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.
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.
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.
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.
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.
google/gemini-4-argonGemini 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.
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.
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.
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.
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.
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.
POST /v1/chat/completionstexttext| 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 |
Text · UTF8 text
messages[].content
| 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.
Tariff references do not add request options. Supported parameters are listed for the selected method.
| 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 $0.0004 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model":"google/gemini-4-argon","messages":[{"role":"user","content":"hello"}],"stream":false}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model="google/gemini-4-argon", messages=[{"role":"user","content":"hello"}], stream=False)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n 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\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\njson or SSE
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.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| 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 |
| 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. |
Ailoot Ultra google/gemini-4-argon
/chat/completions
google/gemini-4-argonGemini 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.
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.
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.
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.
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.
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.
POST /v1/messagestextjson, 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 |
Text · UTF-8 text
messages[].content string
| 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
Tariff references do not add request options. Supported parameters are listed for the selected method.
| 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 $0.0004 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "google/gemini-4-argon",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'google/gemini-4-argon', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'google/gemini-4-argon', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON or SSE
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.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| 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. |
Ailoot Ultra google/gemini-4-argon
/chat/completions