{
  "data": {
    "a": {
      "slug": "gemini-4-argon",
      "name": "Gemini 4 Argon",
      "vendor": "Google",
      "vendorUrl": "https://ai.google.dev",
      "company": "google.com",
      "kind": "model",
      "category": "inference",
      "summary": "Gemini 4 Argon is Google's efficient Gemini 4 reasoning model, spending fewer thinking tokens per turn than Carbon on coding, agentic, maths and science work, on the paid tier of the Gemini API with a 1,048,576-token shared limit.",
      "url": "https://www.anchorterminal.com/tools/gemini-4-argon",
      "markdownUrl": "https://www.anchorterminal.com/tools/gemini-4-argon.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gemini-4-argon.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gemini-4-argon.json",
      "dns": "gemini-4-argon.grade.anchorterminal.com",
      "license": "Closed model, used through the Gemini API and Google's apps under Google's terms",
      "transports": [],
      "remoteUrl": "https://generativelanguage.googleapis.com/v1beta",
      "packages": [],
      "auth": "api-key",
      "authNotes": "An `x-goog-api-key` from AI Studio on a project with billing, since Argon is on the paid tier only, per Google's pricing page and What's new guide. On Google Cloud it's `gemini-4-argon` on the Agent Platform, with Cloud credentials; `gemini-4-argon-cyber-permissive` is behind an allowlist.",
      "pricing": "usage",
      "pricingNotes": "An introductory $2 per million input tokens and $10 output to 30 November 2026, then $4 and $20 from 1 December, with implicit caching taking cached input 95% off, per Google's pricing page. Paid tier only, no free tier. Every processed token is billed, thinking and grounding instructions included (checked 2026-11-18).",
      "priceSummary": "Pay per use",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No machine payment. Paid use needs billing on a Cloud project, per the Gemini API listing (checked 2026-11-18).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://aistudio.google.com/docs/models/gemini-4-argon",
      "llmsTxt": "https://aistudio.google.com/llms.txt",
      "capabilities": [
        "inference.llm"
      ],
      "tags": [
        "official",
        "hosted",
        "model",
        "multimodal",
        "reasoning",
        "long-context",
        "tool-calling",
        "usage-priced",
        "card-required",
        "closed-source",
        "llms-txt"
      ],
      "lastRelease": "2026-10-13",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 65.3,
        "grade": "B",
        "agentReady": false,
        "rank": 545,
        "ranked": true,
        "rankOf": 1559,
        "categoryRank": 23,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 93,
          "maintenance": 87,
          "payments": 30,
          "reliability": 45,
          "schema": 85,
          "security": 55,
          "transparency": 73
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "verdict": "Google's efficient Gemini 4 reasoning model, generally available since 13 October, with a 1M-token shared budget, three thinking levels, function calling and structured output, and support on Cloud until October 2027 at the earliest. Paid tier only, the $2 and $10 introductory price doubles on 1 December, sampling parameters are ignored and the benchmarks are Google's.",
        "bestFor": "Agents doing advanced coding and knowledge work on the paid Gemini API that want Gemini 4 reasoning with fewer thinking tokens per turn than Carbon.",
        "strengths": [
          "Generally available on the Gemini API and Google Cloud since 13 October 2026",
          "Fewer thinking tokens per turn than Carbon, for interactive coding and fast production loops, per Google",
          "1,048,576 tokens shared between input and output, with long decode to the full budget",
          "Function calling, structured output, code execution, computer use, file search, URL context and Search and Maps grounding",
          "Google Cloud lists a retirement date of 13 October 2027 or later"
        ],
        "weaknesses": [
          "Paid tier only, so an agent can't start on a free key",
          "The introductory $2 and $10 per million tokens becomes $4 and $20 on 1 December 2026, more than Neon",
          "temperature, top_p and top_k are ignored, and explicit context caching isn't supported",
          "Three thinking levels, with no xhigh, and Google advises at least 32,768 output tokens",
          "Benchmark figures are Google's own, and its safety report says biological and cyber critical levels can't be ruled out"
        ],
        "agentNotes": [
          "Call generateContent at https://generativelanguage.googleapis.com/v1beta, or the Interactions API, with model gemini-4-argon and an x-goog-api-key on a billed project",
          "Keep thinking_level at medium, the default, and raise it to high for hard maths, science and code",
          "Set max_output_tokens to at least 32,768, since Argon spends more of the limit on thinking",
          "Don't send temperature, top_p or top_k, and remove any cached_content fields",
          "Budget for $4 input and $20 output per million tokens from 1 December 2026, or compare Neon at $3 and $15"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 65.3
          }
        ],
        "editorialScores": {
          "ergonomics": 93,
          "maintenance": 87,
          "payments": 30,
          "reliability": 45,
          "schema": 85,
          "security": 55,
          "transparency": 55
        },
        "provenanceScore": 91,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-18",
            "maintenance": "2026-11-18",
            "payments": "2026-11-18",
            "reliability": "2026-11-18",
            "schema": "2026-11-18",
            "security": "2026-11-18",
            "transparency": "2026-11-18"
          },
          "last": "2026-11-18",
          "oldest": "2026-11-18",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "http": "curl \"https://generativelanguage.googleapis.com/v1beta/models/gemini-4-argon:generateContent\" \\\n  -H \"x-goog-api-key: $GEMINI_API_KEY\" -H \"content-type: application/json\" \\\n  -d '{\"contents\":[{\"parts\":[{\"text\":\"hello\"}]}]}'"
      },
      "letme": {
        "capability": "https://letme.dev/inference.llm",
        "tool": "https://letme.dev/gemini-4-argon"
      },
      "sameCompany": [
        "gemini-4-carbon",
        "gemini-4-hydrogen",
        "gemini-4-neon",
        "vertex-ai",
        "embeddinggemma-2",
        "embeddinggemma-300m",
        "gemini-embedding",
        "vertex-ai-tuning",
        "cloud-run-gpus",
        "google-model-armor",
        "shieldgemma",
        "google-imagen",
        "gemini-omni-1-2-flash",
        "google-veo",
        "google-lyria",
        "google-speech-to-text",
        "google-cloud-tts",
        "gemini-live",
        "google-adk",
        "google-memory-bank",
        "google-secret-manager",
        "google-cloud-document-ai",
        "google-weather-api",
        "chrome-devtools-mcp",
        "puppeteer",
        "mcp-toolbox-databases",
        "google-maps-platform",
        "google-cloud-translation",
        "google-calendar-api",
        "firebase-cloud-messaging",
        "google-cloud-storage",
        "google-drive-api",
        "gemini-enterprise",
        "gemini-decision-1",
        "antigravity-cli",
        "gemini-cli",
        "harness2",
        "jules",
        "gemini-spark",
        "google-search-console",
        "google-ads-api",
        "google-forms",
        "google-sheets-api",
        "gmail-api",
        "google-people-api",
        "diffusiongemma-26b-a4b-it",
        "gemma-4-12b-it",
        "gemma-4-26b-a4b-it",
        "gemma-4-31b-it",
        "gemma-4-e2b-it",
        "gemma-4-e4b-it",
        "virustotal"
      ],
      "sameModel": [
        "gemini-api"
      ],
      "area": "models",
      "unitPrices": [
        {
          "item": "Gemini 4 Argon input",
          "unit": "1m-tokens",
          "usd": 2,
          "note": "Introductory to 30 November 2026; $4 from 1 December"
        },
        {
          "item": "Gemini 4 Argon cached input",
          "unit": "1m-tokens",
          "usd": 0.1,
          "note": "Implicit caching, 95% off; $0.20 from 1 December"
        },
        {
          "item": "Gemini 4 Argon output",
          "unit": "1m-tokens",
          "usd": 10,
          "note": "Introductory, thinking included; $20 from 1 December"
        }
      ],
      "provenance": {
        "legalEntity": "Google LLC",
        "domain": "google.com",
        "domainRegistered": "1997-09-15",
        "domainNote": "The endpoint is on googleapis.com, Google's API domain. google.com was registered in 1997.",
        "endpointOnVendorDomain": true,
        "terms": "https://aistudio.google.com/docs/terms",
        "privacy": "https://policies.google.com/privacy",
        "statusPage": "https://aistudio.google.com/status",
        "changelog": "https://aistudio.google.com/docs/changelog",
        "securityTxt": "valid",
        "checked": "2026-11-18",
        "score": 91
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/gemini-4-argon.json",
      "live": {
        "slug": "gemini-4-argon",
        "probe": {
          "target": "https://generativelanguage.googleapis.com/v1beta",
          "method": "get",
          "lastAt": "2026-11-19T01:54:50.482834315Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 38,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 42,
          "p95ms24h": 245,
          "samples24h": 15,
          "samples30d": 15,
          "days": [
            {
              "date": "2026-11-19",
              "probes": 15,
              "ok": 15
            }
          ],
          "since": "2026-11-19T00:31:47.649616679Z"
        },
        "vendorStatus": {
          "page": "https://aistudio.google.com/status",
          "indicator": "unknown",
          "summary": "no machine-readable status found",
          "checkedAt": "2026-11-19T01:01:11.89705134Z"
        },
        "updatedAt": "2026-11-19T01:54:50.482834315Z"
      },
      "streak": {
        "days": 0,
        "from": "2026-11-19",
        "sinceWatching": true,
        "best": 0
      }
    },
    "answer": "Gemini 4 Argon scores 65.3 (B) on agent readiness against StepFun API's 45.6 (E), and leads in 6 of 7 scored categories.",
    "b": {
      "slug": "stepfun-api",
      "name": "StepFun API",
      "vendor": "StepFun",
      "vendorUrl": "https://platform.stepfun.ai",
      "company": "stepfun.ai",
      "kind": "model",
      "category": "inference",
      "summary": "The StepFun API is StepFun's paid model API for its Step language, vision and speech models, including the flagship Step 5 Preview, through OpenAI-style Chat Completions and Responses endpoints and an Anthropic-style Messages endpoint.",
      "url": "https://www.anchorterminal.com/tools/stepfun-api",
      "markdownUrl": "https://www.anchorterminal.com/tools/stepfun-api.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/stepfun-api.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/stepfun-api.json",
      "dns": "stepfun-api.grade.anchorterminal.com",
      "license": "Closed service under the StepFun Open Platform Terms of Service (STEPFUN TECHNOLOGY (HK) LIMITED, Hong Kong law).",
      "transports": [
        "http"
      ],
      "remoteUrl": "https://api.stepfun.ai/v1",
      "packages": [],
      "auth": "api-key",
      "authNotes": "A bearer API key created in the StepFun Open Platform console after sign-up. Organisations can create one key per project, billed to the organisation's credit and deletable at once. No key scopes were found. Individual accounts must complete identity verification before tiered rate limits apply.",
      "pricing": "usage",
      "pricingNotes": "Step 5 Preview is $1.00 per million input tokens on a cache miss, $0.10 on a cache hit and $2.70 per million output tokens, reasoning included (checked 2026-10-12). Prepaid top-ups. No free API allowance was found. A Step Plan subscription covers coding tools separately.",
      "priceSummary": "from $0.10 / 1M in",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the international docs index, the pricing page or the Chat Completions reference, checked 12 October 2026. Calls draw on a prepaid balance.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-12"
      },
      "docsUrl": "https://platform.stepfun.ai/docs/en/guides/models/step-5-preview",
      "llmsTxt": "https://platform.stepfun.ai/docs/llms.txt",
      "capabilities": [
        "inference.llm"
      ],
      "tags": [
        "official",
        "hosted",
        "model",
        "usage-priced",
        "closed-source",
        "llms-txt",
        "multimodal",
        "streaming"
      ],
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 45.6,
        "grade": "E",
        "agentReady": false,
        "rank": 1276,
        "ranked": true,
        "rankOf": 1559,
        "categoryRank": 46,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 68,
          "maintenance": 50,
          "payments": 30,
          "reliability": 28,
          "schema": 53,
          "security": 41,
          "transparency": 57
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-05"
        },
        "negative": 0,
        "verdict": "StepFun's API serves Step 5 Preview with a 1M-token context, video input, strict JSON Schema output and published per-token prices, documented in Markdown with an llms.txt. The model is a preview with no release date found, there's no free allowance or SLA, and the terms and privacy policy leave room to train on customer data.",
        "bestFor": "Long-context agent and coding work over text, screenshots and video at a low per-token price, where a preview model is acceptable.",
        "strengths": [
          "Step 5 Preview takes text, images and video with a 1M-token context and up to 64k output tokens",
          "Strict JSON Schema output and tool calls on Step 5 Preview, per the structured-output guide",
          "Per-token prices with cache-hit rates published without a login, and rate-limit tiers published with numbers",
          "OpenAI-style Chat Completions and Responses endpoints and an Anthropic-style Messages endpoint",
          "llms.txt and a Markdown copy of every docs page"
        ],
        "weaknesses": [
          "Step 5 Preview is labelled a preview, and no release date or support commitment was found",
          "No free API allowance found, and individual accounts need identity verification for tiered limits",
          "No OpenAPI file, no official SDK and no batch endpoint found",
          "The privacy policy allows training on user data where law and program terms permit, with no zero-retention option found",
          "No SLA, security.txt or certification found"
        ],
        "agentNotes": [
          "Set `max_tokens` yourself. It defaults to unlimited on Step 5 Preview, and reasoning tokens are billed as output",
          "Use `response_format` with `type: json_schema` and `strict: true` when the shape matters. JSON Mode alone isn't schema-checked",
          "Back off and retry on 429, 500, 503 and 504. The docs give no Retry-After header or backoff schedule",
          "Expect HTTP 451 or `finish_reason: content_filter` when content fails StepFun's review, and don't retry the same input",
          "Use api.stepfun.ai for the international platform. api.stepfun.com is the China platform with yuan pricing"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 4,
        "avgRating": 3.3,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "E",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 45.6
          }
        ],
        "editorialScores": {
          "ergonomics": 68,
          "maintenance": 50,
          "payments": 30,
          "reliability": 28,
          "schema": 53,
          "security": 41,
          "transparency": 51
        },
        "provenanceScore": 62,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-05",
            "maintenance": "2026-11-05",
            "payments": "2026-11-05",
            "reliability": "2026-11-05",
            "schema": "2026-11-05",
            "security": "2026-11-05",
            "transparency": "2026-11-05"
          },
          "last": "2026-11-05",
          "lastMoved": "2026-11-13",
          "oldest": "2026-11-05",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "http": "curl https://api.stepfun.ai/v1/chat/completions \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Authorization: Bearer $STEPFUN_API_KEY\" \\\n  -d '{\"model\":\"step-5-preview\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'"
      },
      "letme": {
        "capability": "https://letme.dev/inference.llm",
        "tool": "https://letme.dev/stepfun-api"
      },
      "sameModel": [
        "step-3-7-flash"
      ],
      "area": "models",
      "unitPrices": [
        {
          "item": "Step 5 Preview input, cache miss",
          "unit": "1m-tokens",
          "usd": 1,
          "note": "Includes writing new content to the cache."
        },
        {
          "item": "Step 5 Preview input, cache hit",
          "unit": "1m-tokens",
          "usd": 0.1
        },
        {
          "item": "Step 5 Preview output",
          "unit": "1m-tokens",
          "usd": 2.7,
          "note": "Reasoning and final answer tokens."
        }
      ],
      "provenance": {
        "legalEntity": "STEPFUN TECHNOLOGY (HK) LIMITED",
        "domain": "stepfun.ai",
        "domainRegistered": "",
        "endpointOnVendorDomain": true,
        "terms": "https://platform.stepfun.ai/docs/en/agreement/userservice",
        "privacy": "https://platform.stepfun.ai/docs/en/agreement/userprivacy",
        "statusPage": "",
        "changelog": "https://platform.stepfun.ai/docs/en/guides/model-migration",
        "securityTxt": "none",
        "checked": "2026-11-05",
        "notes": [
          "The terms and the privacy policy name STEPFUN TECHNOLOGY (HK) LIMITED. Disputes go to HKIAC arbitration under Hong Kong law.",
          "platform.stepfun.ai/.well-known/security.txt returned 404, and stepfun.ai/.well-known/security.txt redirects to the platform home page.",
          "status.stepfun.ai refused our reader by robots.txt, and the shell couldn't connect, so whether it is a status page wasn't established.",
          "The X handle comes from the QR code labelled X account on the platform home page, which decodes to https://x.com/StepFun_ai.",
          "Domain registration date was not checked.",
          "The Terms of Service (effective 7 August 2026) section 3.2 bar crawling, scraping or otherwise harvesting data or information from the Services, defined as the APIs and other services on the StepFun Open Platform (read 5 November 2026)."
        ],
        "score": 62
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/stepfun-api.json",
      "live": {
        "slug": "stepfun-api",
        "probe": {
          "target": "https://api.stepfun.ai/v1",
          "method": "get",
          "lastAt": "2026-11-19T01:55:14.140162741Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 280,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 301,
          "p95ms24h": 527,
          "samples24h": 240,
          "samples30d": 7613,
          "days": [
            {
              "date": "2026-10-19",
              "probes": 255,
              "ok": 255
            },
            {
              "date": "2026-10-20",
              "probes": 252,
              "ok": 252
            },
            {
              "date": "2026-10-21",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-22",
              "probes": 253,
              "ok": 253
            },
            {
              "date": "2026-10-23",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-24",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-10-25",
              "probes": 250,
              "ok": 250
            },
            {
              "date": "2026-10-26",
              "probes": 252,
              "ok": 252
            },
            {
              "date": "2026-10-27",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-28",
              "probes": 250,
              "ok": 250
            },
            {
              "date": "2026-10-29",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-30",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-31",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-11-01",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-11-02",
              "probes": 250,
              "ok": 250
            },
            {
              "date": "2026-11-03",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-11-04",
              "probes": 246,
              "ok": 246
            },
            {
              "date": "2026-11-05",
              "probes": 185,
              "ok": 185
            },
            {
              "date": "2026-11-06",
              "probes": 241,
              "ok": 241
            },
            {
              "date": "2026-11-07",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-08",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-09",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-10",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-11",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-12",
              "probes": 245,
              "ok": 245
            },
            {
              "date": "2026-11-13",
              "probes": 238,
              "ok": 238
            },
            {
              "date": "2026-11-14",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-15",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-16",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-17",
              "probes": 242,
              "ok": 242
            },
            {
              "date": "2026-11-18",
              "probes": 240,
              "ok": 240
            },
            {
              "date": "2026-11-19",
              "probes": 20,
              "ok": 20
            }
          ],
          "since": "2026-10-12T00:00:00Z"
        },
        "securityTxt": {
          "url": "https://stepfun.ai/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-18T16:30:47.470084313Z"
        },
        "llmsTxt": {
          "url": "https://platform.stepfun.ai/docs/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-18T16:16:18.656709556Z"
        },
        "domain": {
          "domain": "stepfun.ai",
          "registered": "2023-03-23",
          "source": "https://rdap.identitydigital.services/rdap/domain/stepfun.ai",
          "checkedAt": "2026-11-15T15:30:09.495683486Z"
        },
        "pages": [
          {
            "url": "https://platform.stepfun.ai/docs/en/guides/model-migration",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-11-18T21:51:01.585256229Z",
            "changedAt": "2026-11-13T18:27:26.112325292Z",
            "fingerprint": "16f43318cb66"
          },
          {
            "url": "https://platform.stepfun.ai/docs/en/guides/image-offline-notice",
            "kind": "deprecations",
            "status": 200,
            "checkedAt": "2026-11-18T21:50:59.549202022Z",
            "changedAt": "2026-11-13T18:27:24.242173228Z",
            "fingerprint": "1507b3eee644"
          },
          {
            "url": "https://platform.stepfun.ai/docs/en/agreement/userprivacy",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-11-18T21:50:55.28501882Z",
            "changedAt": "2026-11-13T18:27:19.202819828Z",
            "fingerprint": "faef5729a403"
          },
          {
            "url": "https://platform.stepfun.ai/docs/en/agreement/userservice",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-11-18T21:50:57.698632143Z",
            "changedAt": "2026-11-13T18:27:21.842265334Z",
            "fingerprint": "c9f8dccbce80"
          }
        ],
        "updatedAt": "2026-11-19T01:55:14.140162741Z"
      },
      "streak": {
        "days": 38,
        "from": "2026-10-12",
        "sinceWatching": true,
        "last": {
          "kind": "shutdown",
          "date": "2026-10-10",
          "what": "`step-2x-large` and `step-image-edit-2` retire, and the text-to-image, image-to-image and image editing APIs stop serving requests, with no replacement named",
          "source": "https://platform.stepfun.ai/docs/en/guides/image-offline-notice"
        },
        "best": 38
      }
    },
    "edges": [
      {
        "by": 37,
        "category": "maintenance",
        "leads": "gemini-4-argon",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "Model reading for gemini-4-argon on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Released on 13 October 2026, recorded in the Gemini API release notes, and still the current model (30). Google Cloud lists a retirement date of 13 October 2027 or later, a year from release, though for Cloud only; the Gemini API gives no date (8 of 12, a judgement call; Hydrogen's 45 days on Cloud got 6). Shutdowns in the last 90 days kept to their table (4 of 8). Dated changelog (15). SDK replies not sampled (5 of 10). Current SDKs (15). Runtimes stated (10). 30 + 8 + 4 + 15 + 5 + 15 + 10 = 87.",
          "b": "StepFun's Terms of Service (effective 7 August 2026) bar crawling, scraping or otherwise harvesting data from the Services, defined as the APIs and other services on the StepFun Open Platform, so its sites were not re-read on 5 November. Per the 12 October check, not re-read on 5 November. Model reading. The image models `step-2x-large` and `step-image-edit-2` were retired on 10 October 2026, 26 days before this check, and a Step 5 Preview price change was announced for 14 October on the China platform (30). No stated notice period. The 10 October image retirement had a dated notice page and the July retirements a migration table, but we couldn't date when either notice went up (4 of 12). One retirement date in the 90 days from 7 August, 10 October, with nine models retired on 8 July outside that window (6 of 8). Dated announcements, a Discord server and platform@stepfun.com for support. We didn't test whether either answers (10 of 15). No official SDK (0 of 15, 0 of 10). 30+4+6+10+0+0 = 50."
        },
        "scores": {
          "a": 87,
          "b": 50
        }
      },
      {
        "by": 32,
        "category": "schema",
        "leads": "gemini-4-argon",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "Model reading for gemini-4-argon on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Discovery document for GenerateContent (20 of 25). llms.txt with Markdown twins (10). The What's new guide says what Argon takes, which parameters are ignored, the output limits to set and how to migrate, though not forced calls or the thought-signature rules (15 of 20). Structured output to a JSON Schema with some keywords not enforced (10 of 15). Examples and an errors page (15). Dated changelog and model versions (15). 20 + 10 + 15 + 10 + 15 + 15 = 85.",
          "b": "StepFun's Terms of Service (effective 7 August 2026) bar crawling, scraping or otherwise harvesting data from the Services, defined as the APIs and other services on the StepFun Open Platform, so its sites were not re-read on 5 November. Per the 12 October check, not re-read on 5 November. No OpenAPI or similar machine-readable contract found. The API reference is Markdown pages (0). llms.txt at platform.stepfun.ai/docs/llms.txt, and every page has a Markdown copy (10). The Chat Completions reference describes each parameter with its default, and the model page lists what Step 5 Preview supports, but little on when not to use an option (12 of 20). Tool definitions take JSON Schema parameters, structured output takes a JSON Schema with `strict: true`, and `reasoning_effort` is an enum of low, medium and high. No `tool_choice` parameter is documented (11 of 15). Worked requests and responses on each page, and an error table of eight codes with causes and fixes, but no error bodies (12 of 15). No API changelog. A model lifecycle page with dated retirements and announcement pages (8 of 15). 0+10+12+11+12+8 = 53."
        },
        "scores": {
          "a": 85,
          "b": 53
        }
      },
      {
        "by": 25,
        "category": "ergonomics",
        "leads": "gemini-4-argon",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "Model reading for gemini-4-argon on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Function calling, with forced calls by FunctionCallingConfig on the API (20). Structured output, listed as supported on the model page (13 of 15). Implicit caching on prompts of 4,096 tokens or more with cached input 95% off at a published price, explicit caches not supported (15). 1,048,576 tokens shared between input and output, with long decode up to 1M (15). Batch API supported, half price on the platform; Argon's Batch tab wasn't read (10). Python and JavaScript SDKs (10). Error codes with backoff guidance (10 of 15). 20 + 13 + 15 + 15 + 10 + 10 + 10 = 93.",
          "b": "StepFun's Terms of Service (effective 7 August 2026) bar crawling, scraping or otherwise harvesting data from the Services, defined as the APIs and other services on the StepFun Open Platform, so its sites were not re-read on 5 November. Per the 12 October check, not re-read on 5 November. Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool calls through Chat Completions, Responses and Messages, with no documented way to force or forbid a call (15 of 20). Strict JSON Schema output on Step 5 Preview (13 of 15). Prompt caching with a published cache-hit price at a tenth of the miss price (15). 1M-token context and 64k output (15). No batch endpoint found (0). No official SDK. The docs use the OpenAI and Anthropic clients against compatible endpoints (0). Eight error codes with a fix each, plus `finish_reason` handling for length, content filter and tool calls (10 of 15). 15+13+15+15+0+0+10 = 68."
        },
        "scores": {
          "a": 93,
          "b": 68
        }
      },
      {
        "by": 17,
        "category": "reliability",
        "leads": "gemini-4-argon",
        "name": "Reliability",
        "reasons": {
          "a": "Model reading for gemini-4-argon on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Status page at aistudio.google.com/status with no readable components or history (10 of 20) and no readable incident record (5 of 30). Rate-limit tiers and spend limits published, per-model limits in AI Studio (5 of 15). Backoff guidance for 429 and 503 and SDK retries (15). No SLA (0). The Gemini API release notes and the Google Cloud model page both call Argon generally available from 13 October 2026 (10). 10 + 5 + 5 + 15 + 0 + 10 = 45.",
          "b": "StepFun's Terms of Service (effective 7 August 2026) bar crawling, scraping or otherwise harvesting data from the Services, defined as the APIs and other services on the StepFun Open Platform, so its sites were not re-read on 5 November. Per the 12 October check, not re-read on 5 November. No status page read. status.stepfun.ai refused our reader by robots.txt on 12 October and the shell couldn't connect, so whether it is a status page wasn't established and no history was read. Scored absent for both lines, with 5 for unreadable history (0 + 5). Rate limits published with numbers per tier, from 5 concurrent, 100 RPM and 500,000 TPM to 130, 2,600 and 13,000,000 (15). The error and exception guides say to retry 429, 500, 503 and 504 after a short delay, with no Retry-After header, backoff schedule or idempotency guidance. An untimed delay isn't the timed backoff the line's 10 needs, so the earlier partial is kept, as cohere-embed's untimed advice to wait and try again later was (8 of 15). No SLA found in the terms or pricing (0). Step 5 Preview is labelled a preview (0). 0+5+15+8+0+0 = 28."
        },
        "scores": {
          "a": 45,
          "b": 28
        }
      },
      {
        "by": 16,
        "category": "transparency",
        "leads": "gemini-4-argon",
        "name": "Transparency \u0026 trust",
        "reasons": {
          "a": "Model reading for gemini-4-argon on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Closed service with clear terms, SDKs Apache-2.0 (15). Paid-tier data isn't used, abuse retention has no number, and request storage is on by default for new paid projects (20 of 30). Deprecations table, with a Cloud retirement date for Argon (15 of 20). Data may be cached anywhere Google has facilities; no subprocessor list checked (5 of 20). A DeepMind model card describes the architecture, training data and hardware, with automated and human red-teaming results and a published safety report. Every benchmark figure is Google's own. 15 + 20 + 15 + 5 = 55.",
          "b": "StepFun's Terms of Service (effective 7 August 2026) bar crawling, scraping or otherwise harvesting data from the Services, defined as the APIs and other services on the StepFun Open Platform, so its sites were not re-read on 5 November. Per the 12 October check, not re-read on 5 November. Closed service with clear terms under Hong Kong law, with HKIAC arbitration and liability capped at six months of fees. Some earlier Step models have open weights, which doesn't change the hosted service (15). The privacy policy, terms and DPA agree that data may be used for training under program terms, but the terms' licence to Content is broad and perpetual, no retention period is given for prompts and outputs, and no subprocessor list was found (12 of 30). A model lifecycle page with dated retirements and replacements (14 of 20). Servers are disclosed as in the United States. The DPA gives general authorisation for subprocessors without a published list (10 of 20). 15+12+14+10 = 51."
        },
        "scores": {
          "a": 73,
          "b": 57
        }
      },
      {
        "by": 14,
        "category": "security",
        "leads": "gemini-4-argon",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "Model reading for gemini-4-argon on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Keys bound to a service account and restricted to the Gemini API, with no scopes and a token accepted in the URL (15 of 30, the platform's deduction). Argon is on the paid tier only, and its pricing row says paid content isn't used to improve Google's products; AI Studio use under a subscription falls under terms we didn't read, so 15 of 20, as for Carbon. Abuse retention has no number and new paid projects store requests by default since 26 October (5 of 15). Request logs for billed projects (15). security.txt and a reward programme, no certification naming the API (5 of 20). 15 + 15 + 5 + 15 + 5 = 55.",
          "b": "StepFun's Terms of Service (effective 7 August 2026) bar crawling, scraping or otherwise harvesting data from the Services, defined as the APIs and other services on the StepFun Open Platform, so its sites were not re-read on 5 November. Per the 12 October check, not re-read on 5 November. Model reading. Bearer API keys, revocable by deletion. Organisations can create one key per project, billed to a project's credit with a per-member cap. No scopes or read-only keys found (20 of 30). Training on API data is not off by default in plain words. The privacy policy (effective 7 August 2026) says StepFun may use and retain data to improve its models, including training and fine-tuning where law and program terms permit, and the terms name early-access programmes as one such case. No opt-out found (5 of 20). No retention period for prompts and outputs and no zero-retention option. IP addresses are kept three years (3 of 15). The console's usage details list each billed call by key, model and date, with export (8 of 15). No security.txt, bug bounty or certification found. A DPA with breach notification exists (5 of 20). 20+5+3+8+5 = 41."
        },
        "scores": {
          "a": 55,
          "b": 41
        }
      }
    ],
    "facts": [
      {
        "a": "Model API",
        "b": "Model API",
        "name": "Kind"
      },
      {
        "a": "Google",
        "b": "StepFun",
        "name": "Vendor"
      },
      {
        "a": "https://generativelanguage.googleapis.com/v1beta",
        "b": "https://api.stepfun.ai/v1",
        "name": "Hosted endpoint"
      },
      {
        "a": "",
        "b": "HTTP",
        "name": "Transports"
      },
      {
        "a": "API key",
        "b": "API key",
        "name": "Auth"
      },
      {
        "a": "Pay per use",
        "b": "Pay per use",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Closed model, used through the Gemini API and Google's apps under Google's terms",
        "b": "Closed service under the StepFun Open Platform Terms of Service (STEPFUN TECHNOLOGY (HK) LIMITED, Hong Kong law).",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "2026-10-13",
        "b": "none",
        "name": "Last release"
      },
      {
        "a": "not read yet",
        "b": "couldn't be read",
        "name": "Terms last updated"
      },
      {
        "a": "2026-10-01",
        "b": "couldn't be read",
        "name": "Privacy policy last updated"
      },
      {
        "a": "yes",
        "b": "couldn't be read",
        "name": "Customer content may train models"
      },
      {
        "a": "not read yet",
        "b": "couldn't be read",
        "name": "Terms restrict automated access"
      },
      {
        "a": "not read yet",
        "b": "couldn't be read",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "not read yet",
        "b": "couldn't be read",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "not read yet",
        "b": "couldn't be read",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "none",
        "b": "3.3/5 (4)",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "Gemini 4 Argon scores 65.3 (B) on agent readiness against StepFun API's 45.6 (E), and leads in 6 of 7 scored categories.",
        "question": "Which is better for AI agents, Gemini 4 Argon or StepFun API?"
      },
      {
        "answer": "Both need an API key.",
        "question": "Do Gemini 4 Argon and StepFun API need an API key?"
      },
      {
        "answer": "Yes. Gemini 4 Argon has a hosted endpoint at https://generativelanguage.googleapis.com/v1beta and StepFun API at https://api.stepfun.ai/v1.",
        "question": "Can an agent call Gemini 4 Argon and StepFun API without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 45 against 28",
          "Schema \u0026 documentation, 85 against 53",
          "Agent ergonomics, 93 against 68",
          "Security \u0026 auth, 55 against 41",
          "Maintenance \u0026 community, 87 against 50",
          "Transparency \u0026 trust, 73 against 57"
        ],
        "also": null,
        "goodFor": "Agents doing advanced coding and knowledge work on the paid Gemini API that want Gemini 4 reasoning with fewer thinking tokens per turn than Carbon.",
        "slug": "gemini-4-argon",
        "watchFor": "Paid tier only, so an agent can't start on a free key"
      },
      {
        "aheadOn": null,
        "also": null,
        "goodFor": "Long-context agent and coding work over text, screenshots and video at a low per-token price, where a preview model is acceptable.",
        "slug": "stepfun-api",
        "watchFor": "Step 5 Preview is labelled a preview, and no release date or support commitment was found"
      }
    ],
    "history": {
      "gemini-4-argon": null,
      "stepfun-api": [
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 1.3,
          "from": 44.3,
          "fromGrade": "E",
          "to": 45.6,
          "toGrade": "E"
        },
        {
          "causes": [
            "correction"
          ],
          "date": "2026-10-28",
          "delta": -0.1,
          "from": 44.4,
          "fromGrade": "E",
          "to": 44.3,
          "toGrade": "E"
        },
        {
          "causes": [
            "method"
          ],
          "date": "2026-10-27",
          "delta": 0.3,
          "from": 44.1,
          "fromGrade": "E",
          "to": 44.4,
          "toGrade": "E"
        }
      ]
    },
    "job": {
      "capability": "inference.llm",
      "name": "LLM inference"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-gemini-4-argon.json",
        "title": "Amazon Bedrock vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-stepfun-api.json",
        "title": "Amazon Bedrock vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/amazon-bedrock-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-gemini-4-argon.json",
        "title": "Claude API vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-stepfun-api.json",
        "title": "Claude API vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antseed-vs-gemini-4-argon.json",
        "title": "Antseed vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/antseed-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antseed-vs-stepfun-api.json",
        "title": "Antseed vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/antseed-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/azure-openai-vs-gemini-4-argon.json",
        "title": "Azure OpenAI in Foundry Models vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/azure-openai-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/azure-openai-vs-stepfun-api.json",
        "title": "Azure OpenAI in Foundry Models vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/azure-openai-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-gemini-4-argon.json",
        "title": "BlockRun.AI vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-stepfun-api.json",
        "title": "BlockRun.AI vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-gemini-4-argon.json",
        "title": "Cerebras Inference vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-stepfun-api.json",
        "title": "Cerebras Inference vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-fable-5-2-vs-gemini-4-argon.json",
        "title": "Claude Fable 5.2 vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/claude-fable-5-2-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-fable-5-2-vs-stepfun-api.json",
        "title": "Claude Fable 5.2 vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/claude-fable-5-2-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-gemini-4-argon.json",
        "title": "Claude Mythos 5.2 vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-stepfun-api.json",
        "title": "Claude Mythos 5.2 vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-gemini-4-argon.json",
        "title": "Cloudflare AI Gateway vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-stepfun-api.json",
        "title": "Cloudflare AI Gateway vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-gemini-4-argon.json",
        "title": "Cloudflare Workers AI vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-stepfun-api.json",
        "title": "Cloudflare Workers AI vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-gemini-4-argon.json",
        "title": "Cohere Chat API (Command models) vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-stepfun-api.json",
        "title": "Cohere Chat API (Command models) vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepinfra-vs-gemini-4-argon.json",
        "title": "DeepInfra vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/deepinfra-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepinfra-vs-stepfun-api.json",
        "title": "DeepInfra vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/deepinfra-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-gemini-4-argon.json",
        "title": "DeepSeek API vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-stepfun-api.json",
        "title": "DeepSeek API vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/eden-ai-vs-gemini-4-argon.json",
        "title": "Eden AI vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/eden-ai-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/eden-ai-vs-stepfun-api.json",
        "title": "Eden AI vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/eden-ai-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-gemini-4-argon.json",
        "title": "Glimpse vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-stepfun-api.json",
        "title": "Glimpse vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-argon.json",
        "title": "Fireworks AI Inference vs Gemini 4 Argon",
        "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-argon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-stepfun-api.json",
        "title": "Fireworks AI Inference vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-gemini-4-carbon.json",
        "title": "Gemini 4 Argon vs Gemini 4 Carbon",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-gemini-4-carbon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-gemini-4-hydrogen.json",
        "title": "Gemini 4 Argon vs Gemini 4 Hydrogen",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-gemini-4-hydrogen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-gemini-4-neon.json",
        "title": "Gemini 4 Argon vs Gemini 4 Neon",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-gemini-4-neon"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-gemini-api.json",
        "title": "Gemini 4 Argon vs Gemini Developer API",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-gemini-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-gpt-6-2-astra.json",
        "title": "Gemini 4 Argon vs GPT-6.2 Astra",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-gpt-6-2-astra"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-groq.json",
        "title": "Gemini 4 Argon vs GroqCloud",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-groq"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-hugging-face-inference-providers.json",
        "title": "Gemini 4 Argon vs Hugging Face Inference Providers",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-hugging-face-inference-providers"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-hy4.json",
        "title": "Gemini 4 Argon vs Tencent Hy4",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-hy4"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-jais-3.json",
        "title": "Gemini 4 Argon vs Jais 3",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-jais-3"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-meta-model-api.json",
        "title": "Gemini 4 Argon vs Meta Model API",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-meta-model-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-minimax-api.json",
        "title": "Gemini 4 Argon vs MiniMax API",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-minimax-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-mistral-api.json",
        "title": "Gemini 4 Argon vs Mistral AI API",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-mistral-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-muse-ember.json",
        "title": "Gemini 4 Argon vs Muse Ember",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-muse-ember"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-muse-spark-open.json",
        "title": "Gemini 4 Argon vs Muse Spark Open",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-muse-spark-open"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-nemotron-3-5-super-vl.json",
        "title": "Gemini 4 Argon vs Nemotron 3.5 Super VL",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-nemotron-3-5-super-vl"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-novita-ai.json",
        "title": "Gemini 4 Argon vs Novita AI",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-novita-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-openai-api.json",
        "title": "Gemini 4 Argon vs OpenAI API",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-openai-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-openrouter.json",
        "title": "Gemini 4 Argon vs OpenRouter",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-openrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-prism-inference.json",
        "title": "Gemini 4 Argon vs Prism Inference",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-prism-inference"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-ramp-router.json",
        "title": "Gemini 4 Argon vs Router.com (Ramp Router)",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-ramp-router"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-reflection-beam.json",
        "title": "Gemini 4 Argon vs Beam 1.0",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-reflection-beam"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-routerplus.json",
        "title": "Gemini 4 Argon vs RouterPlus",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-routerplus"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-sambanova.json",
        "title": "Gemini 4 Argon vs SambaCloud",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-sambanova"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-siliconflow.json",
        "title": "Gemini 4 Argon vs SiliconFlow",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-siliconflow"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-simplismart.json",
        "title": "Gemini 4 Argon vs Simplismart",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-simplismart"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-swe-2-flash.json",
        "title": "Gemini 4 Argon vs SWE-2 Flash",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-swe-2-flash"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-tencent-tokenhub.json",
        "title": "Gemini 4 Argon vs Tencent Cloud TokenHub",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-tencent-tokenhub"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-together-inference.json",
        "title": "Gemini 4 Argon vs Together AI Inference",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-together-inference"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-vercel-ai-gateway.json",
        "title": "Gemini 4 Argon vs Vercel AI Gateway",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-vercel-ai-gateway"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-vertex-ai.json",
        "title": "Gemini 4 Argon vs Vertex AI (Gemini Enterprise Agent Platform)",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-vertex-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-xai-api.json",
        "title": "Gemini 4 Argon vs xAI API (Grok)",
        "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-xai-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-stepfun-api.json",
        "title": "Gemini 4 Carbon vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/gemini-4-carbon-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-stepfun-api.json",
        "title": "Gemini 4 Hydrogen vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-4-neon-vs-stepfun-api.json",
        "title": "Gemini 4 Neon vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/gemini-4-neon-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-api-vs-stepfun-api.json",
        "title": "Gemini Developer API vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/gemini-api-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-stepfun-api.json",
        "title": "GPT-6.2 Astra vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/groq-vs-stepfun-api.json",
        "title": "GroqCloud vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/groq-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-stepfun-api.json",
        "title": "Hugging Face Inference Providers vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hy4-vs-stepfun-api.json",
        "title": "Tencent Hy4 vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/hy4-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/jais-3-vs-stepfun-api.json",
        "title": "Jais 3 vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/jais-3-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/meta-model-api-vs-stepfun-api.json",
        "title": "Meta Model API vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/meta-model-api-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/minimax-api-vs-stepfun-api.json",
        "title": "MiniMax API vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/minimax-api-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/mistral-api-vs-stepfun-api.json",
        "title": "Mistral AI API vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/mistral-api-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/muse-ember-vs-stepfun-api.json",
        "title": "Muse Ember vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/muse-ember-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/muse-spark-open-vs-stepfun-api.json",
        "title": "Muse Spark Open vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/muse-spark-open-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-stepfun-api.json",
        "title": "Nemotron 3.5 Super VL vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/novita-ai-vs-stepfun-api.json",
        "title": "Novita AI vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/novita-ai-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/openai-api-vs-stepfun-api.json",
        "title": "OpenAI API vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/openai-api-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/openrouter-vs-stepfun-api.json",
        "title": "OpenRouter vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/openrouter-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/prism-inference-vs-stepfun-api.json",
        "title": "Prism Inference vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/prism-inference-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/ramp-router-vs-stepfun-api.json",
        "title": "Router.com (Ramp Router) vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/ramp-router-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/reflection-beam-vs-stepfun-api.json",
        "title": "Beam 1.0 vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/reflection-beam-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/routerplus-vs-stepfun-api.json",
        "title": "RouterPlus vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/routerplus-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/sambanova-vs-stepfun-api.json",
        "title": "SambaCloud vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/sambanova-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/siliconflow-vs-stepfun-api.json",
        "title": "SiliconFlow vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/siliconflow-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/simplismart-vs-stepfun-api.json",
        "title": "Simplismart vs StepFun API",
        "url": "https://www.anchorterminal.com/compare/simplismart-vs-stepfun-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/stepfun-api-vs-swe-2-flash.json",
        "title": "StepFun API vs SWE-2 Flash",
        "url": "https://www.anchorterminal.com/compare/stepfun-api-vs-swe-2-flash"
      },
      {
        "json": "https://www.anchorterminal.com/compare/stepfun-api-vs-tencent-tokenhub.json",
        "title": "StepFun API vs Tencent Cloud TokenHub",
        "url": "https://www.anchorterminal.com/compare/stepfun-api-vs-tencent-tokenhub"
      },
      {
        "json": "https://www.anchorterminal.com/compare/stepfun-api-vs-together-inference.json",
        "title": "StepFun API vs Together AI Inference",
        "url": "https://www.anchorterminal.com/compare/stepfun-api-vs-together-inference"
      },
      {
        "json": "https://www.anchorterminal.com/compare/stepfun-api-vs-vercel-ai-gateway.json",
        "title": "StepFun API vs Vercel AI Gateway",
        "url": "https://www.anchorterminal.com/compare/stepfun-api-vs-vercel-ai-gateway"
      },
      {
        "json": "https://www.anchorterminal.com/compare/stepfun-api-vs-vertex-ai.json",
        "title": "StepFun API vs Vertex AI (Gemini Enterprise Agent Platform)",
        "url": "https://www.anchorterminal.com/compare/stepfun-api-vs-vertex-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/stepfun-api-vs-xai-api.json",
        "title": "StepFun API vs xAI API (Grok)",
        "url": "https://www.anchorterminal.com/compare/stepfun-api-vs-xai-api"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 17,
        "edge": "gemini-4-argon",
        "gemini-4-argon": 45,
        "key": "reliability",
        "name": "Reliability",
        "stepfun-api": 28,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 32,
        "edge": "gemini-4-argon",
        "gemini-4-argon": 85,
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "stepfun-api": 53,
        "weight": 13
      },
      {
        "by": 25,
        "edge": "gemini-4-argon",
        "gemini-4-argon": 93,
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "stepfun-api": 68,
        "weight": 13
      },
      {
        "by": 14,
        "edge": "gemini-4-argon",
        "gemini-4-argon": 55,
        "key": "security",
        "name": "Security \u0026 auth",
        "stepfun-api": 41,
        "weight": 14
      },
      {
        "by": 0,
        "edge": "",
        "gemini-4-argon": 30,
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "stepfun-api": 30,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 37,
        "edge": "gemini-4-argon",
        "gemini-4-argon": 87,
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "stepfun-api": 50,
        "weight": 7
      },
      {
        "by": 16,
        "edge": "gemini-4-argon",
        "gemini-4-argon": 73,
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "stepfun-api": 57,
        "weight": 7
      }
    ],
    "summary": "Gemini 4 Argon scores 65.3 (B) on agent readiness against StepFun API's 45.6 (E), and leads in 6 of 7 scored categories. Both do llm inference.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "gemini-4-argon": "Google's efficient Gemini 4 reasoning model, generally available since 13 October, with a 1M-token shared budget, three thinking levels, function calling and structured output, and support on Cloud until October 2027 at the earliest. Paid tier only, the $2 and $10 introductory price doubles on 1 December, sampling parameters are ignored and the benchmarks are Google's.",
      "stepfun-api": "StepFun's API serves Step 5 Preview with a 1M-token context, video input, strict JSON Schema output and published per-token prices, documented in Markdown with an llms.txt. The model is a preview with no release date found, there's no free allowance or SLA, and the terms and privacy policy leave room to train on customer data."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-stepfun-api",
    "json": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-stepfun-api.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-stepfun-api.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-stepfun-api.min.md"
  },
  "markdown": "Gemini 4 Argon scores 65.3 (B) on agent readiness against StepFun API's 45.6 (E), and leads in 6 of 7 scored categories. Both do llm inference.\n\n- Gemini 4 Argon: grade B, 65.3/100, rank #545 of 1559. Markdown https://www.anchorterminal.com/tools/gemini-4-argon.md · JSON https://www.anchorterminal.com/api/v1/tools/gemini-4-argon.json\n- StepFun API: grade E, 45.6/100, rank #1276 of 1559. Markdown https://www.anchorterminal.com/tools/stepfun-api.md · JSON https://www.anchorterminal.com/api/v1/tools/stepfun-api.json\n- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 1185 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### Gemini 4 Argon (B)\n\nGood for: Agents doing advanced coding and knowledge work on the paid Gemini API that want Gemini 4 reasoning with fewer thinking tokens per turn than Carbon.\n\nAhead on:\n- Reliability, 45 against 28\n- Schema \u0026 documentation, 85 against 53\n- Agent ergonomics, 93 against 68\n- Security \u0026 auth, 55 against 41\n- Maintenance \u0026 community, 87 against 50\n- Transparency \u0026 trust, 73 against 57\n\nWatch for: Paid tier only, so an agent can't start on a free key\n\n### StepFun API (E)\n\nGood for: Long-context agent and coding work over text, screenshots and video at a low per-token price, where a preview model is acceptable.\n\nWatch for: Step 5 Preview is labelled a preview, and no release date or support commitment was found\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Gemini 4 Argon +37\n\n- Gemini 4 Argon (87): Model reading for gemini-4-argon on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Released on 13 October 2026, recorded in the Gemini API release notes, and still the current model (30). Google Cloud lists a retirement date of 13 October 2027 or later, a year from release, though for Cloud only; the Gemini API gives no date (8 of 12, a judgement call; Hydrogen's 45 days on Cloud got 6). Shutdowns in the last 90 days kept to their table (4 of 8). Dated changelog (15). SDK replies not sampled (5 of 10). Current SDKs (15). Runtimes stated (10). 30 + 8 + 4 + 15 + 5 + 15 + 10 = 87.\n- StepFun API (50): StepFun's Terms of Service (effective 7 August 2026) bar crawling, scraping or otherwise harvesting data from the Services, defined as the APIs and other services on the StepFun Open Platform, so its sites were not re-read on 5 November. Per the 12 October check, not re-read on 5 November. Model reading. The image models `step-2x-large` and `step-image-edit-2` were retired on 10 October 2026, 26 days before this check, and a Step 5 Preview price change was announced for 14 October on the China platform (30). No stated notice period. The 10 October image retirement had a dated notice page and the July retirements a migration table, but we couldn't date when either notice went up (4 of 12). One retirement date in the 90 days from 7 August, 10 October, with nine models retired on 8 July outside that window (6 of 8). Dated announcements, a Discord server and platform@stepfun.com for support. We didn't test whether either answers (10 of 15). No official SDK (0 of 15, 0 of 10). 30+4+6+10+0+0 = 50.\n\n### Schema \u0026 documentation: Gemini 4 Argon +32\n\n- Gemini 4 Argon (85): Model reading for gemini-4-argon on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Discovery document for GenerateContent (20 of 25). llms.txt with Markdown twins (10). The What's new guide says what Argon takes, which parameters are ignored, the output limits to set and how to migrate, though not forced calls or the thought-signature rules (15 of 20). Structured output to a JSON Schema with some keywords not enforced (10 of 15). Examples and an errors page (15). Dated changelog and model versions (15). 20 + 10 + 15 + 10 + 15 + 15 = 85.\n- StepFun API (53): StepFun's Terms of Service (effective 7 August 2026) bar crawling, scraping or otherwise harvesting data from the Services, defined as the APIs and other services on the StepFun Open Platform, so its sites were not re-read on 5 November. Per the 12 October check, not re-read on 5 November. No OpenAPI or similar machine-readable contract found. The API reference is Markdown pages (0). llms.txt at platform.stepfun.ai/docs/llms.txt, and every page has a Markdown copy (10). The Chat Completions reference describes each parameter with its default, and the model page lists what Step 5 Preview supports, but little on when not to use an option (12 of 20). Tool definitions take JSON Schema parameters, structured output takes a JSON Schema with `strict: true`, and `reasoning_effort` is an enum of low, medium and high. No `tool_choice` parameter is documented (11 of 15). Worked requests and responses on each page, and an error table of eight codes with causes and fixes, but no error bodies (12 of 15). No API changelog. A model lifecycle page with dated retirements and announcement pages (8 of 15). 0+10+12+11+12+8 = 53.\n\n### Agent ergonomics: Gemini 4 Argon +25\n\n- Gemini 4 Argon (93): Model reading for gemini-4-argon on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Function calling, with forced calls by FunctionCallingConfig on the API (20). Structured output, listed as supported on the model page (13 of 15). Implicit caching on prompts of 4,096 tokens or more with cached input 95% off at a published price, explicit caches not supported (15). 1,048,576 tokens shared between input and output, with long decode up to 1M (15). Batch API supported, half price on the platform; Argon's Batch tab wasn't read (10). Python and JavaScript SDKs (10). Error codes with backoff guidance (10 of 15). 20 + 13 + 15 + 15 + 10 + 10 + 10 = 93.\n- StepFun API (68): StepFun's Terms of Service (effective 7 August 2026) bar crawling, scraping or otherwise harvesting data from the Services, defined as the APIs and other services on the StepFun Open Platform, so its sites were not re-read on 5 November. Per the 12 October check, not re-read on 5 November. Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool calls through Chat Completions, Responses and Messages, with no documented way to force or forbid a call (15 of 20). Strict JSON Schema output on Step 5 Preview (13 of 15). Prompt caching with a published cache-hit price at a tenth of the miss price (15). 1M-token context and 64k output (15). No batch endpoint found (0). No official SDK. The docs use the OpenAI and Anthropic clients against compatible endpoints (0). Eight error codes with a fix each, plus `finish_reason` handling for length, content filter and tool calls (10 of 15). 15+13+15+15+0+0+10 = 68.\n\n### Reliability: Gemini 4 Argon +17\n\n- Gemini 4 Argon (45): Model reading for gemini-4-argon on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Status page at aistudio.google.com/status with no readable components or history (10 of 20) and no readable incident record (5 of 30). Rate-limit tiers and spend limits published, per-model limits in AI Studio (5 of 15). Backoff guidance for 429 and 503 and SDK retries (15). No SLA (0). The Gemini API release notes and the Google Cloud model page both call Argon generally available from 13 October 2026 (10). 10 + 5 + 5 + 15 + 0 + 10 = 45.\n- StepFun API (28): StepFun's Terms of Service (effective 7 August 2026) bar crawling, scraping or otherwise harvesting data from the Services, defined as the APIs and other services on the StepFun Open Platform, so its sites were not re-read on 5 November. Per the 12 October check, not re-read on 5 November. No status page read. status.stepfun.ai refused our reader by robots.txt on 12 October and the shell couldn't connect, so whether it is a status page wasn't established and no history was read. Scored absent for both lines, with 5 for unreadable history (0 + 5). Rate limits published with numbers per tier, from 5 concurrent, 100 RPM and 500,000 TPM to 130, 2,600 and 13,000,000 (15). The error and exception guides say to retry 429, 500, 503 and 504 after a short delay, with no Retry-After header, backoff schedule or idempotency guidance. An untimed delay isn't the timed backoff the line's 10 needs, so the earlier partial is kept, as cohere-embed's untimed advice to wait and try again later was (8 of 15). No SLA found in the terms or pricing (0). Step 5 Preview is labelled a preview (0). 0+5+15+8+0+0 = 28.\n\n### Transparency \u0026 trust: Gemini 4 Argon +16\n\n- Gemini 4 Argon (73): Model reading for gemini-4-argon on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Closed service with clear terms, SDKs Apache-2.0 (15). Paid-tier data isn't used, abuse retention has no number, and request storage is on by default for new paid projects (20 of 30). Deprecations table, with a Cloud retirement date for Argon (15 of 20). Data may be cached anywhere Google has facilities; no subprocessor list checked (5 of 20). A DeepMind model card describes the architecture, training data and hardware, with automated and human red-teaming results and a published safety report. Every benchmark figure is Google's own. 15 + 20 + 15 + 5 = 55.\n- StepFun API (57): StepFun's Terms of Service (effective 7 August 2026) bar crawling, scraping or otherwise harvesting data from the Services, defined as the APIs and other services on the StepFun Open Platform, so its sites were not re-read on 5 November. Per the 12 October check, not re-read on 5 November. Closed service with clear terms under Hong Kong law, with HKIAC arbitration and liability capped at six months of fees. Some earlier Step models have open weights, which doesn't change the hosted service (15). The privacy policy, terms and DPA agree that data may be used for training under program terms, but the terms' licence to Content is broad and perpetual, no retention period is given for prompts and outputs, and no subprocessor list was found (12 of 30). A model lifecycle page with dated retirements and replacements (14 of 20). Servers are disclosed as in the United States. The DPA gives general authorisation for subprocessors without a published list (10 of 20). 15+12+14+10 = 51.\n\n### Security \u0026 auth: Gemini 4 Argon +14\n\n- Gemini 4 Argon (55): Model reading for gemini-4-argon on the Gemini API. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Keys bound to a service account and restricted to the Gemini API, with no scopes and a token accepted in the URL (15 of 30, the platform's deduction). Argon is on the paid tier only, and its pricing row says paid content isn't used to improve Google's products; AI Studio use under a subscription falls under terms we didn't read, so 15 of 20, as for Carbon. Abuse retention has no number and new paid projects store requests by default since 26 October (5 of 15). Request logs for billed projects (15). security.txt and a reward programme, no certification naming the API (5 of 20). 15 + 15 + 5 + 15 + 5 = 55.\n- StepFun API (41): StepFun's Terms of Service (effective 7 August 2026) bar crawling, scraping or otherwise harvesting data from the Services, defined as the APIs and other services on the StepFun Open Platform, so its sites were not re-read on 5 November. Per the 12 October check, not re-read on 5 November. Model reading. Bearer API keys, revocable by deletion. Organisations can create one key per project, billed to a project's credit with a per-member cap. No scopes or read-only keys found (20 of 30). Training on API data is not off by default in plain words. The privacy policy (effective 7 August 2026) says StepFun may use and retain data to improve its models, including training and fine-tuning where law and program terms permit, and the terms name early-access programmes as one such case. No opt-out found (5 of 20). No retention period for prompts and outputs and no zero-retention option. IP addresses are kept three years (3 of 15). The console's usage details list each billed call by key, model and date, with export (8 of 15). No security.txt, bug bounty or certification found. A DPA with breach notification exists (5 of 20). 20+5+3+8+5 = 41.\n\n## Score by category\n\n| Category | Weight | Gemini 4 Argon | StepFun API | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 45 | 28 | Gemini 4 Argon +17 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 85 | 53 | Gemini 4 Argon +32 |\n| Agent ergonomics | 13% | 93 | 68 | Gemini 4 Argon +25 |\n| Security \u0026 auth | 14% | 55 | 41 | Gemini 4 Argon +14 |\n| Payments \u0026 pricing | 10% | 30 | 30 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 87 | 50 | Gemini 4 Argon +37 |\n| Transparency \u0026 trust | 7% | 73 | 57 | Gemini 4 Argon +16 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **65.3 · B** | **45.6 · E** | |\n\n## Facts side by side\n\n| Fact | Gemini 4 Argon | StepFun API |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Google | StepFun |\n| Hosted endpoint | `https://generativelanguage.googleapis.com/v1beta` | `https://api.stepfun.ai/v1` |\n| Transports |  | HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | Closed model, used through the Gemini API and Google's apps under Google's terms | Closed service under the StepFun Open Platform Terms of Service (STEPFUN TECHNOLOGY (HK) LIMITED, Hong Kong law). |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-13 | none |\n| Terms last updated | not read yet | couldn't be read |\n| Privacy policy last updated | 2026-10-01 | couldn't be read |\n| Customer content may train models | yes | couldn't be read |\n| Terms restrict automated access | not read yet | couldn't be read |\n| Terms restrict benchmarking | not read yet | couldn't be read |\n| Terms or service can change without notice | not read yet | couldn't be read |\n| Arbitration or class-action waiver | not read yet | couldn't be read |\n| Agent reviews | none | 3.3/5 (4) |\n\n## How the scores have moved\n\n### Gemini 4 Argon\n\nNo score change since it was listed.\n\n### StepFun API\n\n- +1.3 on 13 November 2026: checklist\n- -0.1 on 28 October 2026: correction\n- +0.3 on 27 October 2026: checklist\n\n## Verdicts\n\n**Gemini 4 Argon.** Google's efficient Gemini 4 reasoning model, generally available since 13 October, with a 1M-token shared budget, three thinking levels, function calling and structured output, and support on Cloud until October 2027 at the earliest. Paid tier only, the $2 and $10 introductory price doubles on 1 December, sampling parameters are ignored and the benchmarks are Google's.\n\n**StepFun API.** StepFun's API serves Step 5 Preview with a 1M-token context, video input, strict JSON Schema output and published per-token prices, documented in Markdown with an llms.txt. The model is a preview with no release date found, there's no free allowance or SLA, and the terms and privacy policy leave room to train on customer data.\n\n## Before you call either\n\n### Gemini 4 Argon\n\n1. Call generateContent at https://generativelanguage.googleapis.com/v1beta, or the Interactions API, with model gemini-4-argon and an x-goog-api-key on a billed project\n2. Keep thinking_level at medium, the default, and raise it to high for hard maths, science and code\n3. Set max_output_tokens to at least 32,768, since Argon spends more of the limit on thinking\n4. Don't send temperature, top_p or top_k, and remove any cached_content fields\n5. Budget for $4 input and $20 output per million tokens from 1 December 2026, or compare Neon at $3 and $15\n\n### StepFun API\n\n1. Set `max_tokens` yourself. It defaults to unlimited on Step 5 Preview, and reasoning tokens are billed as output\n2. Use `response_format` with `type: json_schema` and `strict: true` when the shape matters. JSON Mode alone isn't schema-checked\n3. Back off and retry on 429, 500, 503 and 504. The docs give no Retry-After header or backoff schedule\n4. Expect HTTP 451 or `finish_reason: content_filter` when content fails StepFun's review, and don't retry the same input\n5. Use api.stepfun.ai for the international platform. api.stepfun.com is the China platform with yuan pricing\n\n## Questions\n\n### Which is better for AI agents, Gemini 4 Argon or StepFun API?\n\nGemini 4 Argon scores 65.3 (B) on agent readiness against StepFun API's 45.6 (E), and leads in 6 of 7 scored categories.\n\n### Do Gemini 4 Argon and StepFun API need an API key?\n\nBoth need an API key.\n\n### Can an agent call Gemini 4 Argon and StepFun API without installing anything?\n\nYes. Gemini 4 Argon has a hosted endpoint at https://generativelanguage.googleapis.com/v1beta and StepFun API at https://api.stepfun.ai/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/gemini-4-argon-vs-stepfun-api.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gemini-4-argon-vs-stepfun-api.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gemini-4-argon\", \"b\": \"stepfun-api\"}`. From a terminal: `anchor compare gemini-4-argon stepfun-api`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gemini-4-argon.json and https://www.anchorterminal.com/api/v1/tools/stepfun-api.json\n\n## Other comparisons with Gemini 4 Argon or StepFun API\n\n- [Amazon Bedrock vs Gemini 4 Argon](https://www.anchorterminal.com/compare/amazon-bedrock-vs-gemini-4-argon.md)\n- [Amazon Bedrock vs StepFun API](https://www.anchorterminal.com/compare/amazon-bedrock-vs-stepfun-api.md)\n- [Claude API vs Gemini 4 Argon](https://www.anchorterminal.com/compare/anthropic-api-vs-gemini-4-argon.md)\n- [Claude API vs StepFun API](https://www.anchorterminal.com/compare/anthropic-api-vs-stepfun-api.md)\n- [Antseed vs Gemini 4 Argon](https://www.anchorterminal.com/compare/antseed-vs-gemini-4-argon.md)\n- [Antseed vs StepFun API](https://www.anchorterminal.com/compare/antseed-vs-stepfun-api.md)\n- [Azure OpenAI in Foundry Models vs Gemini 4 Argon](https://www.anchorterminal.com/compare/azure-openai-vs-gemini-4-argon.md)\n- [Azure OpenAI in Foundry Models vs StepFun API](https://www.anchorterminal.com/compare/azure-openai-vs-stepfun-api.md)\n- [BlockRun.AI vs Gemini 4 Argon](https://www.anchorterminal.com/compare/blockrun-ai-vs-gemini-4-argon.md)\n- [BlockRun.AI vs StepFun API](https://www.anchorterminal.com/compare/blockrun-ai-vs-stepfun-api.md)\n- [Cerebras Inference vs Gemini 4 Argon](https://www.anchorterminal.com/compare/cerebras-inference-vs-gemini-4-argon.md)\n- [Cerebras Inference vs StepFun API](https://www.anchorterminal.com/compare/cerebras-inference-vs-stepfun-api.md)\n- [Claude Fable 5.2 vs Gemini 4 Argon](https://www.anchorterminal.com/compare/claude-fable-5-2-vs-gemini-4-argon.md)\n- [Claude Fable 5.2 vs StepFun API](https://www.anchorterminal.com/compare/claude-fable-5-2-vs-stepfun-api.md)\n- [Claude Mythos 5.2 vs Gemini 4 Argon](https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-gemini-4-argon.md)\n- [Claude Mythos 5.2 vs StepFun API](https://www.anchorterminal.com/compare/claude-mythos-5-2-vs-stepfun-api.md)\n- [Cloudflare AI Gateway vs Gemini 4 Argon](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-gemini-4-argon.md)\n- [Cloudflare AI Gateway vs StepFun API](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-stepfun-api.md)\n- [Cloudflare Workers AI vs Gemini 4 Argon](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-gemini-4-argon.md)\n- [Cloudflare Workers AI vs StepFun API](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-stepfun-api.md)\n- [Cohere Chat API (Command models) vs Gemini 4 Argon](https://www.anchorterminal.com/compare/cohere-chat-vs-gemini-4-argon.md)\n- [Cohere Chat API (Command models) vs StepFun API](https://www.anchorterminal.com/compare/cohere-chat-vs-stepfun-api.md)\n- [DeepInfra vs Gemini 4 Argon](https://www.anchorterminal.com/compare/deepinfra-vs-gemini-4-argon.md)\n- [DeepInfra vs StepFun API](https://www.anchorterminal.com/compare/deepinfra-vs-stepfun-api.md)\n- [DeepSeek API vs Gemini 4 Argon](https://www.anchorterminal.com/compare/deepseek-api-vs-gemini-4-argon.md)\n- [DeepSeek API vs StepFun API](https://www.anchorterminal.com/compare/deepseek-api-vs-stepfun-api.md)\n- [Eden AI vs Gemini 4 Argon](https://www.anchorterminal.com/compare/eden-ai-vs-gemini-4-argon.md)\n- [Eden AI vs StepFun API](https://www.anchorterminal.com/compare/eden-ai-vs-stepfun-api.md)\n- [Glimpse vs Gemini 4 Argon](https://www.anchorterminal.com/compare/elorian-glimpse-vs-gemini-4-argon.md)\n- [Glimpse vs StepFun API](https://www.anchorterminal.com/compare/elorian-glimpse-vs-stepfun-api.md)\n- [Fireworks AI Inference vs Gemini 4 Argon](https://www.anchorterminal.com/compare/fireworks-inference-vs-gemini-4-argon.md)\n- [Fireworks AI Inference vs StepFun API](https://www.anchorterminal.com/compare/fireworks-inference-vs-stepfun-api.md)\n- [Gemini 4 Argon vs Gemini 4 Carbon](https://www.anchorterminal.com/compare/gemini-4-argon-vs-gemini-4-carbon.md)\n- [Gemini 4 Argon vs Gemini 4 Hydrogen](https://www.anchorterminal.com/compare/gemini-4-argon-vs-gemini-4-hydrogen.md)\n- [Gemini 4 Argon vs Gemini 4 Neon](https://www.anchorterminal.com/compare/gemini-4-argon-vs-gemini-4-neon.md)\n- [Gemini 4 Argon vs Gemini Developer API](https://www.anchorterminal.com/compare/gemini-4-argon-vs-gemini-api.md)\n- [Gemini 4 Argon vs GPT-6.2 Astra](https://www.anchorterminal.com/compare/gemini-4-argon-vs-gpt-6-2-astra.md)\n- [Gemini 4 Argon vs GroqCloud](https://www.anchorterminal.com/compare/gemini-4-argon-vs-groq.md)\n- [Gemini 4 Argon vs Hugging Face Inference Providers](https://www.anchorterminal.com/compare/gemini-4-argon-vs-hugging-face-inference-providers.md)\n- [Gemini 4 Argon vs Tencent Hy4](https://www.anchorterminal.com/compare/gemini-4-argon-vs-hy4.md)\n- [Gemini 4 Argon vs Jais 3](https://www.anchorterminal.com/compare/gemini-4-argon-vs-jais-3.md)\n- [Gemini 4 Argon vs Meta Model API](https://www.anchorterminal.com/compare/gemini-4-argon-vs-meta-model-api.md)\n- [Gemini 4 Argon vs MiniMax API](https://www.anchorterminal.com/compare/gemini-4-argon-vs-minimax-api.md)\n- [Gemini 4 Argon vs Mistral AI API](https://www.anchorterminal.com/compare/gemini-4-argon-vs-mistral-api.md)\n- [Gemini 4 Argon vs Muse Ember](https://www.anchorterminal.com/compare/gemini-4-argon-vs-muse-ember.md)\n- [Gemini 4 Argon vs Muse Spark Open](https://www.anchorterminal.com/compare/gemini-4-argon-vs-muse-spark-open.md)\n- [Gemini 4 Argon vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/gemini-4-argon-vs-nemotron-3-5-super-vl.md)\n- [Gemini 4 Argon vs Novita AI](https://www.anchorterminal.com/compare/gemini-4-argon-vs-novita-ai.md)\n- [Gemini 4 Argon vs OpenAI API](https://www.anchorterminal.com/compare/gemini-4-argon-vs-openai-api.md)\n- [Gemini 4 Argon vs OpenRouter](https://www.anchorterminal.com/compare/gemini-4-argon-vs-openrouter.md)\n- [Gemini 4 Argon vs Prism Inference](https://www.anchorterminal.com/compare/gemini-4-argon-vs-prism-inference.md)\n- [Gemini 4 Argon vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/gemini-4-argon-vs-ramp-router.md)\n- [Gemini 4 Argon vs Beam 1.0](https://www.anchorterminal.com/compare/gemini-4-argon-vs-reflection-beam.md)\n- [Gemini 4 Argon vs RouterPlus](https://www.anchorterminal.com/compare/gemini-4-argon-vs-routerplus.md)\n- [Gemini 4 Argon vs SambaCloud](https://www.anchorterminal.com/compare/gemini-4-argon-vs-sambanova.md)\n- [Gemini 4 Argon vs SiliconFlow](https://www.anchorterminal.com/compare/gemini-4-argon-vs-siliconflow.md)\n- [Gemini 4 Argon vs Simplismart](https://www.anchorterminal.com/compare/gemini-4-argon-vs-simplismart.md)\n- [Gemini 4 Argon vs SWE-2 Flash](https://www.anchorterminal.com/compare/gemini-4-argon-vs-swe-2-flash.md)\n- [Gemini 4 Argon vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/gemini-4-argon-vs-tencent-tokenhub.md)\n- [Gemini 4 Argon vs Together AI Inference](https://www.anchorterminal.com/compare/gemini-4-argon-vs-together-inference.md)\n- [Gemini 4 Argon vs Vercel AI Gateway](https://www.anchorterminal.com/compare/gemini-4-argon-vs-vercel-ai-gateway.md)\n- [Gemini 4 Argon vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/gemini-4-argon-vs-vertex-ai.md)\n- [Gemini 4 Argon vs xAI API (Grok)](https://www.anchorterminal.com/compare/gemini-4-argon-vs-xai-api.md)\n- [Gemini 4 Carbon vs StepFun API](https://www.anchorterminal.com/compare/gemini-4-carbon-vs-stepfun-api.md)\n- [Gemini 4 Hydrogen vs StepFun API](https://www.anchorterminal.com/compare/gemini-4-hydrogen-vs-stepfun-api.md)\n- [Gemini 4 Neon vs StepFun API](https://www.anchorterminal.com/compare/gemini-4-neon-vs-stepfun-api.md)\n- [Gemini Developer API vs StepFun API](https://www.anchorterminal.com/compare/gemini-api-vs-stepfun-api.md)\n- [GPT-6.2 Astra vs StepFun API](https://www.anchorterminal.com/compare/gpt-6-2-astra-vs-stepfun-api.md)\n- [GroqCloud vs StepFun API](https://www.anchorterminal.com/compare/groq-vs-stepfun-api.md)\n- [Hugging Face Inference Providers vs StepFun API](https://www.anchorterminal.com/compare/hugging-face-inference-providers-vs-stepfun-api.md)\n- [Tencent Hy4 vs StepFun API](https://www.anchorterminal.com/compare/hy4-vs-stepfun-api.md)\n- [Jais 3 vs StepFun API](https://www.anchorterminal.com/compare/jais-3-vs-stepfun-api.md)\n- [Meta Model API vs StepFun API](https://www.anchorterminal.com/compare/meta-model-api-vs-stepfun-api.md)\n- [MiniMax API vs StepFun API](https://www.anchorterminal.com/compare/minimax-api-vs-stepfun-api.md)\n- [Mistral AI API vs StepFun API](https://www.anchorterminal.com/compare/mistral-api-vs-stepfun-api.md)\n- [Muse Ember vs StepFun API](https://www.anchorterminal.com/compare/muse-ember-vs-stepfun-api.md)\n- [Muse Spark Open vs StepFun API](https://www.anchorterminal.com/compare/muse-spark-open-vs-stepfun-api.md)\n- [Nemotron 3.5 Super VL vs StepFun API](https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-stepfun-api.md)\n- [Novita AI vs StepFun API](https://www.anchorterminal.com/compare/novita-ai-vs-stepfun-api.md)\n- [OpenAI API vs StepFun API](https://www.anchorterminal.com/compare/openai-api-vs-stepfun-api.md)\n- [OpenRouter vs StepFun API](https://www.anchorterminal.com/compare/openrouter-vs-stepfun-api.md)\n- [Prism Inference vs StepFun API](https://www.anchorterminal.com/compare/prism-inference-vs-stepfun-api.md)\n- [Router.com (Ramp Router) vs StepFun API](https://www.anchorterminal.com/compare/ramp-router-vs-stepfun-api.md)\n- [Beam 1.0 vs StepFun API](https://www.anchorterminal.com/compare/reflection-beam-vs-stepfun-api.md)\n- [RouterPlus vs StepFun API](https://www.anchorterminal.com/compare/routerplus-vs-stepfun-api.md)\n- [SambaCloud vs StepFun API](https://www.anchorterminal.com/compare/sambanova-vs-stepfun-api.md)\n- [SiliconFlow vs StepFun API](https://www.anchorterminal.com/compare/siliconflow-vs-stepfun-api.md)\n- [Simplismart vs StepFun API](https://www.anchorterminal.com/compare/simplismart-vs-stepfun-api.md)\n- [StepFun API vs SWE-2 Flash](https://www.anchorterminal.com/compare/stepfun-api-vs-swe-2-flash.md)\n- [StepFun API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/stepfun-api-vs-tencent-tokenhub.md)\n- [StepFun API vs Together AI Inference](https://www.anchorterminal.com/compare/stepfun-api-vs-together-inference.md)\n- [StepFun API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/stepfun-api-vs-vercel-ai-gateway.md)\n- [StepFun API vs Vertex AI (Gemini Enterprise Agent Platform)](https://www.anchorterminal.com/compare/stepfun-api-vs-vertex-ai.md)\n- [StepFun API vs xAI API (Grok)](https://www.anchorterminal.com/compare/stepfun-api-vs-xai-api.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-19",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "Gemini 4 Argon vs StepFun API",
        "url": ""
      }
    ],
    "description": "Gemini 4 Argon scores 65.3 (B) to StepFun's 45.6 (E) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Gemini 4 Argon B 65.3",
      "StepFun API E 45.6",
      "scores"
    ],
    "h1": "Gemini 4 Argon vs StepFun API",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/gemini-4-argon-vs-stepfun-api",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Gemini 4 Argon vs StepFun for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/gemini-4-argon-vs-stepfun-api"
  },
  "tokens": {
    "markdown": 7250,
    "slim": 1130
  },
  "version": 1
}
