Source: https://ailoot.ai/models/en/google-gemini-3-flash-preview-u003a-batch/
Canonical: https://ailoot.ai/models/en/google-gemini-3-flash-preview-u003a-batch/
Language: en

# Google: Gemini 3 Flash Preview (batch)

[Markdown](https://ailoot.ai/models/en/google-gemini-3-flash-preview-u003a-batch/index.md) · [JSON](https://ailoot.ai/models/en/google-gemini-3-flash-preview-u003a-batch/facts.json)

## [Google: Gemini 3 Flash Preview (batch)](https://ailoot.ai/models/en/google-gemini-3-flash-preview-u003a-batch/)

Gemini 3 Flash Preview combines multimodal understanding and reasoning with text output. It supports code, document and visual analysis, structured results and tool-oriented workflows, with four documented thinking levels for choosing the depth of analysis.

- [**Ailoot Ultra · Batch** `POST /v1/batches` `google/gemini-3-flash-preview:batch`](https://ailoot.ai/models/en/google-gemini-3-flash-preview-u003a-batch/#method-0)

About the model

This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.

Gemini 3 Flash Preview is a Google reasoning model for multimodal understanding, coding and agentic tasks. It accepts text, images, video, audio and PDF and returns text. A request can therefore join written instructions, source files, visual observations and conversation history around one problem. The result may be an explanation, a code proposal, extracted data or a plan grounded in those materials, rather than a generated image or spoken response.

The exact model card gives an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. Plan the source and result separately: a long repository excerpt, document collection or recording can fit only when its processed representation and instructions fit the input budget, and the answer still needs its own allotted length. Label related sources and identify which material is authoritative. For a long prompt, the developer guide recommends placing the specific question after the data and tying it explicitly to the preceding information.

Thinking is dynamic, with high as the documented default for this model. The supported levels are minimal, low, medium and high. They are relative reasoning allowances rather than guaranteed token counts. Minimal can still involve some reasoning on a difficult coding problem. Choose a level according to the task: a short transformation and a multi-condition debugging problem need different treatment. Use direct, clear instructions instead of forcing elaborate reasoning rituals into the prompt; request the final artifact and the checks that make it usable.

The producer card lists structured outputs, function calling, code execution, computer use, file search, search grounding, Google Maps grounding, URL context and caching. Built-in tools can be combined with custom function calling in the documented Gemini 3 flow. An application defines the functions, checks their arguments, executes accepted actions and sends back their results. For a code assistant, a read-file or controlled test-runner tool can provide concrete evidence for the next step. A proposed action and an observed tool result should remain distinct in the final report.

For programming, supply the relevant files, language, expected behavior and an input that demonstrates the issue. Set the scope of the change and name the interface or behavior that must remain. Ask for a revised implementation and the cases that should be checked. For an analytical document task, define the question, required fields and source references. If structured output is used, provide a schema with clear field meanings and missing-value rules. Validate both its syntax and whether each value follows from the original material.

For multimodal analysis, identify what matters in each source. A screenshot can support an interface explanation, a PDF can supply a table or chart, and a recording can provide spoken or visible events. The developer guide discusses media-resolution controls because detail changes the processed representation and token use. The producer’s code-execution workflow can crop or zoom supplied images, run calculations from visual data and add annotations before the model prepares its answer. Readable small text may require a different setting from a broad scene description. Keep the relevant page, image or clip available so observations can be checked rather than treating a fluent summary as evidence that every detail was read correctly.

Conversation and tool state need to be retained in the chosen interface. Gemini 3 uses thought signatures to carry reasoning context between calls; the developer guide distinguishes managed stateful history from manually managed stateless history. Preserve the required context when continuing a tool task or revising a result. Google also recommends keeping its default temperature of 1.0 rather than importing a low-temperature recipe that can cause loops or degraded behavior on complex tasks. These are producer integration practices, not new claims about any particular application’s transport.

The text model does not advertise image or audio generation or the Live API. The guide also distinguishes visual understanding from pixel-level image segmentation, which is not a supported Gemini 3 Flash capability. Use an appropriate final result for the actual task: source-linked observations, a structured record, a code change or a decision with its assumptions stated. Check arithmetic, verify code in the intended environment and review returned tool information. When recent facts matter, use the configured grounding sources or supplied current data instead of assuming that model knowledge is a live database.

**Ailoot Ultra · Batch** `POST /v1/batches` `google/gemini-3-flash-preview:batch`

[`google/gemini-3-flash-preview:batch`](https://ailoot.ai/models/en/#m=google%2Fgemini-3-flash-preview%3Abatch&route=Ultra&caller=google%2Fgemini-3-flash-preview%3Abatch&fmt=batches)

Google /`google/gemini-3-flash-preview:batch`

### Overview

Gemini 3 Flash Preview combines multimodal understanding and reasoning with text output. It supports code, document and visual analysis, structured results and tool-oriented workflows, with four documented thinking levels for choosing the depth of analysis.

Accepted inputs

Text

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot Ultra · Batch** `POST /v1/batches`

Input types

`text`

Output types

`text`

Output format

inline results\[\].response.body JSON

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`endpoint` | Type`string` | RequirementRequired | Values & limits /v1/chat/completions | Default— |
| Field`model` | Type`string` | RequirementRequired | Values & limits google/gemini-3-flash-preview:batch | Default— |
| Field`requests` | Type`batch_item[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`requests[].custom_id` | Type`string` | RequirementRequired | Values & limits | Default— |
| Field`requests[].body.messages` | Type`message[]` | RequirementRequired | Values & limits | Default— |
| Field`completion_window` | Type`string` | RequirementOptional | Values & limits 24h | Default— |
| Field`provider` | Type`object\|null` | RequirementOptional | Values & limits | Default— |
| Field`requests[].body.model` | Type`string` | RequirementOptional | Values & limits google/gemini-3-flash-preview:batch, google/gemini-3-flash-preview | Default— |
| Field`provider.only` | Type`string[]` | RequirementOptional | Values & limits google-vertex/global | Default— |
| Field`provider.allow_fallbacks` | Type`boolean\|null` | RequirementOptional | Values & limits false, null | Default— |

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`content_type` | Contractapplication/json |
| Parameter`required` | Contractendpoint, model, requests |
| Parameter`material_types` | Contracttext |
| Parameter`representation` | Contractinline requests\[\]; each item has custom\_id and body |
| Parameter`request_endpoint_profile` | Contract/v1/chat/completions |
| Parameter`file_material` | ContractCaller may read actual UTF-8 JSONL locally into requests\[\]. No upload purpose, input\_file\_id or file reference is used. Missing/empty customer material stops preparation before POST. |
| Parameter`serialization_order` | Contractendpoint, model, provider (if supplied), completion\_window (if supplied), requests last |
| Parameter`optional_controls` | Contractprovider.only, provider.allow\_fallbacks, completion\_window |
| Parameter`schema_scope` | ContractText Chat Completions bodies in the documented inline Batch envelope. |

Lifecycle: `asynchronous`

`GET /v1/batches/{operation_id}` · actual original create response.id; same user/key/group

### Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode

Not specified When fast mode is selected

Flex mode

Not specified When flex mode is selected

Maximum reasoning effort

Not specified When maximum reasoning effort uses the default adjustment

Explicit cache pricing

Not enabled When explicit cache is requested

#### Ailoot rates

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0005** / 1K tokens Output · Output tokens **$0.003** / 1K tokens Input · Cache read **—** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0005** / 1K tokens Output · Output tokens **$0.003** / 1K tokens Input · Cache read **—** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

### Example requests

#### Ailoot Ultra · Batch

curl · retained fixturePython HTTP · actual customer JSONLPython · save every completed result

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_REQUEST'
import json
from pathlib import Path
body=json.loads('{"endpoint":"/v1/chat/completions","model":"google/gemini-3-flash-preview:batch","requests":[{"custom_id":"req-0001","body":{"messages":[{"role":"user","content":"Hello!"}],"max_tokens":16}}]}')
Path("batch-request.json").write_text(json.dumps(body,ensure_ascii=False),encoding="utf-8")
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/batches \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @batch-request.json -D batch-response-headers.txt -o batch-create-response.json
```

```python
import json, os
from pathlib import Path
from urllib.request import Request, urlopen

def prepare_requests(customer_path):
    path = Path(customer_path)
    if not path.is_file(): raise ValueError("Customer JSONL file is missing")
    items = [json.loads(line) for line in path.read_text(encoding="utf-8").splitlines() if line.strip()]
    if not items: raise ValueError("Customer JSONL contains no requests")
    ids = set()
    for item in items:
        if set(item) != {"custom_id", "body"}: raise ValueError("Each item needs custom_id and body")
        cid = item["custom_id"]
        if not isinstance(cid, str) or not cid.strip() or cid in ids: raise ValueError("custom_id must be nonempty and unique")
        ids.add(cid)
        if not isinstance(item["body"], dict) or not item["body"].get("messages"): raise ValueError("Supply actual text messages")
        supplied_model = item["body"].get("model")
        if supplied_model is not None and supplied_model not in ['google/gemini-3-flash-preview:batch', 'google/gemini-3-flash-preview']: raise ValueError("body.model must be an exact documented caller or wire ID")
    return {"endpoint":"/v1/chat/completions", "model":"google/gemini-3-flash-preview:batch", "requests":items}

if __name__ == "__main__":
    material = os.environ.get("AILOOT_BATCH_REQUESTS_JSONL", "")
    if not material: raise SystemExit("Set AILOOT_BATCH_REQUESTS_JSONL to your actual customer file")
    body = prepare_requests(material)
    key = os.environ.get("AILOOT_API_KEY", "")
    if not key: raise SystemExit("Set AILOOT_API_KEY")
    request = Request("https://api.ailoot.ai/v1/batches", data=json.dumps(body, ensure_ascii=False).encode("utf-8"), headers={"Authorization":"Bearer " + key, "Content-Type":"application/json"}, method="POST")
    with urlopen(request) as response:
        raw = response.read()
        Path("batch-create-response.json").write_bytes(raw)
        print(raw.decode("utf-8"))
```

```python
import json
from pathlib import Path
raw = Path("batch-status-response.json").read_bytes()
response = json.loads(raw)
if response.get("status") != "completed":
    raise SystemExit("Keep the original operation; read its status without resubmitting")
results = response.get("results")
if not isinstance(results, list) or not results:
    raise SystemExit("Preserve the original response; completed results are missing")
Path("batch-results.jsonl").write_text("".join(json.dumps(item, ensure_ascii=False) + "\n" for item in results), encoding="utf-8")
# Preserve batch-status-response.json with aggregate usage and every result/error.
```

### Receive and save results

#### Ailoot Ultra · Batch

inline results\[\].response.body JSON

- `GET /v1/batches/{operation_id}`

##### Check job status

curl · original operation status

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
BATCH_OPERATION_ID="$(python3 - <<'PY_ID'
import json
from pathlib import Path
from urllib.parse import quote
response = json.loads(Path("batch-create-response.json").read_text(encoding="utf-8"))
operation = response.get("id")
if not isinstance(operation, str) or not operation: raise SystemExit("No actual original operation ID; preserve the response and do not resubmit")
print(quote(operation, safe=""))
PY_ID
)"
curl --fail-with-body --silent --show-error "https://api.ailoot.ai/v1/batches/$BATCH_OPERATION_ID" \
  -H "Authorization: Bearer $AILOOT_API_KEY" -o batch-status-response.json
```

##### Keep all completed results

Keep every complete returned response, file and content part.

Preserve the full original status JSON, every result/custom\_id and complete response or error body. Save completed results\[\] as JSONL without filtering.

##### If the original response needs checking

Preserve the original operation ID. 503 result\_pending\_check has X-Should-Retry:false; never resubmit an unknown original batch.

Response fields

| Field | Type |
| --- | --- |
| Field`results[].custom_id` | Typestring |
| Field`results[].response.body.choices[].message.content` | Typestring\|null |
| Field`results[].error` | Typeobject\|null |
| Field`usage` | Typeobject\|null |
| Field`id` | Typestring |
| Field`model` | Typestring |
| Field`endpoint` | Typestring |
| Field`status` | Typestring |
| Field`request_counts` | Typeobject |
| Field`results[].id` | Typestring |
| Field`results[].response.status_code` | Typeinteger |
| Field`results[].response.request_id` | Typestring |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid documented inline envelope, duplicate keys, item identity, or configured model capabilities conflict. | Next stepCorrect the indicated fields before any new submission. |
| Response401 · `authentication_error` | ConditionInvalid API key. | Next stepUse the authorized Ailoot key. |
| Response403 · `permission_error` | ConditionBatch group unavailable. | Next stepCheck key/group entitlement. |
| Response422 · `invalid_request_error` | ConditionBatch uses balance billing; subscription creation is rejected. | Next stepUse the authorized balance-billed group. |
| Response422 · `price_unavailable` | ConditionBatch input cannot be quoted. | Next stepPreserve response; use documented family input. |
| Response402 · `billing_error` | ConditionBatch reserve unavailable. | Next stepResolve admission before a new request. |
| Response503 · `price_unavailable` | ConditionBatch method price/native rates unavailable. | Next stepPreserve response; do not substitute prices. |
| Response503 · `api_error` | ConditionExact supplier route unavailable. | Next stepPreserve response for route repair. |
| Response503 · `result_pending_check` | ConditionOriginal result requires checking; X-Should-Retry:false. | Next stepKeep original operation\_id/id and read its status; never repeat original POST. |
| Response404 · `not_found` | ConditionBatch status operation absent or owned by another identity. | Next stepUse exact original id and same user/key/group. |

### Aliases

#### Model aliases

**Ailoot Ultra** [`google/gemini-3-flash-preview:batch`](https://ailoot.ai/models/en/#m=google%2Fgemini-3-flash-preview%3Abatch&route=Ultra&caller=google%2Fgemini-3-flash-preview%3Abatch&fmt=batches)

#### Method path aliases

Use the method paths shown above.

#### Related caller IDs

[`google/gemini-3-flash-preview:batch`](https://ailoot.ai/models/en/#m=google%2Fgemini-3-flash-preview%3Abatch&route=Ultra&caller=google%2Fgemini-3-flash-preview%3Abatch&fmt=batches)

FAQ · Google: Gemini 3 Flash Preview (batch)

What inputs and results are available?

`POST /v1/batches` · `google/gemini-3-flash-preview:batch`: `text` → `text`

Which fields does the request use?

`POST /v1/batches` · `google/gemini-3-flash-preview:batch`: `endpoint`, `model`, `requests`, `completion_window`, `provider`

What limits apply?

`POST /v1/batches` · `google/gemini-3-flash-preview:batch`: `requests.min_items`: `1`

Connect Ailoot to Claude Code, OpenCode, Hermes or your own app.

## The company and its project portfolio

The company and its project portfolio: millions of customers; monthly sales in the billions.

## Buy tokens at a discount.

Subscription discounts for regular use. Promo codes offer up to 50% off token purchases.

Subscription

Choose a discounted plan for your regular requests.

Promo code: up to 50% off

Enter your code at checkout. The price updates to reflect the current promotion.

Spending in your history

The model, tokens and amount are recorded for each request.

[Choose a subscription](https://ailoot.ai/docs/en/billing/subscriptions/) · [View model prices](https://ailoot.ai/models/en/)

## Connect the API to a product you sell.

Use Ailoot in SaaS, apps and bots under its official service offer and licence agreement. Request a reseller licence for resale.

Commercial application

Add text, image, video and audio generation to paid features in your service.

Reseller licence

Send a description of your project and how you provide access. Request written terms for use and resale.

Documents on the website

The service offer, licence agreement and data processing policy are available before you connect.

[Request a reseller licence](mailto:support@ailoot.ai) · [Service offer and licence agreement](https://ailoot.ai/legal/offer?lang=en)

## Ailoot · The company and its project portfolio





Ailoot combines established operating experience, a large client base, stable service and ongoing KPI control.





The company and its project portfolio: millions of customers; monthly sales in the billions.





Ailoot brings that operating experience to API access for AI features in customer products, agents, applications and automations.