Gemini 3 Flash Serverless API

Frontier-class reasoning and multimodal AI at scale.

PlaygroundAPI
Pricing
~14.55s

API Format: Google Gemini

This model uses Google Gemini request/response format.

POST /v2/gemini-3-flash · submit + poll
 1# pip install "segmind>=1.1.0"
 2# export SEGMIND_API_KEY="YOUR_API_KEY"
 3import segmind
 4
 5payload = {
 6    "messages": {
 7        "system_instruction": {
 8            "parts": {
 9                "text": "You are a helpful assistant."
10            }
11        },
12        "contents": [
13            {
14                "role": "user",
15                "parts": [
16                    {
17                        "text": "What's in this image?"
18                    },
19                    {
20                        "inlineData": {
21                            "mimeType": "image/jpeg",
22                            "data": "iVBORw0KGgoAAAANSUhEUgA..."
23                        }
24                    }
25                ]
26            }
27        ]
28    },
29    "effort": "medium",
30    "response_format": {
31        "type": "json_schema",
32        "json_schema": {
33            "name": "answer",
34            "strict": True,
35            "schema": {
36                "type": "object",
37                "properties": {"answer": {"type": "string"}},
38                "required": ["answer"],
39                "additionalProperties": False
40            }
41        }
42    }
43}
44
45# Async chat (v2): submit to the queue, block until COMPLETED.
46reply = segmind.chat("gemini-3-flash", **payload)
47print(reply.text)
48
49# --- Or get a handle (track request_id, control the poll cadence) ---
50job = segmind.submit_chat("gemini-3-flash", **payload)
51print(job.request_id)                         # available immediately
52reply = job.wait(timeout=600)
53print(reply.text)

API Endpoint

POST https://api.segmind.com/v1/gemini-3-flash

Parameters

messagesrequired
object[]

Object containing contents array with role and parts. Parts can contain text or inlineData for images.

Array items:
rolerequired
string

Role of the message sender

Allowed values :
"user""model"
contentrequired
array

Array of parts (text or inlineData)

messages.system_instructionoptional
object

System instruction with parts containing text to guide model behavior.

partsoptional
object
textrequired
string

System instruction text

effortoptional
string

How hard the model reasons before answering; 'minimal' answers with almost no thinking. Thinking is billed as output tokens, so higher levels cost more and take longer.

Allowed values :
"minimal""low""medium""high"
response_formatoptional
object

Structured output. {"type": "json_object"} returns any valid JSON; {"type": "json_schema", "json_schema": {"name", "strict", "schema"}} enforces the given JSON Schema. Omit for plain text.

Response Format

{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "I can see a beautiful sunset over the ocean with vibrant orange and pink hues in the sky."
          }
        ],
        "role": "model"
      },
      "finishReason": "STOP",
      "index": 0,
      "safetyRatings": []
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 56,
    "candidatesTokenCount": 31,
    "totalTokenCount": 87
  }
}

With response_format

The envelope is unchanged: your JSON arrives as a string in the same field, which you parse yourself. Structured outputs guide

{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "{\"answer\":\"Paris\"}"
          }
        ],
        "role": "model"
      },
      "finishReason": "STOP",
      "index": 0,
      "safetyRatings": []
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 56,
    "candidatesTokenCount": 31,
    "totalTokenCount": 87
  }
}

Image Input Format

Important: Google Gemini Format

Images should be base64 encoded in the inlineData.data field with mimeType specified

This model supports vision capabilities. You can include images in your requests.

Asynchronous requests (v2)

Use Async for video, long-running (>~60s), or high-concurrency workloads; Sync is simplest for fast image & LLM calls. Async submits a request and you poll it to completion.

  1. 1
    POST /v2/gemini-3-flash

    Submit — returns request_id, status_url, response_url

  2. 2
    GET /v2/requests/{id}/status

    Poll — until COMPLETED or FAILED

  3. 3
    GET /v2/requests/{id}

    Result — final response body

Status states

QUEUED— Accepted, waiting for a worker
PROCESSING— Running on a worker
COMPLETED— Done — result body is ready
FAILED— Errored (incl. content/RAI blocks)
  • A FAILED request is served as HTTP 422 — the body still carries the error detail.
  • An unknown or expired request_id returns HTTP 404.
  • Results are retained for 1 hour, then expire.
  • Content / RAI blocks surface as FAILED, not a separate state.
  • Track completion by polling the status endpoint.

Common Error Codes

The API returns standard HTTP status codes. Detailed error messages are provided in the response body.

400

Bad Request

Invalid message format or parameters — including a response_format this model does not accept, or a json_schema sent without a schema object

401

Unauthorized

Missing or invalid API key

403

Forbidden

Insufficient permissions

404

Not Found

Model or endpoint not found

406

Insufficient Credits

Not enough credits to process request

429

Rate Limited

Too many requests

500

Server Error

Internal server error

502

Bad Gateway

Service temporarily unavailable

504

Timeout

Request timed out