{
  "schema_version": 1,
  "public_model_id": "google/gemini-4-argon",
  "canonical_page": "https://www.maxapi.dev/models/google/gemini-4-argon",
  "reviewed_at": "2026-10-26",
  "generated_at": "2026-10-26T14:21:27.957Z",
  "scope": "Checked against MaxAPI's public catalogue, gateway implementation and local regression cases. Shared gateway checks are not separate end-to-end tests of every listed model. This is an integration reference, not a live upstream availability or performance report.",
  "summary": "Gemini 4 Argon is listed as google/gemini-4-argon. Use the Gemini-native request format in the example below, then read candidates and usageMetadata from the response. Model access, routing and account limits are separate from the task instructions you put in contents.",
  "aliases": [],
  "model_profile": {
    "family_id": "google/gemini-4-argon",
    "reviewed_at": "2026-10-26",
    "title": "Long-context analysis and complex reasoning",
    "provider_positioning": "Gemini 4 Argon is a stable text-output model with multimodal input. Google lists a 1,048,576-token context window shared by input and output, and 65,536 output tokens per synchronous response. MaxAPI provides the Gemini-native endpoint on the official-cheap route; long decode and other upstream features are not guaranteed on every relay.",
    "selection_advice": "Evaluate it for analysis across long documents, multi-file engineering changes and problems that need several reasoning steps. It costs more per token than Gemini 3.8 Flash, so compare both on the same task and acceptance criteria before switching.",
    "limitations": "Thinking supports low, medium and high; minimal is not supported. Output billing includes thinking tokens. Google offers implicit caching only, so the cached-input rate applies only when the response reports cached tokens. Start with optional settings omitted. The website composer accepts text; API multimodal inputs and tools need validation for your workflow.",
    "suggested_use_cases": [
      {
        "title": "Analyze a long source set",
        "body": "Send the complete documents in one request and ask for findings with passage references. Check each reference against the source."
      },
      {
        "title": "Plan a multi-file change",
        "body": "Provide the relevant files, constraints and failing test output. Ask for a step-by-step plan with the risk of each step before any code is written."
      },
      {
        "title": "Continue an account conversation",
        "body": "Save a conversation to your MaxAPI account, then resume it on another device with the same model."
      }
    ],
    "example_prompt": {
      "title": "Review a rollout order",
      "text": "Review this rollout plan: a new database column is added in the same release that starts reading it, and every application server restarts at once. State the failure risk, a safer order of steps and how to verify each step. Separate facts from assumptions and do not claim tests were run.",
      "review": "Check that the schema change lands before code that depends on it and that every step has an observable check."
    },
    "scope": "Provider capabilities describe the model, not the complete MaxAPI feature set. Use the parameters, input types and routes documented for this MaxAPI entry. Vendor speed or quality descriptions are not service-level guarantees.",
    "variant_note": null,
    "sources": [
      {
        "label": "Google · gemini-4-argon",
        "url": "https://ai.google.dev/gemini-api/docs/models/gemini-4-argon"
      }
    ]
  },
  "illustration": {
    "url": "https://www.maxapi.dev/model-guides/gemini4-argon-20261026/gemini-4-argon.webp",
    "alt": "Glass tube glowing with violet light, linked to documents, a film panel, an audio plate and code tiles",
    "caption": "Long-context concept: bring documents, media and code into one request before reasoning.",
    "provenance": "ai_generated_editorial_concept",
    "is_output_from_named_model": false,
    "is_benchmark": false
  },
  "illustrations": [
    {
      "section": "usecases",
      "url": "https://www.maxapi.dev/model-guides/gemini4-argon-20261026/gemini-4-argon.webp",
      "alt": "Glass tube glowing with violet light, linked to documents, a film panel, an audio plate and code tiles",
      "caption": "Long-context concept: bring documents, media and code into one request before reasoning.",
      "width": 1536,
      "height": 1024,
      "provenance": "ai_generated_editorial_concept",
      "is_output_from_named_model": false,
      "is_benchmark": false
    },
    {
      "section": "features",
      "url": "https://www.maxapi.dev/model-guides/gemini4-argon-20261026/practice.webp",
      "alt": "Document stack, film reel and cassette marked with coloured tabs, in one row with a plain binder",
      "caption": "Prepare the complete source set and mark what each part is before asking questions.",
      "width": 1536,
      "height": 1024,
      "provenance": "ai_generated_editorial_concept",
      "is_output_from_named_model": false,
      "is_benchmark": false
    },
    {
      "section": "prompts",
      "url": "https://www.maxapi.dev/model-guides/gemini4-argon-20261026/prompt.webp",
      "alt": "Aluminium switchboard linked by violet cables to a glowing glass core, with a loupe, a map and an abacus in front",
      "caption": "Tool-use concept: declare each tool and its arguments explicitly, then check every call.",
      "width": 1536,
      "height": 1024,
      "provenance": "ai_generated_editorial_concept",
      "is_output_from_named_model": false,
      "is_benchmark": false
    },
    {
      "section": "workflow",
      "url": "https://www.maxapi.dev/model-guides/gemini4-argon-20261026/workflow.webp",
      "alt": "Balance scale weighing evidence cards against a violet glass block beside three indicator lights",
      "caption": "Verification concept: weigh each conclusion against the supplied evidence before accepting it.",
      "width": 1536,
      "height": 1024,
      "provenance": "ai_generated_editorial_concept",
      "is_output_from_named_model": false,
      "is_benchmark": false
    }
  ],
  "configured_facts": [
    {
      "label": "Request model ID",
      "value": "google/gemini-4-argon",
      "code": true
    },
    {
      "label": "Output type",
      "value": "Language"
    },
    {
      "label": "Base URL",
      "value": "https://api.maxapi.dev",
      "code": true
    },
    {
      "label": "Generation workflow",
      "value": "Gemini-compatible generateContent"
    }
  ],
  "integration_checklist": {
    "reviewedAt": "2026-10-26",
    "labels": {
      "title": "Check your first result",
      "requestTitle": "Send the right fields",
      "responseTitle": "Read the actual result",
      "example": "Illustrative response shape — not a live result",
      "poll": "Query the existing task",
      "reviewed": "Request-contract review",
      "nativeRequest": "Alternative: a Gemini-native request",
      "nativeResult": "Gemini-native result shape — illustrative only"
    },
    "scope": "Checked against the public catalogue and gateway code. Examples are structural illustrations, not paid model tests, latency measurements or a guarantee that every route is currently available.",
    "requestChecks": [
      {
        "field": "POST /v1beta/models/gemini-4-argon:generateContent",
        "body": "Use the short model ID in the URL and contents[].parts[].text in the body. This is a language endpoint, not an image-generation request."
      },
      {
        "field": "X-MaxAPI-Route-Mode",
        "body": "If you need an explicit route, use this header, not a route_mode field in the Gemini body. A configured API-key route list still takes priority over the header."
      },
      {
        "field": "generationConfig",
        "body": "The minimal example omits optional thinking, tools and output-schema settings. Add only options supported by this exact model and route; a short prompt is not a fixed-cost quote."
      }
    ],
    "responseChecks": [
      {
        "field": "candidates / finishReason / promptFeedback",
        "body": "Read the candidate text parts, finish reason and any prompt feedback. Handle missing candidates or an interrupted answer explicitly; HTTP success alone is not an accepted answer."
      },
      {
        "field": "usageMetadata",
        "body": "Use returned usage and MaxAPI billing records to verify spend. Do not turn the catalogue price per million tokens into a fixed price per response, or invent missing token counts."
      },
      {
        "field": ":streamGenerateContent",
        "body": "MaxAPI currently waits for the complete result, then emits one SSE data event. This provides response-format compatibility, not progressive token streaming. Do not design typing indicators around immediate first-token delivery."
      }
    ],
    "sample": {
      "candidates": [
        {
          "content": {
            "role": "model",
            "parts": [
              {
                "text": "Illustrative answer only."
              }
            ]
          },
          "finishReason": "STOP"
        }
      ]
    }
  },
  "pricing_scope": "1 credit = US$1. These are catalogue base rates, not a live account quote. Account multipliers and the active billing configuration determine the final charge. Token rates are not a fixed price per image.",
  "pricing_index": "https://www.maxapi.dev/pricing.json",
  "routing_rules": [
    {
      "title": "Which route wins?",
      "body": "Routing priority is: the API key's configured route_modes list → an explicitly requested route → the model's default route. A non-empty key list takes precedence over route_mode in the request. To test a specific route, check the key configuration first; changing the request alone may not change the route used."
    },
    {
      "title": "RPM is shared at account level",
      "body": "An account's positive RPM limit covers its API keys together. A key can impose a stricter limit, but a higher key limit does not override the user limit. For example, a user limit of 200 RPM is not 200 RPM for each key. Service-level RPM and concurrency controls also apply; adding keys is not a way to bypass them."
    }
  ],
  "troubleshooting": [
    {
      "code": "429",
      "title": "rate_limit_exceeded / capacity_exhausted",
      "meaning": "429 can represent account/key RPM, service-wide capacity or generation capacity. Use Retry-After and available X-RateLimit-* / X-Global-* headers to distinguish them; one status code does not identify one unique cause.",
      "action": "Respect Retry-After when present, reduce request rate or active concurrency as appropriate, and use bounded backoff. Do not treat the site's total capacity as your account's personal quota."
    }
  ],
  "verification": {
    "environment": "local_mock_requests_and_test_storage",
    "coverage": "shared_gateway_components_not_each_model_end_to_end",
    "paid_upstream_calls": 0,
    "reviewed_at": "2026-10-26",
    "cases": [
      {
        "key": "shared-user-rpm",
        "title": "Multiple keys share the user limit",
        "input": "Use two keys owned by the same account against an in-memory limiter with a small user quota.",
        "result": "Requests across the keys consume the same user quota; subsequent requests are limited. A larger key quota does not override the user quota, and a smaller key quota remains effective."
      }
    ],
    "limitations": "Local tests use simulated requests, responses and test storage; they do not call paid model channels. They verify request handling, not model image quality, live success rates, latency or end-to-end support for the maximum reference count. The concept illustrations elsewhere on this page are not these test outputs."
  },
  "sources": {
    "maxapi_documentation": "https://www.maxapi.dev/docs",
    "catalogue": "https://www.maxapi.dev/models.json",
    "provider_documentation": "https://ai.google.dev/gemini-api/docs/models/gemini-4-argon"
  }
}