Google: Gemini 4 Argon (batch)

Gemini 4 Argon (batch) is the separately listed batch variant of Google’s long-context reasoning model. It accepts text, images, audio, video and documents and produces text, with tool-calling and structured-output features. Keep its identifier and output allowances distinct from standard Argon when organising batch work.

Ailoot Ultra · Batch POST /v1/batches google/gemini-4-argon:batch

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 4 Argon (batch) is the published batch-labelled variant of Google’s multimodal reasoning model. It retains the Argon model family’s focus on software engineering, mathematical and scientific analysis, and multi-step reasoning over large evidence sets. The record accepts text, images, audio, video and files such as PDFs and returns text.

Organise a collection of independent tasks

A useful batch workload contains many clearly defined items with comparable result requirements. A document collection can use one extraction or comparison rubric across all items. A code-review workload can define the same review questions for a series of changes. A research collection can ask for the same evidence fields from each source package.

Give every work item an identity that the surrounding application retains with its input and result. Keep the instructions stable where the work is comparable, while placing item-specific evidence and questions in the individual task. This makes completed outputs easier to compare without confusing one document or repository change with another.

Long context with a precise output contract

The published context window is 1,048,576 tokens. Keep related source material together and identify document boundaries, filenames or sections that matter to the task. Ask for an output that serves the collection’s purpose: a reviewed change, an evidence table, a structured set of findings or a concise report.

The batch variant publishes mandatory reasoning with low, medium and high effort levels. Match the effort to the questions that must be resolved and keep the answer format explicit. When the response is consumed by another process, the published structured-output capability can support fields that remain comparable across the collection. Tool-calling is also listed as a model feature; the application defines and executes the tools supplied to the task.

Keep variant identity attached to the work

The standard and batch entries have distinct published identifiers within the Argon family. Preserve the exact batch suffix when selecting this variant and retain that choice with the completed artifact. Use the chosen variant’s own capacity and output requirements when organising the collection.

For a large answer, plan the expected content and the completion allowance of the selected batch profile before choosing a work-item size. The batch source page discusses long output separately from the standard entry. Keep the batch variant and its selected completion allowance attached to the collection so every item follows the same output plan.

Compare outputs consistently

Use a representative sample of the collection to assess whether the chosen instructions produce the required evidence and level of detail. Keep document references, extracted findings and any open questions together in each result. If an item needs a revision, retain its original evidence and selection so the corrected result remains comparable with the rest of the collection.

Capabilities

Separate published batch-labelled Argon identifier.
Text, image, audio, video and document inputs with text output.
Published 1,048,576-token context window.
Mandatory reasoning and published tool-calling support.
Schema-guided structured outputs for comparable results.

Use cases

Document collection review — A consistent review rubric and one identified source package per item. Result: Comparable findings with document references retained.
Change-review collection — A series of code changes with shared behaviour and test criteria. Result: An identified review result for each change.
Structured research processing — Independent evidence sets with the same requested result fields. Result: A collection of structured findings ready for comparison.
Long-form synthesis — A large, related input package and a defined report outline. Result: A substantial text artifact under the chosen batch profile’s completion allowance.

Limits

Context — Published batch context window: 1,048,576 tokens.
Variant — Keep google/gemini-4-argon:batch distinct from the standard identifier.
Output planning — Choose work-item sizes using the selected batch profile’s completion allowance; keep the intended result format explicit.
Reasoning — Reasoning is mandatory; low, medium and high effort levels are published.

Ailoot Ultra · Batch POST /v1/batches google/gemini-4-argon:batch

google/gemini-4-argon:batch

Google /google/gemini-4-argon:batch

Overview

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-4-argon: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-4-argon:batch, google/gemini-4-argon	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 $0.002 / 1K tokens Output · Output tokens $0.01 / 1K tokens Input · Cache read $0.0001 / 1K tokens Input · Cache write $0.000375 / 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 $0.002 / 1K tokens Output · Output tokens $0.01 / 1K tokens Input · Cache read $0.0001 / 1K tokens Input · Cache write $0.000375 / 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 →

Example requests

Ailoot Ultra · Batch

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

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-4-argon: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

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-4-argon:batch', 'google/gemini-4-argon']: raise ValueError("body.model must be an exact documented caller or wire ID")
    return {"endpoint":"/v1/chat/completions", "model":"google/gemini-4-argon: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"))

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

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-4-argon:batch

Method path aliases

Use the method paths shown above.

Related caller IDs

google/gemini-4-argon:batch

FAQ · Google: Gemini 4 Argon (batch)

What inputs and results are available?: POST /v1/batches · google/gemini-4-argon:batch: text → text
Which fields does the request use?: POST /v1/batches · google/gemini-4-argon:batch: endpoint, model, requests, completion_window, provider
What limits apply?: POST /v1/batches · google/gemini-4-argon:batch: requests.min_items: 1

Google: Gemini 4 Argon (batch)