType": "application/json",
"responseSchema": {
"type": "object",
"properties": {
"service": {"type": "string"},
"severity": {"type": "string"},
"action": {"type": "string"}
},
"required": ["service", "severity", "action"]
}
}
}'
```
## Authentication and headers
AnyFast API key.
Request media type.
## Request body
Conversation turns containing the extraction or generation instruction.
Instruction and source text.
Use `application/json` for JSON structured output or `text/x.enum` for a single enum value.
Schema that constrains the generated JSON. Define explicit properties and required fields.
## Successful response
```json 200 theme={null}
{
"candidates": [{
"content": {
"parts": [{
"text": "{\"service\":\"checkout-api\",\"severity\":\"critical\",\"action\":\"rollback\"}"
}],
"role": "model"
},
"finishReason": "STOP",
"index": 0
}],
"usageMetadata": {
"promptTokenCount": 27,
"candidatesTokenCount": 24,
"totalTokenCount": 51
},
"modelVersion": "gemini-4-argon",
"responseId": "response-example-003"
}
```
JSON serialized as text and conforming to the requested schema.
Reason generation stopped.
Token accounting for the request.
Model version that produced the response.
Response identifier.
## Generate function call
`POST /v1beta/models/gemini-4-argon:generateContent`
```bash cURL theme={null}
curl --request POST \
--url 'https://www.anyfast.ai/v1beta/models/gemini-4-argon:generateContent?key=YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"contents": [{
"role": "user",
"parts": [{"text": "Check the deployment status for checkout-api."}]
}],
"tools": [{
"functionDeclarations": [{
"name": "get_deployment_status",
"description": "Return the current deployment status for a service.",
"parameters": {
"type": "object",
"properties": {"service": {"type": "string"}},
"required": ["service"]
}
}]
}],
"toolConfig": {
"functionCallingConfig": {
"mode": "ANY",
"allowedFunctionNames": ["get_deployment_status"]
}
}
}'
```
## Authentication and headers
AnyFast API key.
Request media type.
## Request body
Conversation turns containing the user request and, for later steps, previous model calls and function results.
Functions available to the model.
Function name.
When and how the model should use the function.
JSON Schema for function arguments.
`AUTO`, `ANY`, `NONE`, or `VALIDATED`.
Subset of declared functions the model may call.
Function name when returning a tool result.
Call ID returned by the model.
Structured function result.
Opaque signature returned by the model. Preserve it exactly in later requests.
## Function-call response
```json 200 theme={null}
{
"candidates": [{
"content": {
"parts": [{
"functionCall": {
"id": "call-example-001",
"name": "get_deployment_status",
"args": {"service": "checkout-api"}
},
"thoughtSignature": "opaque-signature-placeholder"
}],
"role": "model"
},
"finishReason": "STOP",
"index": 0
}],
"usageMetadata": {
"promptTokenCount": 86,
"candidatesTokenCount": 18,
"toolUsePromptTokenCount": 64,
"totalTokenCount": 168
},
"modelVersion": "gemini-4-argon",
"responseId": "response-example-004"
}
```
Function requested by the model.
Call ID to associate with a returned function result.
Function name.
Model-generated function arguments.
Opaque signature that must be preserved when the model turn is replayed.
Tokens used for tool context when this metric is reported.
Response identifier.
## Generate grounded content
`POST /v1beta/models/gemini-4-argon:generateContent`
```bash cURL theme={null}
curl --request POST \
--url 'https://www.anyfast.ai/v1beta/models/gemini-4-argon:generateContent?key=YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"contents": [{
"role": "user",
"parts": [{"text": "Find the latest stable Gemini API model and cite the source."}]
}],
"tools": [{"googleSearch": {}}]
}'
```
## Authentication and headers
AnyFast API key.
Request media type.
## Request body
Conversation turns containing the tool-assisted request.
Ground the response with current Google Search results.
Ground location-related answers with Google Maps data.
Read and analyze URLs supplied in the prompt.
Allow the model to execute code.
Allow the model to propose computer-use actions. This tool is in Preview.
Computer-use environment, such as `ENVIRONMENT_BROWSER`.
## Grounded response
```json 200 theme={null}
{
"candidates": [{
"content": {
"parts": [{"text": "Gemini 4 Argon is the latest stable Flash model..."}],
"role": "model"
},
"finishReason": "STOP",
"groundingMetadata": {
"webSearchQueries": ["latest stable Gemini API model"],
"searchEntryPoint": {
"renderedContent": "
...
"
},
"groundingChunks": [{
"web": {
"uri": "https://ai.google.dev/gemini-api/docs/models",
"title": "Gemini models"
}
}],
"groundingSupports": [{
"segment": {"startIndex": 0, "endIndex": 56, "text": "Gemini 4 Argon is the latest stable Flash model"},
"groundingChunkIndices": [0]
}]
}
}],
"usageMetadata": {
"promptTokenCount": 15,
"candidatesTokenCount": 58,
"toolUsePromptTokenCount": 43,
"totalTokenCount": 116
},
"modelVersion": "gemini-4-argon",
"responseId": "response-example-005"
}
```