Google: Gemini 4 Argon
Gemini 4 Argon is Google’s multimodal reasoning model for software engineering, mathematical and scientific work, and multi-step agents. It combines text, images, audio, video and documents within a 1,048,576-token context and returns text, with published tool-calling and structured-output support.
- Ailoot Ultra · OpenAI Chat
POST /v1/chat/completionsgoogle/gemini-4-argon - Ailoot Ultra · Anthropic Messages
POST /v1/messagesgoogle/gemini-4-argon
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 is a Google reasoning model for work that combines a large evidence set with a multi-step objective. Its published input range includes text, images, audio, video and files such as PDFs, while the result is text. This lets a task bring together a specification, a chart, a screenshot and supporting material instead of relying on a written summary of every source.
Give the model an evidence set and a deliverable
Start with a clear question and the artifact you need at the end. A software task can ask for a change plan, affected components and verification criteria. A mathematical task can ask for a derivation with stated assumptions. A document task can ask for a comparison that keeps disagreements between text, tables and figures visible.
The published context window is 1,048,576 tokens. Use that capacity to keep relevant material together, with document names and section boundaries that make references unambiguous. Group supporting material around the question rather than inserting unrelated files simply because space is available. Ask the response to distinguish evidence supplied in the task from assumptions introduced during analysis.
Reasoning, tools and structured results
The model’s published reasoning configuration is mandatory, with low, medium and high effort levels and medium as the listed default. Choose a level around the depth of the problem and define what a successful answer must establish. A short factual comparison needs different verification criteria from a code change that affects several components.
Argon publishes tool-calling and schema-guided structured-output capabilities. These are useful when an application supplies tools for retrieving additional evidence or needs a machine-readable analysis result. Keep the model’s proposed tool activity distinct from the application that executes it, and preserve the returned observations before asking for the next decision. For a structured result, define the intended fields around the business decision: findings, evidence references, unresolved assumptions and the recommended action.
Engineering and document workflows
For a repository task, supply the relevant source, the behaviour to preserve and the checks that should pass. Ask for a focused implementation plan or a review of a concrete change, then evaluate the resulting proposal against those checks. For a technical report, present the underlying observations and request an explanation that connects each conclusion to its supporting material.
For mixed documents, include the tables and images that carry meaning instead of replacing them with an incomplete transcript. The model’s output can consolidate those inputs into a readable report, a set of extracted findings or an action list. Image and audio inputs are evidence for that text result; they do not change this record into an image- or speech-generation model.
Output planning
The standard Argon record and its model-page FAQ list a 65,536-token completion limit. Specify the expected depth and layout of the answer before requesting a long result. Preserve the standard identifier separately from the batch-labelled record, because their published completion allowances differ. Use the selected variant’s own limits when dividing work into responses.
Capabilities
- Multimodal text reasoning over text, images, audio, video and PDF documents.
- Published 1,048,576-token context and 65,536-token standard completion limit.
- Mandatory reasoning with low, medium and high effort levels.
- Tool calling for application-controlled multi-step workflows.
- Schema-guided structured text output.
Use cases
- Repository change analysis — Relevant files, desired behaviour and verification criteria. Result: A focused change plan or review tied to the supplied code.
- Mixed-document synthesis — Documents, tables, charts and a precise comparison question. Result: A text report retaining the evidence behind each conclusion.
- Mathematical investigation — A problem statement, assumptions and the required form of the answer. Result: A derivation or analysis whose steps can be checked.
- Tool-driven agent — An objective, controlled tools and the observations returned by those tools. Result: Successive reasoned decisions towards a defined deliverable.
Limits
- Context — Published context window: 1,048,576 tokens.
- Standard reply — Published standard completion limit: 65,536 tokens.
- Reasoning — Reasoning is mandatory; published efforts are low, medium and high, with medium as the default.
- Output family — The published result is text; multimodal inputs support analysis of supplied evidence.
Ailoot Ultra · OpenAI Chat POST /v1/chat/completions google/gemini-4-argon
google/gemini-4-argonOverview
Gemini 4 Argon is Google’s multimodal reasoning model for software engineering, mathematical and scientific work, and multi-step agents. It combines text, images, audio, video and documents within a 1,048,576-token context and returns text, with published tool-calling and structured-output support.
- Accepted inputs
- Text
- Results
- Text
Available in Ailoot · inputs & methods
Ailoot Ultra · OpenAI Chat POST /v1/chat/completions
- Input types
text- Output types
text- Output format
- json or SSE
| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-4-argon | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Model-specific | Default— |
Fieldmessages[].content | Typestring | RequirementOptional | Values & limits Applies when: Text conversation | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Input material combinations
Text · UTF8 text
messages[].content
Method parameters and lifecycle
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream |
Parametercontrol_scope | ContractText conversation; stream is a boolean and defaults to false. |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Method aliases: /chat/completions
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
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
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.008 / 1K tokens Output · Output tokens $0.04 / 1K tokens Input · Cache read $0.0004 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Example requests
Ailoot Ultra · OpenAI Chat
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model":"google/gemini-4-argon","messages":[{"role":"user","content":"hello"}],"stream":false}')
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
-H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
r=json.loads(Path("result.json").read_text())
for x in r.get("choices",[]):
if x.get("message",{}).get("content"): print(x["message"]["content"])
PY_RESULT
from openai import OpenAI
import os
if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
result=client.chat.completions.create(model="google/gemini-4-argon", messages=[{"role":"user","content":"hello"}], stream=False)
import base64, json
from pathlib import Path
def save_result(data, stem="result"):
# Keep every field, including usage, IDs, reasoning and tool requests.
Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
print(json.dumps(data, ensure_ascii=False, indent=2))
def save_blob(encoded, suffix, label):
raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
file = Path(stem + "-" + label + "." + ext)
file.write_bytes(raw)
print("Saved", file)
for index, block in enumerate(data.get("content") or []):
print("Content", index, json.dumps(block, ensure_ascii=False))
for choice in data.get("choices") or []:
print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
for index, item in enumerate(data.get("output") or []):
print("Output", index, json.dumps(item, ensure_ascii=False))
if item.get("type") == "image_generation_call" and item.get("result"):
save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
for ci, candidate in enumerate(data.get("candidates") or []):
for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
blob = part.get("inlineData") or part.get("inline_data")
if blob and blob.get("data"):
mime = blob.get("mimeType") or blob.get("mime_type")
suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))
save_result(result.to_dict(mode="json"))
Receive and save results
Ailoot Ultra · OpenAI Chat
json or SSE
Keep all completed results
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
If the original response needs checking
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
Response fields
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
Errors and next steps
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Aliases
Model aliases
Ailoot Ultra google/gemini-4-argon
Method path aliases
/chat/completions
Related caller IDs
Ailoot Ultra · Anthropic Messages POST /v1/messages google/gemini-4-argon
google/gemini-4-argonOverview
Gemini 4 Argon is Google’s multimodal reasoning model for software engineering, mathematical and scientific work, and multi-step agents. It combines text, images, audio, video and documents within a 1,048,576-token context and returns text, with published tool-calling and structured-output support.
- Accepted inputs
- Text
- Results
- json · sse
Available in Ailoot · inputs & methods
Ailoot Ultra · Anthropic Messages POST /v1/messages
- Input types
text- Output types
json,sse- Output format
- JSON or SSE
| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/gemini-4-argon | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Input material combinations
Text · UTF-8 text
messages[].content string
Method parameters and lifecycle
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
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
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.008 / 1K tokens Output · Output tokens $0.04 / 1K tokens Input · Cache read $0.0004 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Example requests
Ailoot Ultra · Anthropic Messages
{
"model": "google/gemini-4-argon",
"max_tokens": 128,
"messages": [
{
"role": "user",
"content": "Summarize the incident report."
}
],
"stream": false
}set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json, os
from pathlib import Path
source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
raise SystemExit('Choose a document containing text')
payload = {'model': 'google/gemini-4-argon', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
Path('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
-H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
PY_RESULT
import json, os
from pathlib import Path
source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
raise SystemExit('Choose a document containing text')
payload = {'model': 'google/gemini-4-argon', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
from urllib.request import Request, urlopen
from urllib.error import HTTPError
api_key = os.environ['AILOOT_API_KEY']
if not api_key.strip():
raise SystemExit('Set AILOOT_API_KEY before making a request')
headers = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}
headers['x-api-key'] = api_key
request = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')
try:
with urlopen(request, timeout=120) as response:
raw = response.read()
Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')
except HTTPError as error:
Path('result.json').write_bytes(error.read())
Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')
raise
Path('result.json').write_bytes(raw)
import json
from pathlib import Path
result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
Receive and save results
Ailoot Ultra · Anthropic Messages
JSON or SSE
Keep all completed results
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
If the original response needs checking
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
Response fields
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
Errors and next steps
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Aliases
Model aliases
Ailoot Ultra google/gemini-4-argon
Method path aliases
/chat/completions
Related caller IDs
FAQ · Google: Gemini 4 Argon
- What inputs and results are available?
POST /v1/chat/completions·google/gemini-4-argon:text→textPOST /v1/messages·google/gemini-4-argon:text→json,sse- Which fields does the request use?
POST /v1/chat/completions·google/gemini-4-argon:model,messages,streamPOST /v1/messages·google/gemini-4-argon:model,messages,max_tokens,stream- What limits apply?
POST /v1/chat/completions·google/gemini-4-argon:messages.min_items:1