{
  "data": {
    "a": {
      "slug": "antseed",
      "name": "Antseed",
      "vendor": "Antseed Foundation",
      "vendorUrl": "https://antseed.com",
      "kind": "router",
      "category": "inference",
      "summary": "Antseed is an open-source peer-to-peer network for buying and selling AI inference. A buyer runs a local proxy with OpenAI and Anthropic format endpoints, which routes each request to an independent seller and pays in USDC on Base.",
      "url": "https://www.anchorterminal.com/tools/antseed",
      "markdownUrl": "https://www.anchorterminal.com/tools/antseed.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/antseed.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/antseed.json",
      "repo": "https://github.com/Antseed/antseed",
      "license": "GPL-3.0 (LICENSE in the repository). The @antseed/cli manifest on npm carries no licence field",
      "transports": [
        "http"
      ],
      "packages": [
        {
          "registry": "npm",
          "name": "@antseed/cli"
        }
      ],
      "auth": "none",
      "authNotes": "No account and no API key. The local proxy at 127.0.0.1:8377 doesn't check a key, so clients that need one send a placeholder such as `antseed-p2p`. Identity is a secp256k1 key the CLI creates on first run. Its EVM address is the peer id and the paying wallet. A public tunnel or the gateway (`antseed gateway`, `antseed tunnel start`) needs a generated `antseed_...` bearer key, with optional spend limits and expiry per key.",
      "pricing": "usage",
      "pricingNotes": "Sellers set their own prices per 1M input, cached-input and output tokens, published without login at https://network.antseed.com/stats. Buyers pre-deposit USDC on Base and pay per request. Some models are free, with nine free ids in the 8 October 2026 snapshot. The FAQ sets network fees at 4 per cent, and a gasless deposit costs a fixed $0.05 relay fee. The software is free.",
      "priceSummary": "4% fee",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "Inference isn't paid by x402. Sellers answer HTTP 402 and the buyer signs Antseed's own EIP-712 ReserveAuth and SpendingAuth against an on-chain USDC channel (https://antseed.com/blog/the-402-flow/). x402 v2 appears only on `POST /v1/key/topup` of a gateway the owner runs, off until enabled per key (CHANGELOG.md, checked 2026-10-08).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 106,
        "npmWeekly": 1823,
        "pypiWeekly": null,
        "asOf": "2026-10-08"
      },
      "docsUrl": "https://antseed.com/docs/",
      "llmsTxt": "https://antseed.com/llms.txt",
      "capabilities": [
        "inference.router",
        "inference.llm"
      ],
      "tags": [
        "open-source",
        "local",
        "p2p",
        "usdc",
        "base",
        "no-signup",
        "no-card",
        "openai-compatible",
        "anthropic-compatible",
        "llms-txt",
        "cli",
        "desktop",
        "pre-1.0"
      ],
      "lastRelease": "2026-10-08",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 55.1,
        "grade": "C",
        "agentReady": false,
        "rank": 459,
        "ranked": true,
        "rankOf": 629,
        "categoryRank": 9,
        "methodology": "0.4",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 56,
          "maintenance": 79,
          "payments": 70,
          "reliability": 62,
          "schema": 55,
          "security": 45,
          "transparency": 59
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-08"
        },
        "negative": -4,
        "negativeNotes": [
          "2026-10-08. The buyer proxy forwards a client's `Authorization`, `x-api-key` and cookie headers to the seller it routes to, confirmed in apps/cli/src/proxy/buyer-proxy.ts at commit 10a1f6b. The repository's own review of 8 March 2026 lists it as VULN-002, and issue #1104 (4 October 2026) is open. Clients started through `antseed claude` or `antseed codex` send a placeholder, so the deduction is 4 of a possible 15. https://github.com/Antseed/antseed/issues/1104"
        ],
        "verdict": "A buyer needs no account. The CLI creates a wallet key, free models answer at once and paid ones draw on deposited USDC, with seller, tokens and cost returned in response headers. Sellers are unvetted and can read prompts unless TEE-verified, the proxy forwards a client's own credential headers to them, and every package is pre-1.0.",
        "bestFor": "Agents and coding tools that want pay-per-request inference with no account, and owners comfortable holding USDC on Base.",
        "strengths": [
          "No sign-up. `npm install -g @antseed/cli` and `antseed buyer start` give a local endpoint at http://localhost:8377, and nine model ids were free in the 8 October snapshot",
          "One proxy accepts Anthropic Messages, OpenAI Chat Completions and OpenAI Responses requests and translates between them when the seller speaks another format",
          "Seller prices per 1M tokens are public JSON at https://network.antseed.com/stats with no login, and `antseed network browse --json` reads them live",
          "Non-streaming responses carry `x-antseed-peer-id`, token counts and `x-antseed-estimated-cost-usd`, and `antseed buyer metering` gives totals per channel",
          "GPL-3.0 source with CI passing on main on 8 October 2026 and 28 tagged releases since 19 August 2026"
        ],
        "weaknesses": [
          "The buyer proxy copies a client's `Authorization` and `x-api-key` headers to the seller. The repository's March 2026 review flagged it and issue #1104 is open",
          "Sellers are independent and unvetted. The FAQ says a standard seller can read the prompt it serves, and each sets its own data practices",
          "Pre-1.0 everywhere. The CLI is 0.1.173, the release tag is v0.2.51, and CHANGELOG.md keeps everything since August under one Unreleased heading",
          "No OpenAPI document, security.txt, SECURITY.md, published advisory, bug bounty or contract audit report was found",
          "The buyer key is also the wallet, and the CLI stores it in plain text at ~/.antseed/identity.key unless `ANTSEED_IDENTITY_HEX` is set"
        ],
        "agentNotes": [
          "Send a placeholder key such as `antseed-p2p`. The proxy forwards whatever `Authorization` or `x-api-key` header the client sends to the seller",
          "Call `GET /v1/models` first and request a concrete id. The `antseed` alias works only when the desktop app has a model selected",
          "Handle 402 `insufficient_deposits` by reading `suggestedAmount`, then fund the address from `antseed buyer deposit` with USDC on Base",
          "Pass `--verifiers antseed-verifier --require-verifier` to `antseed buyer start` when prompts are private, so only TEE-verified sellers are routed",
          "Read `x-antseed-peer-id` and `x-antseed-estimated-cost-usd` on each response, and pin a seller with `\u003cpeerId\u003e@\u003cmodel\u003e` when the same one must answer"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "C",
            "methodology": "0.4",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 55.1
          }
        ],
        "editorialScores": {
          "ergonomics": 56,
          "maintenance": 79,
          "payments": 70,
          "reliability": 62,
          "schema": 55,
          "security": 45,
          "transparency": 66
        },
        "provenanceScore": 52
      },
      "connect": {
        "install": "npm install -g @antseed/cli \u0026\u0026 antseed buyer start",
        "http": "curl http://localhost:8377/v1/chat/completions -H 'content-type: application/json' -d '{\"model\": \"deepseek-v4-flash\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}]}'"
      },
      "letme": {
        "capability": "https://letme.dev/inference.router",
        "tool": "https://letme.dev/antseed"
      },
      "area": "models",
      "unitPrices": [
        {
          "item": "Network fee",
          "unit": "pct",
          "usd": 4,
          "note": "Per the FAQ. Model prices are set by each seller"
        },
        {
          "item": "Gasless deposit relay",
          "unit": "tx",
          "usd": 0.05,
          "note": "Fixed fee per sweep on Base mainnet"
        }
      ],
      "provenance": {
        "legalEntity": "Antseed Foundation",
        "domain": "antseed.com",
        "domainRegistered": "2026-02-23",
        "endpointOnVendorDomain": null,
        "terms": "https://antseed.com/terms-of-service/",
        "privacy": "",
        "statusPage": "",
        "changelog": "https://github.com/Antseed/antseed/blob/main/CHANGELOG.md",
        "securityTxt": "none",
        "checked": "2026-10-08",
        "notes": [
          "The site footer reads © 2026 Antseed Foundation. The foundation post of 17 July 2026 calls it a non-profit and gives no jurisdiction or registration number.",
          "The terms (last updated 15 May 2026) say the protocol is not a company and that supporting entities don't operate or control the network. Their contact section points to the repository's issues.",
          "https://antseed.com/privacy/ is a product page about anonymity, not a privacy policy. Section 16 of the terms covers data, and docs/telemetry.md in the repository covers the desktop app.",
          "The endpoint an agent calls is on the owner's machine. The price snapshot is at network.antseed.com, and https://antseed.com/network shows live network data with no incident history.",
          "antseed.com/.well-known/security.txt and /security.txt both return 404, and the repository has no SECURITY.md.",
          "RDAP gives 2026-02-23 as the registration date for antseed.com. @antseed/cli was first published to npm on 2026-02-24."
        ],
        "score": 52
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/antseed.json",
      "live": {
        "slug": "antseed",
        "versions": [
          {
            "registry": "github",
            "name": "Antseed/antseed",
            "version": "v0.2.51",
            "released": "2026-10-08",
            "seenAt": "2026-10-08T15:58:43.119163816Z"
          },
          {
            "registry": "npm",
            "name": "@antseed/cli",
            "version": "0.1.173",
            "seenAt": "2026-10-08T15:58:39.375087215Z"
          }
        ],
        "githubStars": 109,
        "npmWeekly": 1823,
        "securityTxt": {
          "url": "https://antseed.com/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-10-08T15:38:32.487292893Z"
        },
        "pages": [
          {
            "url": "https://raw.githubusercontent.com/Antseed/antseed/main/CHANGELOG.md",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-10-08T18:23:37.539347164Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "7beb610d0657"
          },
          {
            "url": "https://antseed.com/terms-of-service/",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-10-08T18:15:12.029803409Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "a494a37d507a"
          }
        ],
        "updatedAt": "2026-10-08T18:23:37.539347164Z"
      }
    },
    "answer": "BlockRun.AI scores 72.4 (BB) on agent readiness against Antseed's 55.1 (C), and leads in 6 of 7 scored categories. Antseed leads on reliability.",
    "b": {
      "slug": "blockrun-ai",
      "name": "BlockRun.AI",
      "vendor": "BlockRun, Inc.",
      "vendorUrl": "https://blockrun.ai",
      "kind": "mcp",
      "category": "inference",
      "summary": "Model and API gateway with an OpenAI-compatible interface, MCP support and per-request stablecoin payments through x402.",
      "url": "https://www.anchorterminal.com/tools/blockrun-ai",
      "markdownUrl": "https://www.anchorterminal.com/tools/blockrun-ai.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/blockrun-ai.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/blockrun-ai.json",
      "repo": "https://github.com/BlockRunAI/blockrun-llm",
      "license": "MIT",
      "transports": [
        "stdio"
      ],
      "packages": [
        {
          "registry": "pypi",
          "name": "blockrun-llm"
        },
        {
          "registry": "npm",
          "name": "@blockrun/llm"
        },
        {
          "registry": "npm",
          "name": "@blockrun/mcp"
        }
      ],
      "auth": "mixed",
      "authNotes": "Either an API key backed by prepaid card credit (user.blockrun.ai) or a non-custodial wallet signing x402 USDC payments (Base mainnet at https://blockrun.ai/api, Solana at https://sol.blockrun.ai/api, testnets available).",
      "pricing": "usage",
      "pricingNotes": "Per-token LLM pricing by model ($0.20-$30 per 1M input, $0.40-$180 per 1M output per SDK README; site examples $10/$50 for Claude Fable 5.1, $4/$20 for GPT-5.6 Sol per 1M tokens); per-token chat models billed at zero platform margin since 2026-08-08, plus a flat $0.001 network fee per wallet call on Base since 2026-07-29 (the account rail and the Solana gateway charge no fee); images $0.015-$0.10; web search $0.011/search; some data endpoints $0.002-$0.0085 per call; six or seven free models (the vendor's repository says 6, its llms.txt names 7, after four NVIDIA free models retired on 2026-08-30); failed calls (400, 402, 429, 5xx) aren't charged; x402 in USDC on Base or Solana (https://blockrun.ai/docs/resources/changelog; https://blockrun.ai/docs/api-reference/errors; https://github.com/BlockRunAI/blockrun-mcp).",
      "priceSummary": "Pay per use",
      "where": "local",
      "x402": {
        "level": "yes",
        "evidence": "Core business model: x402 v2 micropayments in USDC (ERC-20 on Base mainnet, SPL on Solana) per request; the '~$0.002/call' figure could NOT be verified for LLM inference, which is per-token; $0.002 appears only for trading-market/stock data endpoints (https://github.com/BlockRunAI/blockrun-llm; https://github.com/BlockRunAI/awesome-blockrun)",
        "endpoints": [
          {
            "url": "https://blockrun.ai/api/v1/chat/completions",
            "priceUsd": null,
            "network": "eip155:8453"
          }
        ]
      },
      "toolCount": 19,
      "popularity": {
        "githubStars": 5,
        "npmWeekly": null,
        "pypiWeekly": 679,
        "asOf": "2026-09-26"
      },
      "docsUrl": "https://github.com/BlockRunAI/awesome-blockrun",
      "llmsTxt": "https://blockrun.ai/llms.txt",
      "openapi": "https://blockrun.ai/api/openapi",
      "capabilities": [
        "inference.llm",
        "web.search",
        "market.crypto"
      ],
      "tags": [
        "hosted",
        "x402",
        "inference",
        "openai-compatible"
      ],
      "lastRelease": "2026-09-29",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 72.4,
        "grade": "BB",
        "agentReady": true,
        "rank": 86,
        "ranked": true,
        "rankOf": 629,
        "categoryRank": 4,
        "methodology": "0.4",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 70,
          "maintenance": 85,
          "payments": 100,
          "reliability": 55,
          "schema": 75,
          "security": 70,
          "transparency": 65
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-01"
        },
        "negative": 0,
        "verdict": "x402 v2 on its own gateway, USDC on Base and Solana, with Base Sepolia for testing. The status page shows live checks only and keeps no incident history.",
        "bestFor": "Agents that must start and pay with no human sign-up, and builders testing x402 against a real inference gateway.",
        "strengths": [
          "x402 v2 on its own gateway, USDC on Base and Solana, with Base Sepolia for testing",
          "Rate limits and 429 headers published, and 400, 402, 429 and 5xx responses aren't charged",
          "Privacy policy says prompts aren't stored past the request and aren't used for training, with request metadata kept 30 days",
          "The MCP server marks every one of its 19 tools with readOnlyHint or destructiveHint, and trades need `confirm:true`",
          "Dated gateway changelog with entries most weeks, last on 2026-09-29"
        ],
        "weaknesses": [
          "The status page shows live checks only and keeps no incident history",
          "The terms say 'We do not commit to any particular uptime', and there's no SLA",
          "Models are removed on the day, with no notice period, and the terms let providers withdraw a model at any time",
          "No subprocessor list or data locations, and the privacy footer names a different entity from the terms",
          "The wallet key controls the whole balance and sits in a local file or environment variable"
        ],
        "agentNotes": [
          "Fund a dedicated wallet with a small USDC balance. The balance is the spending cap",
          "Use `blockrun_wallet` delegate with `agent_limit` before handing a sub-agent the server",
          "On a 429, wait `Retry-After` and read `X-RateLimit-Source` to fail over to the same tier on another provider",
          "Call `blockrun_models` before hard-coding a model name, since models are removed without notice",
          "Use `mode:\"free\"` for drafts and classification, paid models for generation"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 2,
        "avgRating": 3.5,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "BB",
            "methodology": "0.4",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 72.4
          }
        ],
        "editorialScores": {
          "ergonomics": 70,
          "maintenance": 85,
          "payments": 100,
          "reliability": 55,
          "schema": 75,
          "security": 70,
          "transparency": 50
        },
        "provenanceScore": 80
      },
      "connect": {
        "claudeCode": "claude mcp add blockrun -- npx -y @blockrun/mcp",
        "config": {
          "mcpServers": {
            "blockrun": {
              "args": [
                "-y",
                "@blockrun/mcp"
              ],
              "command": "npx",
              "env": {
                "BLOCKRUN_WALLET_KEY": "${BLOCKRUN_WALLET_KEY}"
              }
            }
          }
        },
        "x402": "curl -s -i https://blockrun.ai/api/v1/chat/completions -H 'content-type: application/json' -d '{\"model\":\"\u003cmodel\u003e\",\"messages\":[{\"role\":\"user\",\"content\":\"hi\"}]}'\n# 402 Payment Required -\u003e PAYMENT-REQUIRED header -\u003e retry with PAYMENT-SIGNATURE"
      },
      "letme": {
        "capability": "https://letme.dev/inference.llm",
        "tool": "https://letme.dev/blockrun-ai"
      },
      "area": "models",
      "provenance": {
        "legalEntity": "BlockRun, Inc.",
        "domain": "blockrun.ai",
        "domainRegistered": "2025-10-06",
        "domainNote": "The terms (updated 2026-09-02) name BlockRun, Inc., a Delaware corporation headquartered in San Francisco, while the privacy policy footer says BlockRun Labs, Inc. No founders or street address are published. The domain is under a year old. The status page is self-hosted and keeps no incident history.",
        "endpointOnVendorDomain": null,
        "terms": "https://blockrun.ai/terms",
        "privacy": "https://blockrun.ai/privacy",
        "statusPage": "https://blockrun.ai/status",
        "changelog": "https://blockrun.ai/docs/resources/changelog",
        "securityTxt": "valid",
        "checked": "2026-10-02",
        "score": 80
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/blockrun-ai.json",
      "live": {
        "slug": "blockrun-ai",
        "vendorStatus": {
          "page": "https://blockrun.ai/status",
          "indicator": "unknown",
          "summary": "no machine-readable status found",
          "checkedAt": "2026-10-08T17:50:25.834755093Z"
        },
        "versions": [
          {
            "registry": "github",
            "name": "BlockRunAI/blockrun-llm",
            "version": "v1.17.1",
            "released": "2026-09-30",
            "seenAt": "2026-10-08T16:03:03.38534707Z"
          },
          {
            "registry": "npm",
            "name": "@blockrun/llm",
            "version": "3.20.1",
            "seenAt": "2026-10-08T16:03:00.626430849Z"
          },
          {
            "registry": "npm",
            "name": "@blockrun/mcp",
            "version": "0.54.2",
            "seenAt": "2026-10-08T16:03:03.163417147Z"
          },
          {
            "registry": "pypi",
            "name": "blockrun-llm",
            "version": "1.18.1",
            "released": "2026-10-02",
            "seenAt": "2026-10-08T16:02:56.881672754Z"
          }
        ],
        "githubStars": 5,
        "npmWeekly": 3038,
        "pypiWeekly": 613,
        "securityTxt": {
          "url": "https://blockrun.ai/.well-known/security.txt",
          "state": "valid",
          "expires": "2027-10-08T15:38:59.798Z",
          "checkedAt": "2026-10-08T15:38:59.626671491Z"
        },
        "llmsTxt": {
          "url": "https://blockrun.ai/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-10-08T14:00:08.691101317Z"
        },
        "domain": {
          "domain": "blockrun.ai",
          "registered": "2025-10-06",
          "source": "https://rdap.identitydigital.services/rdap/domain/blockrun.ai",
          "checkedAt": "2026-10-04T13:10:06.086473367Z"
        },
        "pages": [
          {
            "url": "https://blockrun.ai/changelog",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-10-01T13:11:21.906696649Z",
            "changedAt": "2026-09-30T13:09:43.712367412Z",
            "fingerprint": "658ca7fbc8ce"
          },
          {
            "url": "https://blockrun.ai/docs/resources/changelog",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-10-08T18:15:47.647222361Z",
            "changedAt": "2026-10-07T18:02:55.765897221Z",
            "fingerprint": "c92dc1246502"
          },
          {
            "url": "https://blockrun.ai/privacy",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-10-08T18:15:50.108128149Z",
            "changedAt": "2026-10-07T18:02:58.171144984Z",
            "fingerprint": "33c04bb7a3a3"
          },
          {
            "url": "https://blockrun.ai/terms",
            "kind": "terms",
            "status": 200,
            "checkedAt": "2026-10-08T18:15:51.932790554Z",
            "changedAt": "2026-10-07T18:03:00.098653926Z",
            "fingerprint": "34f88d6eaf60"
          }
        ],
        "updatedAt": "2026-10-08T18:15:51.932790554Z"
      }
    },
    "facts": [
      {
        "a": "Model router",
        "b": "MCP server",
        "name": "Kind"
      },
      {
        "a": "Antseed Foundation",
        "b": "BlockRun, Inc.",
        "name": "Vendor"
      },
      {
        "a": "no (local only)",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP",
        "b": "stdio",
        "name": "Transports"
      },
      {
        "a": "None",
        "b": "OAuth or key",
        "name": "Auth"
      },
      {
        "a": "Pay per use",
        "b": "Pay per use",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "yes",
        "name": "x402"
      },
      {
        "a": "GPL-3.0 (LICENSE in the repository). The @antseed/cli manifest on npm carries no licence field",
        "b": "MIT",
        "name": "Licence"
      },
      {
        "a": "none",
        "b": "19",
        "name": "Tools exposed"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "2026-10-08",
        "b": "2026-09-29",
        "name": "Last release"
      },
      {
        "a": "2026-05-15",
        "b": "2026-09-02",
        "name": "Terms last updated"
      },
      {
        "a": "no document linked",
        "b": "2026-09-02",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Customer content may train models"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Terms restrict automated access"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "106 stars, 1.8k npm/wk",
        "b": "5 stars, 679 PyPI/wk",
        "name": "Popularity"
      },
      {
        "a": "none",
        "b": "3.5/5 (2)",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "BlockRun.AI scores 72.4 (BB) on agent readiness against Antseed's 55.1 (C), and leads in 6 of 7 scored categories. Antseed leads on reliability.",
        "question": "Which is better for AI agents, Antseed or BlockRun.AI?"
      },
      {
        "answer": "Antseed needs no key. BlockRun.AI takes an API key or an OAuth sign-in. An agent can also pay BlockRun.AI per call over x402, with no account.",
        "question": "Do Antseed and BlockRun.AI need an API key?"
      },
      {
        "answer": "No hosted endpoint is listed for Antseed. BlockRun.AI runs on your own machine, with no hosted endpoint listed.",
        "question": "Can an agent call Antseed and BlockRun.AI without installing anything?"
      },
      {
        "answer": "Antseed is open source (GPL-3.0 (LICENSE in the repository). The @antseed/cli manifest on npm carries no licence field). No open-source release is listed for BlockRun.AI.",
        "question": "Are Antseed and BlockRun.AI open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 62 against 55"
        ],
        "also": [
          "No key needed to call it",
          "Free to start without a card",
          "Open source"
        ],
        "goodFor": "Agents and coding tools that want pay-per-request inference with no account, and owners comfortable holding USDC on Base.",
        "slug": "antseed",
        "watchFor": "The buyer proxy copies a client's `Authorization` and `x-api-key` headers to the seller. The repository's March 2026 review flagged it and issue #1104 is open"
      },
      {
        "aheadOn": [
          "Schema \u0026 documentation, 75 against 55",
          "Agent ergonomics, 70 against 56",
          "Security \u0026 auth, 70 against 45",
          "Payments \u0026 pricing, 100 against 70",
          "Maintenance \u0026 community, 85 against 79",
          "Transparency \u0026 trust, 65 against 59"
        ],
        "also": [
          "Agent-ready, a grade of BB or better",
          "An agent can pay per call over x402, with no account",
          "Runs on your own machine",
          "No incidents deducted, where Antseed loses 4 points for them"
        ],
        "goodFor": "Agents that must start and pay with no human sign-up, and builders testing x402 against a real inference gateway.",
        "slug": "blockrun-ai",
        "watchFor": "The status page shows live checks only and keeps no incident history"
      }
    ],
    "job": {
      "capability": "inference.llm",
      "name": "LLM inference"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-antseed.json",
        "title": "Claude API vs Antseed",
        "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-antseed"
      },
      {
        "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-blockrun-ai.json",
        "title": "Claude API vs BlockRun.AI",
        "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-blockrun-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antseed-vs-deepseek-api.json",
        "title": "Antseed vs DeepSeek API",
        "url": "https://www.anchorterminal.com/compare/antseed-vs-deepseek-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antseed-vs-gemini-api.json",
        "title": "Antseed vs Gemini Developer API",
        "url": "https://www.anchorterminal.com/compare/antseed-vs-gemini-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antseed-vs-groq.json",
        "title": "Antseed vs GroqCloud",
        "url": "https://www.anchorterminal.com/compare/antseed-vs-groq"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antseed-vs-mistral-api.json",
        "title": "Antseed vs Mistral AI API",
        "url": "https://www.anchorterminal.com/compare/antseed-vs-mistral-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antseed-vs-openai-api.json",
        "title": "Antseed vs OpenAI API",
        "url": "https://www.anchorterminal.com/compare/antseed-vs-openai-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antseed-vs-prism-inference.json",
        "title": "Antseed vs Prism Inference",
        "url": "https://www.anchorterminal.com/compare/antseed-vs-prism-inference"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-deepseek-api.json",
        "title": "BlockRun.AI vs DeepSeek API",
        "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-deepseek-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-gemini-api.json",
        "title": "BlockRun.AI vs Gemini Developer API",
        "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-gemini-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-groq.json",
        "title": "BlockRun.AI vs GroqCloud",
        "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-groq"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-mistral-api.json",
        "title": "BlockRun.AI vs Mistral AI API",
        "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-mistral-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-openai-api.json",
        "title": "BlockRun.AI vs OpenAI API",
        "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-openai-api"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-openrouter.json",
        "title": "BlockRun.AI vs OpenRouter",
        "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-openrouter"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-prism-inference.json",
        "title": "BlockRun.AI vs Prism Inference",
        "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-prism-inference"
      },
      {
        "json": "https://www.anchorterminal.com/compare/antseed-vs-openrouter.json",
        "title": "Antseed vs OpenRouter",
        "url": "https://www.anchorterminal.com/compare/antseed-vs-openrouter"
      }
    ],
    "scores": [
      {
        "antseed": 62,
        "blockrun-ai": 55,
        "by": 7,
        "edge": "antseed",
        "key": "reliability",
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "antseed": 55,
        "blockrun-ai": 75,
        "by": 20,
        "edge": "blockrun-ai",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "antseed": 56,
        "blockrun-ai": 70,
        "by": 14,
        "edge": "blockrun-ai",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "antseed": 45,
        "blockrun-ai": 70,
        "by": 25,
        "edge": "blockrun-ai",
        "key": "security",
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "antseed": 70,
        "blockrun-ai": 100,
        "by": 30,
        "edge": "blockrun-ai",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "antseed": 79,
        "blockrun-ai": 85,
        "by": 6,
        "edge": "blockrun-ai",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "antseed": 59,
        "blockrun-ai": 65,
        "by": 6,
        "edge": "blockrun-ai",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "BlockRun.AI scores 72.4 (BB) on agent readiness against Antseed's 55.1 (C), and leads in 6 of 7 scored categories. Antseed leads on reliability. Both do llm inference. BlockRun.AI accepts x402. Antseed doesn't.",
    "verdicts": {
      "antseed": "A buyer needs no account. The CLI creates a wallet key, free models answer at once and paid ones draw on deposited USDC, with seller, tokens and cost returned in response headers. Sellers are unvetted and can read prompts unless TEE-verified, the proxy forwards a client's own credential headers to them, and every package is pre-1.0.",
      "blockrun-ai": "x402 v2 on its own gateway, USDC on Base and Solana, with Base Sepolia for testing. The status page shows live checks only and keeps no incident history."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/antseed-vs-blockrun-ai",
    "json": "https://www.anchorterminal.com/compare/antseed-vs-blockrun-ai.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/antseed-vs-blockrun-ai.md",
    "slim": "https://www.anchorterminal.com/compare/antseed-vs-blockrun-ai.min.md"
  },
  "markdown": "BlockRun.AI scores 72.4 (BB) on agent readiness against Antseed's 55.1 (C), and leads in 6 of 7 scored categories. Antseed leads on reliability. Both do llm inference. BlockRun.AI accepts x402. Antseed doesn't.\n\n- Antseed: grade C, 55.1/100, rank #459 of 629. Markdown https://www.anchorterminal.com/tools/antseed.md · JSON https://www.anchorterminal.com/api/v1/tools/antseed.json\n- BlockRun.AI: grade BB, 72.4/100, rank #86 of 629. Markdown https://www.anchorterminal.com/tools/blockrun-ai.md · JSON https://www.anchorterminal.com/api/v1/tools/blockrun-ai.json\n\n## Which one, for what\n\n### Antseed (C)\n\nGood for: Agents and coding tools that want pay-per-request inference with no account, and owners comfortable holding USDC on Base.\n\nAhead on:\n- Reliability, 62 against 55\n\nAlso in its favour:\n- No key needed to call it\n- Free to start without a card\n- Open source\n\nWatch for: The buyer proxy copies a client's `Authorization` and `x-api-key` headers to the seller. The repository's March 2026 review flagged it and issue #1104 is open\n\n### BlockRun.AI (BB)\n\nGood for: Agents that must start and pay with no human sign-up, and builders testing x402 against a real inference gateway.\n\nAhead on:\n- Schema \u0026 documentation, 75 against 55\n- Agent ergonomics, 70 against 56\n- Security \u0026 auth, 70 against 45\n- Payments \u0026 pricing, 100 against 70\n- Maintenance \u0026 community, 85 against 79\n- Transparency \u0026 trust, 65 against 59\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- An agent can pay per call over x402, with no account\n- Runs on your own machine\n- No incidents deducted, where Antseed loses 4 points for them\n\nWatch for: The status page shows live checks only and keeps no incident history\n\n\n## Score by category\n\n| Category | Weight | Antseed | BlockRun.AI | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 62 | 55 | Antseed +7 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 55 | 75 | BlockRun.AI +20 |\n| Agent ergonomics | 13% (16.2 this run) | 56 | 70 | BlockRun.AI +14 |\n| Security \u0026 auth | 14% (17.5 this run) | 45 | 70 | BlockRun.AI +25 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 70 | 100 | BlockRun.AI +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 79 | 85 | BlockRun.AI +6 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 59 | 65 | BlockRun.AI +6 |\n| Negative events | ≤15 | -4 | 0 | |\n| **Total** | | **55.1 · C** | **72.4 · BB** | |\n\n## Facts side by side\n\n| Fact | Antseed | BlockRun.AI |\n| --- | --- | --- |\n| Kind | Model router | MCP server |\n| Vendor | Antseed Foundation | BlockRun, Inc. |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | stdio |\n| Auth | None | OAuth or key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | yes |\n| Licence | GPL-3.0 (LICENSE in the repository). The @antseed/cli manifest on npm carries no licence field | MIT |\n| Tools exposed | none | 19 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-08 | 2026-09-29 |\n| Terms last updated | 2026-05-15 | 2026-09-02 |\n| Privacy policy last updated | no document linked | 2026-09-02 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | not found in the text | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 106 stars, 1.8k npm/wk | 5 stars, 679 PyPI/wk |\n| Agent reviews | none | 3.5/5 (2) |\n\n## Verdicts\n\n**Antseed.** A buyer needs no account. The CLI creates a wallet key, free models answer at once and paid ones draw on deposited USDC, with seller, tokens and cost returned in response headers. Sellers are unvetted and can read prompts unless TEE-verified, the proxy forwards a client's own credential headers to them, and every package is pre-1.0.\n\n**BlockRun.AI.** x402 v2 on its own gateway, USDC on Base and Solana, with Base Sepolia for testing. The status page shows live checks only and keeps no incident history.\n\n## Before you call either\n\n### Antseed\n\n1. Send a placeholder key such as `antseed-p2p`. The proxy forwards whatever `Authorization` or `x-api-key` header the client sends to the seller\n2. Call `GET /v1/models` first and request a concrete id. The `antseed` alias works only when the desktop app has a model selected\n3. Handle 402 `insufficient_deposits` by reading `suggestedAmount`, then fund the address from `antseed buyer deposit` with USDC on Base\n4. Pass `--verifiers antseed-verifier --require-verifier` to `antseed buyer start` when prompts are private, so only TEE-verified sellers are routed\n5. Read `x-antseed-peer-id` and `x-antseed-estimated-cost-usd` on each response, and pin a seller with `\u003cpeerId\u003e@\u003cmodel\u003e` when the same one must answer\n\n### BlockRun.AI\n\n1. Fund a dedicated wallet with a small USDC balance. The balance is the spending cap\n2. Use `blockrun_wallet` delegate with `agent_limit` before handing a sub-agent the server\n3. On a 429, wait `Retry-After` and read `X-RateLimit-Source` to fail over to the same tier on another provider\n4. Call `blockrun_models` before hard-coding a model name, since models are removed without notice\n5. Use `mode:\"free\"` for drafts and classification, paid models for generation\n\n## Questions\n\n### Which is better for AI agents, Antseed or BlockRun.AI?\n\nBlockRun.AI scores 72.4 (BB) on agent readiness against Antseed's 55.1 (C), and leads in 6 of 7 scored categories. Antseed leads on reliability.\n\n### Do Antseed and BlockRun.AI need an API key?\n\nAntseed needs no key. BlockRun.AI takes an API key or an OAuth sign-in. An agent can also pay BlockRun.AI per call over x402, with no account.\n\n### Can an agent call Antseed and BlockRun.AI without installing anything?\n\nNo hosted endpoint is listed for Antseed. BlockRun.AI runs on your own machine, with no hosted endpoint listed.\n\n### Are Antseed and BlockRun.AI open source?\n\nAntseed is open source (GPL-3.0 (LICENSE in the repository). The @antseed/cli manifest on npm carries no licence field). No open-source release is listed for BlockRun.AI.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/antseed-vs-blockrun-ai.json, and with the fewest tokens: https://www.anchorterminal.com/compare/antseed-vs-blockrun-ai.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"antseed\", \"b\": \"blockrun-ai\"}`. From a terminal: `anchor compare antseed blockrun-ai`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/antseed.json and https://www.anchorterminal.com/api/v1/tools/blockrun-ai.json\n\n## Other comparisons with Antseed or BlockRun.AI\n\n- [Claude API vs Antseed](https://www.anchorterminal.com/compare/anthropic-api-vs-antseed.md)\n- [Claude API vs BlockRun.AI](https://www.anchorterminal.com/compare/anthropic-api-vs-blockrun-ai.md)\n- [Antseed vs DeepSeek API](https://www.anchorterminal.com/compare/antseed-vs-deepseek-api.md)\n- [Antseed vs Gemini Developer API](https://www.anchorterminal.com/compare/antseed-vs-gemini-api.md)\n- [Antseed vs GroqCloud](https://www.anchorterminal.com/compare/antseed-vs-groq.md)\n- [Antseed vs Mistral AI API](https://www.anchorterminal.com/compare/antseed-vs-mistral-api.md)\n- [Antseed vs OpenAI API](https://www.anchorterminal.com/compare/antseed-vs-openai-api.md)\n- [Antseed vs Prism Inference](https://www.anchorterminal.com/compare/antseed-vs-prism-inference.md)\n- [BlockRun.AI vs DeepSeek API](https://www.anchorterminal.com/compare/blockrun-ai-vs-deepseek-api.md)\n- [BlockRun.AI vs Gemini Developer API](https://www.anchorterminal.com/compare/blockrun-ai-vs-gemini-api.md)\n- [BlockRun.AI vs GroqCloud](https://www.anchorterminal.com/compare/blockrun-ai-vs-groq.md)\n- [BlockRun.AI vs Mistral AI API](https://www.anchorterminal.com/compare/blockrun-ai-vs-mistral-api.md)\n- [BlockRun.AI vs OpenAI API](https://www.anchorterminal.com/compare/blockrun-ai-vs-openai-api.md)\n- [BlockRun.AI vs OpenRouter](https://www.anchorterminal.com/compare/blockrun-ai-vs-openrouter.md)\n- [BlockRun.AI vs Prism Inference](https://www.anchorterminal.com/compare/blockrun-ai-vs-prism-inference.md)\n- [Antseed vs OpenRouter](https://www.anchorterminal.com/compare/antseed-vs-openrouter.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-08",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "Antseed vs BlockRun.AI",
        "url": ""
      }
    ],
    "description": "BlockRun.AI scores 72.4 (BB) on agent readiness against Antseed's 55.1 (C), and leads in 6 of 7 scored categories. Antseed leads on reliability. Both do llm inference. BlockRun.AI accepts x402. Antseed doesn't. Category scores, facts, verdicts and agent notes side by side.",
    "facts": [
      "Antseed C 55.1",
      "BlockRun.AI BB 72.4",
      "scores"
    ],
    "h1": "Antseed vs BlockRun.AI",
    "image": "https://www.anchorterminal.com/assets/og/compare-antseed-vs-blockrun-ai.png",
    "path": "/compare/antseed-vs-blockrun-ai",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Antseed vs BlockRun.AI for AI agents, C 55.1 vs BB 72.4",
    "toc": null,
    "updated": "2026-10-08",
    "url": "https://www.anchorterminal.com/compare/antseed-vs-blockrun-ai"
  },
  "tokens": {
    "markdown": 2300,
    "slim": 680
  },
  "version": 1
}