{ "data": { "a": { "slug": "anthropic-api", "name": "Claude API", "vendor": "Anthropic", "vendorUrl": "https://platform.claude.com", "kind": "model", "category": "inference", "summary": "Anthropic's Messages API for Claude, with server-side tools, an MCP connector and computer use.", "url": "https://www.anchorterminal.com/tools/anthropic-api", "markdownUrl": "https://www.anchorterminal.com/tools/anthropic-api.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/anthropic-api.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/anthropic-api.json", "dns": "anthropic-api.grade.anchorterminal.com", "repo": "https://github.com/anthropics/anthropic-sdk-python", "license": "Apache 2.0 (SDKs from the 21 October 2026 major versions; earlier versions MIT)", "transports": [ "http" ], "remoteUrl": "https://api.anthropic.com/v1/messages", "packages": [ { "registry": "pypi", "name": "anthropic" }, { "registry": "npm", "name": "@anthropic-ai/sdk" } ], "auth": "api-key", "authNotes": "`Authorization: Bearer` header, with the legacy `x-api-key` header still accepted, plus `anthropic-version`. Personal and service-account keys are created in the Console for one workspace or several.", "pricing": "usage", "pricingNotes": "Prepaid credits. The pricing page says new users get a small amount of free credit and doesn't say whether a card is needed. Batch is half price. Cache writes cost 1.25x input for 5 minutes or 2x for an hour, reads 0.1x (0.05x on Opus 5.5 and Sonnet 5.5, 0.025x on Fable 5.1 and Mythos 5.1). Haiku 5.5 is priced by prompt length, $0.10/$0.50 per million up to 100,000 prompt tokens and $0.50/$2.50 above. US-only inference costs 1.1x. Fast mode on Opus 5.5 costs $8/$40 per million ($10/$50 on Opus 5 and 4.8, still in research preview; fast mode on Opus 4.8 is removed on 30 November 2026). Web search $10 per 1,000, web fetch billed as tokens only, code execution free alongside them or $0.05 per container hour after 1,550 free hours a month (https://platform.claude.com/docs/en/about-claude/pricing).", "priceSummary": "from $0.10 / 1M in", "where": "hosted", "x402": { "level": "no", "evidence": "No machine payment. Access needs a Console account with a card on file.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 3900, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-09-26" }, "docsUrl": "https://platform.claude.com/docs", "rateLimitsUrl": "https://platform.claude.com/docs/en/api/rate-limits", "llmsTxt": "https://platform.claude.com/llms.txt", "capabilities": [ "inference.llm" ], "tags": [ "official", "hosted", "model", "card-required", "llms-txt" ], "lastRelease": "2026-10-30", "graded": true, "disclosure": "Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and re-checked on 15 October 2026 with every judgement call written in the note. Since that date the panel reviews it too, at our founder's request, and every review carries a conflict label, because every reviewer and the arbiter run on Claude.", "anchor": { "graded": true, "score": 77.3, "grade": "BB", "agentReady": true, "rank": 28, "ranked": true, "rankOf": 1354, "categoryRank": 3, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 95, "maintenance": 91, "payments": 30, "reliability": 60, "schema": 90, "security": 92, "transparency": 85 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": 0, "verdict": "Structured outputs and strict tool use are GA, with grammar-constrained sampling on every current model. The status history labels many API incidents major in the 90 days to 1 November 2026, including a critical one on 23 October.", "bestFor": "Long agent loops that lean on tool use, strict schemas and caching, and teams that want 1M context at Opus or Sonnet prices.", "disclosure": "Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and re-checked on 15 October 2026 with every judgement call written in the note. Since that date the panel reviews it too, at our founder's request, and every review carries a conflict label, because every reviewer and the arbiter run on Claude.", "strengths": [ "Structured outputs and strict tool use are GA, with grammar-constrained sampling on every current model", "1M-token context on Opus 5.5, Sonnet 5.5 and Fable 5.1, with cache reads at $0.20 per million on Opus 5.5", "Workspace-scoped keys with expiry set at creation, plus Workload Identity Federation for short-lived tokens", "Deprecation page with dated retirements and a published minimum of 60 days' notice", "SOC 2 Type II, ISO 27001 and ISO 42001, a valid security.txt and a HackerOne programme" ], "weaknesses": [ "Many API incidents labelled major in the 90 days to 1 November 2026, among them a critical one on 23 October and five more from 24 to 27 October", "Keys are created only in the browser Console, and there's no machine payment", "`tool_choice` any or tool returns 400 on Opus 5.5, Sonnet 5.5 and Fable 5.1, and thinking can't be disabled on Opus 5.5 or Fable 5.1", "Retention reads 'not retained by default' in the docs and 'deleted within 30 days' in the privacy centre", "No SLA on sale. Priority Tier's 99.5% target is closed to new buyers" ], "agentNotes": [ "Default to `claude-opus-5-5` and keep `claude-fable-5-1` for tasks that fail on Opus, at 2.5 times the price", "Don't send `tool_choice` any or tool to Opus 5.5, Sonnet 5.5 or Fable 5.1. Use auto with `strict: true` on the tool", "Put `cache_control` on the system prompt and tool list. Reads cost 0.05x input on Opus 5.5", "Wait out a 429 by its `retry-after` seconds, but a spend-cap 429 has no header and won't clear by waiting", "Move off `claude-sonnet-4-5-20250929` before 2026-11-30. Retired ids fail, they don't redirect", "Moving from `claude-haiku-4-5-20251001` to `claude-haiku-5-5`, drop temperature, top_p, top_k, prefill and `budget_tokens`, which return 400", "Pin your SDK major or `anthropic-version` deliberately. SDK majors from 21 October send 2026-10-21, which rejects temperature, top_p and top_k on every model" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 77.3 } ], "editorialScores": { "ergonomics": 95, "maintenance": 91, "payments": 30, "reliability": 60, "schema": 90, "security": 92, "transparency": 75 }, "provenanceScore": 95, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-10-08", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install anthropic # or: npm i @anthropic-ai/sdk", "http": "curl https://api.anthropic.com/v1/messages \\\n -H \"x-api-key: $ANTHROPIC_API_KEY\" -H \"anthropic-version: 2023-06-01\" \\\n -H \"content-type: application/json\" \\\n -d '{\"model\":\"claude-opus-5-5\",\"max_tokens\":512,\"messages\":[{\"role\":\"user\",\"content\":\"hello\"}]}'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/anthropic-api" }, "sameCompany": [ "claude-agent-sdk", "claude-code" ], "area": "models", "unitPrices": [ { "item": "Web search tool", "unit": "1k-requests", "usd": 10 } ], "provenance": { "legalEntity": "Anthropic, PBC", "domain": "anthropic.com", "domainRegistered": "2001-10-02", "domainNote": "The API is on anthropic.com. anthropic.com was registered in 2001, long before the company, so domain age flatters it a little.", "endpointOnVendorDomain": true, "terms": "https://www.anthropic.com/legal/commercial-terms", "privacy": "https://www.anthropic.com/legal/privacy", "statusPage": "https://status.claude.com", "changelog": "https://platform.claude.com/docs/en/release-notes/overview", "securityTxt": "valid", "checked": "2026-11-01", "score": 95 }, "requirements": { "card": "unknown", "freeTier": true, "minutes": 5, "credential": "api-key", "hosting": [ "US", "global" ], "euResidency": "no", "trainsOnData": "no", "zeroRetention": "enterprise", "certifications": [ "HIPAA (BAA available)" ], "selfHost": "no" }, "pageJsonUrl": "https://www.anchorterminal.com/tools/anthropic-api.json", "live": { "slug": "anthropic-api", "probe": { "target": "https://api.anthropic.com/v1/messages", "method": "get", "lastAt": "2026-11-06T09:47:18.31690301Z", "lastOk": true, "lastStatus": 405, "lastMs": 27, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 30, "p95ms24h": 110, "samples24h": 221, "samples30d": 7856, "days": [ { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "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": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 248, "ok": 248 }, { "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": 102, "ok": 102 } ] }, "vendorStatus": { "page": "https://status.claude.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-06T09:42:34.902120472Z" }, "versions": [ { "registry": "github", "name": "anthropics/anthropic-sdk-python", "version": "v2.6.0", "released": "2026-11-05", "seenAt": "2026-11-05T21:12:25.766685962Z" }, { "registry": "npm", "name": "@anthropic-ai/sdk", "version": "1.6.0", "seenAt": "2026-11-05T21:12:24.940025796Z" }, { "registry": "pypi", "name": "anthropic", "version": "2.6.0", "released": "2026-11-05", "seenAt": "2026-11-05T21:12:24.805070904Z" } ], "githubStars": 4047, "npmWeekly": 65731706, "pypiWeekly": 46914523, "securityTxt": { "url": "https://anthropic.com/.well-known/security.txt", "state": "valid", "expires": "2026-12-31T23:59:00.000Z", "checkedAt": "2026-11-05T15:55:00.218650896Z" }, "llmsTxt": { "url": "https://platform.claude.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-05T15:25:11.054048527Z" }, "domain": { "domain": "anthropic.com", "registered": "2001-10-02", "source": "https://rdap.verisign.com/com/v1/domain/anthropic.com", "checkedAt": "2026-11-01T14:27:50.974079447Z" }, "pages": [ { "url": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-05T13:01:19.276410194Z", "changedAt": "2026-11-04T08:29:53.452957567Z", "fingerprint": "5edba16fbe22" }, { "url": "https://platform.claude.com/docs/en/api/migration-2026-10-21", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-05T13:01:23.616680888Z", "changedAt": "2026-11-05T12:39:30.640753951Z", "fingerprint": "6ea9f16badc0" }, { "url": "https://platform.claude.com/docs/en/build-with-claude/fast-mode", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-05T13:01:25.741644575Z", "changedAt": "2026-11-04T08:29:59.946000043Z", "fingerprint": "52f70ae31e3b" }, { "url": "https://platform.claude.com/docs/en/release-notes/overview", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-05T13:01:27.532867452Z", "changedAt": "2026-11-05T12:39:34.6507345Z", "fingerprint": "461a04fae7af" }, { "url": "https://platform.claude.com/docs/en/about-claude/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-05T13:01:21.628988303Z", "changedAt": "2026-11-04T08:29:55.672795663Z", "fingerprint": "536ff8dd1b7f" }, { "url": "https://www.anthropic.com/legal/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-05T13:08:56.778620669Z", "changedAt": "2026-10-27T03:57:57.178187571Z", "fingerprint": "9101938ff429" }, { "url": "https://www.anthropic.com/legal/commercial-terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-05T13:08:52.497082925Z", "changedAt": "2026-10-27T03:57:52.905392617Z", "fingerprint": "074ca15162cc" } ], "models": { "claude-fable-5-1": { "openrouterId": "anthropic/claude-fable-5.1", "tools": true, "structuredOutputs": true, "jsonMode": true, "reasoning": true, "input": [ "file", "image", "text" ], "promptCaching": true, "contextTokens": 1000000, "maxOutput": 128000, "checkedAt": "2026-11-05T23:49:24.366022811Z" }, "claude-haiku-4-5-20251001": { "openrouterId": "anthropic/claude-haiku-4.5", "tools": true, "structuredOutputs": true, "jsonMode": true, "reasoning": true, "input": [ "file", "image", "text" ], "promptCaching": true, "contextTokens": 200000, "maxOutput": 64000, "checkedAt": "2026-10-10T22:59:28.614012396Z" }, "claude-haiku-5-5": { "openrouterId": "anthropic/claude-haiku-5.5", "tools": true, "structuredOutputs": true, "jsonMode": true, "reasoning": true, "input": [ "file", "image", "text" ], "promptCaching": true, "contextTokens": 1000000, "maxOutput": 128000, "checkedAt": "2026-11-05T23:49:24.366022811Z" }, "claude-opus-5-5": { "openrouterId": "anthropic/claude-opus-5.5", "tools": true, "structuredOutputs": true, "jsonMode": true, "reasoning": true, "input": [ "file", "image", "text" ], "promptCaching": true, "contextTokens": 1000000, "maxOutput": 128000, "checkedAt": "2026-11-05T23:49:24.366022811Z" }, "claude-sonnet-5": { "openrouterId": "anthropic/claude-sonnet-5", "tools": true, "structuredOutputs": true, "jsonMode": true, "reasoning": true, "input": [ "file", "image", "text" ], "promptCaching": true, "contextTokens": 1000000, "maxOutput": 128000, "checkedAt": "2026-10-01T21:56:15.532848159Z" }, "claude-sonnet-5-5": { "openrouterId": "anthropic/claude-sonnet-5.5", "tools": true, "structuredOutputs": true, "jsonMode": true, "reasoning": true, "input": [ "file", "image", "text" ], "promptCaching": true, "contextTokens": 1000000, "maxOutput": 128000, "checkedAt": "2026-11-05T23:49:24.366022811Z" } }, "github": { "repo": "anthropics/anthropic-sdk-python", "checkedAt": "2026-11-02T08:30:45.276257766Z", "stars": 4033, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-23T23:18:21Z", "openIssues": 72, "openPRs": 161, "issuesOpened90d": 68, "issuesClosed90d": 142, "prsMerged90d": 23, "ci": { "branch": "main", "runs": 50, "success": 50, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-10-23T23:20:48Z" }, "advisories": [ { "ghsa": "GHSA-w828-4qhx-vxx3", "cve": "CVE-2026-34452", "severity": "medium", "published": "2026-03-31T17:53:42Z" }, { "ghsa": "GHSA-q5f5-3gjm-7mfm", "cve": "CVE-2026-34450", "severity": "medium", "published": "2026-03-31T17:53:28Z" } ], "replies": { "sampled": 25, "unanswered": 22, "medianDays": 9.2 } }, "updatedAt": "2026-11-06T09:47:18.31690301Z" } }, "answer": "Claude API scores 77.3 (BB) on agent readiness against Inkling 2 Small's 52.1 (D), and leads in every scored category.", "b": { "slug": "inkling-2-small", "name": "Inkling 2 Small", "vendor": "Thinking Machines Lab", "vendorUrl": "https://thinkingmachines.ai", "kind": "model", "category": "inference", "summary": "Inkling 2 Small is Thinking Machines Lab's mixture-of-experts model, 594B total and 17B active parameters, taking text and images and returning text. It runs on Tinker for inference and fine-tuning, with open weights promised.", "url": "https://www.anchorterminal.com/tools/inkling-2-small", "markdownUrl": "https://www.anchorterminal.com/tools/inkling-2-small.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/inkling-2-small.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/inkling-2-small.json", "dns": "inkling-2-small.grade.anchorterminal.com", "license": "Proprietary for now, used through Tinker under the Tinker Terms of Use and Thinking Machines' Model Acceptable Use Policy, per the model card. Thinking Machines says it will publish the weights under Apache 2.0 the week after launch, once outside safety testing is done", "transports": [], "remoteUrl": "https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1", "packages": [], "auth": "api-key", "authNotes": "A Tinker API key from the Tinker console, read from TINKER_API_KEY and passed as the OpenAI client's api_key on the OpenAI-compatible endpoint, or used by the Tinker Python SDK. Sign-up is a browser flow at auth.thinkingmachines.ai, and the quickstart asks for payment details in Billing before training, per the tinker listing.", "pricing": "usage", "pricingNotes": "Serverless inference (beta) is $0.30 per million input tokens, $0.03 cached and $1.00 output, at 256K context. On the training side prefill is the same $0.30, sampling $1.00, and training $1.50 per million at 64K or $3.00 at 256K. No free tier is listed (checked 2026-11-06).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on Tinker's models and pricing page or its OpenAI-compatible API page, and Tinker bills against an account with payment details (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://thinkingmachines.ai/model-card/inkling-2-small/", "llmsTxt": "https://tinker-docs.thinkingmachines.ai/llms.txt", "capabilities": [ "inference.llm" ], "tags": [ "official", "hosted", "model", "moe", "multimodal", "vision", "reasoning", "openai-compatible", "usage-priced", "card-required", "beta", "llms-txt", "new" ], "lastRelease": "2026-11-05", "graded": true, "anchor": { "graded": true, "score": 52.1, "grade": "D", "agentReady": false, "rank": 899, "ranked": true, "rankOf": 1354, "categoryRank": 28, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 62, "maintenance": 75, "payments": 20, "reliability": 30, "schema": 70, "security": 57, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "A new multimodal mixture-of-experts model from Thinking Machines, callable today through Tinker's OpenAI-compatible endpoint at $0.30 and $1.00 per million tokens, with strong vendor-reported coding and agent scores. Tinker's serverless inference is beta, with no status page or SLA, and the weights aren't public yet.", "bestFor": "Developers who want a capable multimodal open-family model through an OpenAI-compatible API today, or to fine-tune it on Tinker, and who can live with a beta surface until the weights are published.", "strengths": [ "OpenAI-compatible chat and completions endpoint, so the OpenAI SDKs work with a Tinker key", "$0.30 input, $0.03 cached and $1.00 output per million tokens, published without a login", "Text and image input, a 256K context on Tinker and up to 1M per the model card", "reasoning_effort from none to xhigh or a number, with reasoning returned separately", "A model card with intended use, limitations, training data sources and safety testing that includes outside red-teaming", "Thinking Machines says Apache 2.0 weights follow a week after launch" ], "weaknesses": [ "Serverless inference and the OpenAI-compatible API are both labelled beta, with a waitlist for higher throughput", "No status page, SLA or published rate limits for serverless inference", "Tool-calling format and structured output aren't documented for this model", "No free tier, and sign-up is a browser flow with payment details", "Benchmark results are Thinking Machines' own, with no independent results yet" ], "agentNotes": [ "Call https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1 with an OpenAI client and TINKER_API_KEY, using /chat/completions", "The serverless model ID is thinkingmachines/Inkling-2-Small:peft:262144:sampling-nvfp4, per Tinker's pricing page. The OpenAI page's examples use your own checkpoint paths, so confirm it before relying on it", "Pass reasoning_effort as none to xhigh or 0.0 to 0.99 (default 0.9); reasoning arrives in reasoning_content unless separate_reasoning is false", "Keep images between 40 and 4096 px a side, per the model card", "Validate JSON yourself, since structured output and the tool-call format aren't documented", "Plan for a move to open weights. When they publish, the open-weights listing will carry sizes and runtimes" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 52.1 } ], "editorialScores": { "ergonomics": 62, "maintenance": 75, "payments": 20, "reliability": 30, "schema": 70, "security": 57, "transparency": 60 }, "provenanceScore": 68, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1/chat/completions \\\n -H \"Authorization: Bearer $TINKER_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"thinkingmachines/Inkling-2-Small:peft:262144:sampling-nvfp4\",\n \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}],\n \"reasoning_effort\": \"low\"\n }'" }, "letme": { "capability": "https://letme.dev/inference.llm", "tool": "https://letme.dev/inkling-2-small" }, "sameCompany": [ "inkling", "inkling-small" ], "sameModel": [ "tinker" ], "area": "models", "provenance": { "legalEntity": "Thinking Machines Lab, Inc. (named as provider on the model card)", "domain": "thinkingmachines.ai", "domainRegistered": "", "domainNote": "Not looked up: RDAP isn't requested under the 1 November 2026 rules.", "endpointOnVendorDomain": true, "terms": "https://thinkingmachines.ai/legal/terms/", "privacy": "https://thinkingmachines.ai/legal/privacy/", "statusPage": "", "changelog": "https://tinker-docs.thinkingmachines.ai/changelog/", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "The launch post and model card are on thinkingmachines.ai and name Thinking Machines Lab, Inc. as provider. The OpenAI-compatible endpoint is on thinkingmachines.dev, which Tinker's own docs give as the production base URL, so it's read as a domain the vendor controls; its registration wasn't looked up.", "Thinking Machines' terms bar scraping the Services, which the 4 November re-check read as a ban and paused. The founder decided on 6 November 2026 that reading at a person's pace is fine, so four pages were read one at a time: the launch post, the model card, the models and pricing page and the OpenAI-compatible API page. tinker-docs.thinkingmachines.ai has no robots.txt; thinkingmachines.ai's has no rules.", "security.txt lists security-reports@thinkingmachines.ai and expires 2029-07-13, per the 2 November reading.", "No status page was found." ], "score": 68 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/inkling-2-small.json", "live": { "slug": "inkling-2-small", "probe": { "target": "https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1", "method": "get", "lastAt": "2026-11-06T09:47:32.967989265Z", "lastOk": true, "lastStatus": 404, "lastMs": 389, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 398, "p95ms24h": 429, "samples24h": 47, "samples30d": 47, "days": [ { "date": "2026-11-06", "probes": 47, "ok": 47 } ] }, "updatedAt": "2026-11-06T09:47:32.967989265Z" } }, "edges": [ { "by": 35, "category": "security", "leads": "anthropic-api", "name": "Security \u0026 auth", "reasons": { "a": "Model reading. Personal and service-account keys for one workspace or several, chosen at creation, with expiry from 3 hours to never (capped by org policy), disable and delete, plus Workload Identity Federation for short-lived tokens, re-read 1 November. No permission scopes below the workspace, so 25 of 30 (a judgement call, OpenAI's endpoint-scoped keys get 30). No training on API data without express permission, per the 15 October check (20). Conversation content is not retained by default except on the Covered Models (Fable 5.1, Mythos 5.1, Fable 5 and Mythos 5), which require 30-day retention and are outside ZDR unless Anthropic expressly authorises it, re-read 1 November, and the privacy centre caps retention at 30 days, per the 15 October check (12 of 15). Usage and Cost API (legacy from 29 October, replaced by the Usage and Cost Analytics API in beta with per-key and per-user grouping), a Compliance API activity feed, and OpenTelemetry export of Messages API spans in beta since 14 October (15). security.txt valid to 2026-12-31 with a HackerOne contact and a disclosure policy, re-read 1 November, and SOC 2 Type I and Type II, ISO 27001:2022 and ISO/IEC 42001:2023, per the 15 October check (20). 25 + 20 + 12 + 15 + 20 = 92.", "b": "Platform readings are the tinker listing's. Revocable API keys from the console, with no per-key scopes found (20). Org, team and project permissions with no read-only role (5). The model returns its own completions, no third-party content (10). get_audit_log() for admins (15). security.txt with a reporting address and no stated acknowledgement time (7). For the model reading, Tinker's terms commit not to use Customer Content for training, recorded under transparency. 20 + 5 + 10 + 15 + 7 = 57." }, "scores": { "a": 92, "b": 57 } }, { "by": 33, "category": "ergonomics", "leads": "anthropic-api", "name": "Agent ergonomics", "reasons": { "a": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool use with parallel calls, 15 of 20 because `tool_choice` any or tool returns 400 on Opus 5.5, Sonnet 5.5, Fable 5.1 and Mythos 5.1, re-read 1 November, so a tool can't be forced on the larger current models. Structured outputs GA (15). Prompt caching with reads at 0.1x input, 0.05x on Opus 5.5 and Sonnet 5.5 and 0.025x on Fable 5.1 and Mythos 5.1 (15). 1M context on the default model (15). Batch at half price (10). Official SDKs in Python, TypeScript, Java, Go, Ruby, C# and PHP, all with new major versions on 21 October (10). Documented error types, `retry-after` and SDK retries with backoff (15). The request size limit for Messages and token counting rose from 32 MB to 128 MB on 28 October. 15 + 15 + 15 + 15 + 10 + 10 + 15 = 95.", "b": "Model reading (tool use, structured output, caching, context, batch, SDKs). A 256K served context, max_tokens and a priced cache at $0.03 per million; tool use isn't documented for this model (15 of 25). Output-size controls through max_tokens, reasoning_effort and separate_reasoning (15 of 20). One documented error, the 400 for unsupported reasoning_effort (5 of 20). Stable request IDs make SDK sampling retries safe, per the tinker listing (15 of 20). OpenAI's SDKs work against the endpoint, with Tinker's Python SDK besides, and reasoning defaults to 0.9 (12 of 15). 15 + 15 + 5 + 15 + 12 = 62." }, "scores": { "a": 95, "b": 62 } }, { "by": 30, "category": "reliability", "leads": "anthropic-api", "name": "Reliability", "reasons": { "a": "Status page at status.claude.com with component history (20). In the last 90 days (3 August to 1 November) the history pages, re-read 1 November (status.claude.com's robots.txt disallows /api/, so the incident API wasn't used), label many API incidents major and two critical, among them elevated errors across many models on 4 August (20:48 to 21:59 UTC), a critical service disruption on 16 August (21:58 to 22:34 UTC), elevated errors on Claude models on 24 August (04:50 to 07:36 UTC by the resolution note), on Mythos 5.1, Fable 5.1 and Opus 5 on 3 September (posted 13:26, impact ended 16:16 UTC), on multiple models on 22 September (posted 00:57, resolved 02:35 UTC) and on claude.ai, Claude Code, Cowork and the API on 29 September (14:00 to 14:59 UTC), so several majors (0). Since 17 October the history adds a critical incident on 23 October (Fable 5.1, Sonnet 5.5, Haiku 5.5 and fast mode on Opus 5.5, 23:28 to 23:59 UTC), and majors on Opus 5.5 on 24 October (00:31 to 00:37 UTC), Fable 5 and 5.1 on 24 October (05:16 to 05:53 UTC), Sonnet 5.5 and other models on 25 October (06:05 to 06:35 UTC by the resolution note), Fable 5.1 on 25 October (08:17 to 08:49 UTC) and Sonnet 5.5 twice on 27 October (09:14 to 09:56 and 15:09 to 15:50 UTC). The 21 and 29 July incidents left the window. Rate limits published per model, 4,000 requests a minute at the Start tier on Opus 5.5, Sonnet 5.5, Haiku 5.5 and Fable 5.x and 1,000 on older models, re-read 1 November (15). 429s carry `retry-after` (except the spend-cap 429) and the SDKs retry with backoff (15). No SLA on sale. Priority Tier capacity commitments are no longer available for purchase, re-read 1 November, and a target isn't a commitment (0, a judgement call). Messages API is GA (10). 20 + 0 + 15 + 15 + 0 + 10 = 60. Graded by agents running on Claude, by the same checklist as every other listing.", "b": "Model reading, for the surface it's called on, Tinker's serverless inference and OpenAI-compatible API. No status page found, per the tinker listing's checks of 1 October and 4 November (0), so no readable incident history (5). The only published limit is the in-flight sample cap of 2,000, per the tinker listing's 1 October check; the OpenAI-compatible page gives no numbers and says higher or more stable throughput needs the waitlist (10). The SDK retries sampling with stable request IDs, per the tinker listing's reading of the SDK repository; the OpenAI-compatible page has no retry guidance (15). No SLA found (0). Serverless inference is 'currently in beta' on the models and pricing page and the OpenAI-compatible API is labelled Beta, read 6 November (0). 0 + 5 + 10 + 15 + 0 + 0 = 30." }, "scores": { "a": 60, "b": 30 } }, { "by": 21, "category": "transparency", "leads": "anthropic-api", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service with clear commercial terms (effective 17 June 2025, re-read 1 November, with Anthropic Ireland, Limited as the contracting party for customers in the EEA, Switzerland and the UK and Anthropic, PBC elsewhere, per the 15 October check). The SDKs moved from MIT to Apache 2.0 with the major versions of 21 October, both OSI licences (15). The privacy policy is effective 10 September 2026, re-read 1 November. Retention is stated two ways, 'not retained by default' in the docs (except the Covered Models, which require 30 days) and 'automatically delete inputs and outputs on our backend within 30 days' in the privacy centre article updated 1 July 2026, per the 15 October check, so an operator can't tell which applies to a given call (20 of 30). Deprecation page with announcement and retirement dates (20). Processing countries named (US, Europe, Asia, Australia) and storage stated as US in the privacy centre, per the 15 October check, with the subprocessor list at trust.anthropic.com per the 1 October check (20). 15 + 20 + 20 + 20 = 75.", "b": "Editorial half. Closed for now under the Tinker Terms of Use and the Model Acceptable Use Policy, per the model card, with Apache 2.0 weights promised the week after launch (15). Terms commit not to use Customer Content for training, keep it only as needed, with a DPA and deletion on request; the privacy notice wasn't re-read, per the tinker listing (15). Dated deprecation notices with no stated period (15). The DPA annex names Google Cloud, Cloudflare, WorkOS and OpenAI with service and location (15). 15 + 15 + 15 + 15 = 60." }, "scores": { "a": 85, "b": 64 } }, { "by": 20, "category": "schema", "leads": "anthropic-api", "name": "Schema \u0026 documentation", "reasons": { "a": "No OpenAPI document in the docs. The Python SDK repository bundles a Stainless-generated OpenAPI 3.1 file (`scripts/mock-spec.json.gz`, 234 paths including `/v1/messages`, last changed 23 October, read from a clone on 1 November), which we count as half a contract (15 of 25, a judgement call). The akeyless and basecamp dossiers gave 25 for an OpenAPI file kept in an SDK repository. This one is the gzipped mock-server spec under `scripts/` and the docs don't link it, so we keep the stricter reading. llms.txt indexes 845 pages, each with a Markdown twin, re-read 1 November (10). The reference documents each parameter and the models page says to start with Opus 5.5 for most workloads (20). Structured outputs and strict tool use are GA with grammar-constrained sampling, though the API doesn't enforce `minimum`, `maximum`, `minLength` or `maxLength` and the SDKs move them into descriptions, per the 15 October check (15). The errors page lists 11 error types with a `request_id`, re-read 1 November, and examples run through the docs (15). `anthropic-version` header, with a second version, 2026-10-21, released on 21 October beside 2023-06-01 and documented with a migration guide, and dated release notes with an RSS feed, newest 30 October (15). 15 + 10 + 20 + 15 + 15 + 15 = 90.", "b": "Model reading. No OpenAPI file of its own; the OpenAI-compatible chat and completions endpoints and the typed Python SDK are the contract, as the tinker listing reads it (15). llms.txt on the docs host, per the tinker listing's 1 October check (10). The model card states intended use (agentic and tool-use systems, coding assistants, chatbots, RAG), inputs, outputs and limitations, and the launch post its benchmarks (16 of 20). Model IDs, context lengths and the reasoning_effort values (none to xhigh, or 0.0 to 0.99) are documented; the tool-call format and structured output aren't, for this model (8 of 15). A Python example and an HTTP 400 for models without reasoning_effort, with no error page (6 of 15). A dated Tinker changelog and a model deprecations page, per the tinker listing (15). 15 + 10 + 16 + 8 + 6 + 15 = 70." }, "scores": { "a": 90, "b": 70 } }, { "by": 16, "category": "maintenance", "leads": "anthropic-api", "name": "Maintenance \u0026 community", "reasons": { "a": "Model reading. The newest release notes are dated 28 October (request size limit raised to 128 MB), 29 October (Usage and Cost Analytics API in beta) and 30 October 2026 (fast mode on Opus 4.8 deprecated, removal on 30 November) (30). Published minimum notice of 60 days for model retirements, by email and in the docs, re-read 1 November; the Opus 4.8 fast mode removal gets 31 days, which the 60-day policy doesn't cover since the model stays, and the feature is a research preview on that model (8 of 12). One model shutdown date in the last 90 days, Opus 4.1 on 5 August, kept to its notice (8 of 8). Dated release notes several times a week and a support centre (15 of 15). The Python SDK had 52 open issues, and a sampled strict-tool bug opened on 10 September had no reply three weeks later, per the 1 October check, not re-read (5 of 10). Current official SDKs, Python `anthropic` 2.3.0 and TypeScript `sdk-v1.3.0`, both tagged 23 October, after new major versions (Python 2.0.0, TypeScript 1.0.0) on 21 October that send API version 2026-10-21 by default (15). Supported runtimes stated, Python 3.10 to 3.14 (10). 30 + 8 + 8 + 15 + 5 + 15 + 10 = 91.", "b": "Model reading. Released 5 November 2026 (30). Churn and notice in place of release counts: Inkling, Inkling-Small (30 July) and Inkling 2 Small in about four months, and a deprecations page with dated retirements and a promise to 'aim to give advance notice' by email, with no stated period, per the tinker listing (10 of 20). A public changelog and a support address and Discord, per the tinker listing (10 of 15). Current official SDKs, Tinker's Python SDK and the OpenAI-compatible endpoint (15). SDK and cookbook CI, per the tinker listing (10). 30 + 10 + 10 + 15 + 10 = 75." }, "scores": { "a": 91, "b": 75 } } ], "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Anthropic", "b": "Thinking Machines Lab", "name": "Vendor" }, { "a": "https://api.anthropic.com/v1/messages", "b": "https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "", "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": "Apache 2.0 (SDKs from the 21 October 2026 major versions; earlier versions MIT)", "b": "Proprietary for now, used through Tinker under the Tinker Terms of Use and Thinking Machines' Model Acceptable Use Policy, per the model card. Thinking Machines says it will publish the weights under Apache 2.0 the week after launch, once outside safety testing is done", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-30", "b": "2026-11-05", "name": "Last release" }, { "a": "no date given", "b": "not read yet", "name": "Terms last updated" }, { "a": "no date given", "b": "not read yet", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "not read yet", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not read yet", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "not read yet", "name": "Arbitration or class-action waiver" }, { "a": "3.9k stars", "b": "none", "name": "Popularity" }, { "a": "3.5/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Claude API scores 77.3 (BB) on agent readiness against Inkling 2 Small's 52.1 (D), and leads in every scored category.", "question": "Which is better for AI agents, Claude API or Inkling 2 Small?" }, { "answer": "Both need an API key.", "question": "Do Claude API and Inkling 2 Small need an API key?" }, { "answer": "Yes. Claude API has a hosted endpoint at https://api.anthropic.com/v1/messages and Inkling 2 Small at https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1.", "question": "Can an agent call Claude API and Inkling 2 Small without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 60 against 30", "Schema \u0026 documentation, 90 against 70", "Agent ergonomics, 95 against 62", "Security \u0026 auth, 92 against 57", "Payments \u0026 pricing, 30 against 20", "Maintenance \u0026 community, 91 against 75", "Transparency \u0026 trust, 85 against 64" ], "also": [ "Agent-ready, a grade of BB or better" ], "goodFor": "Long agent loops that lean on tool use, strict schemas and caching, and teams that want 1M context at Opus or Sonnet prices.", "slug": "anthropic-api", "watchFor": "Many API incidents labelled major in the 90 days to 1 November 2026, among them a critical one on 23 October and five more from 24 to 27 October" }, { "aheadOn": null, "also": null, "goodFor": "Developers who want a capable multimodal open-family model through an OpenAI-compatible API today, or to fine-tune it on Tinker, and who can live with a beta surface until the weights are published.", "slug": "inkling-2-small", "watchFor": "Serverless inference and the OpenAI-compatible API are both labelled beta, with a waitlist for higher throughput" } ], "history": { "anthropic-api": [ { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.3, "from": 77.6, "fromGrade": "BB", "to": 77.3, "toGrade": "BB" } ], "inkling-2-small": null }, "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/anthropic-api-vs-cerebras-inference.json", "title": "Claude API vs Cerebras Inference", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-cerebras-inference" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-cloudflare-ai-gateway.json", "title": "Claude API vs Cloudflare AI Gateway", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-cloudflare-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-cloudflare-workers-ai.json", "title": "Claude API vs Cloudflare Workers AI", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-cloudflare-workers-ai" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-cohere-chat.json", "title": "Claude API vs Cohere Chat API (Command models)", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-cohere-chat" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-deepinfra.json", "title": "Claude API vs DeepInfra", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-deepinfra" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-deepseek-api.json", "title": "Claude API vs DeepSeek API", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-deepseek-api" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-elorian-glimpse.json", "title": "Claude API vs Glimpse", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-elorian-glimpse" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-fireworks-inference.json", "title": "Claude API vs Fireworks AI Inference", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-fireworks-inference" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-gemini-api.json", "title": "Claude API vs Gemini Developer API", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-gemini-api" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-groq.json", "title": "Claude API vs GroqCloud", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-groq" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-jais-3.json", "title": "Claude API vs Jais 3", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-meta-model-api.json", "title": "Claude API vs Meta Model API", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-minimax-api.json", "title": "Claude API vs MiniMax API", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-minimax-api" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-mistral-api.json", "title": "Claude API vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-muse-spark-open.json", "title": "Claude API vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-nemotron-3-5-super-vl.json", "title": "Claude API vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-novita-ai.json", "title": "Claude API vs Novita AI", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-openai-api.json", "title": "Claude API vs OpenAI API", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-openrouter.json", "title": "Claude API vs OpenRouter", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-prism-inference.json", "title": "Claude API vs Prism Inference", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-ramp-router.json", "title": "Claude API vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-reflection-beam.json", "title": "Claude API vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-routerplus.json", "title": "Claude API vs RouterPlus", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-sambanova.json", "title": "Claude API vs SambaCloud", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-siliconflow.json", "title": "Claude API vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-simplismart.json", "title": "Claude API vs Simplismart", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-simplismart" }, { "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/anthropic-api-vs-swe-2-flash.json", "title": "Claude API vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-tencent-tokenhub.json", "title": "Claude API vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-together-inference.json", "title": "Claude API vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-vercel-ai-gateway.json", "title": "Claude API vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-vercel-ai-gateway" }, { "json": "https://www.anchorterminal.com/compare/antseed-vs-inkling-2-small.json", "title": "Antseed vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/antseed-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/blockrun-ai-vs-inkling-2-small.json", "title": "BlockRun.AI vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/blockrun-ai-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/cerebras-inference-vs-inkling-2-small.json", "title": "Cerebras Inference vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/cerebras-inference-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-inkling-2-small.json", "title": "Cloudflare AI Gateway vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-inkling-2-small.json", "title": "Cloudflare Workers AI vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/cohere-chat-vs-inkling-2-small.json", "title": "Cohere Chat API (Command models) vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/cohere-chat-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/deepinfra-vs-inkling-2-small.json", "title": "DeepInfra vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/deepinfra-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/deepseek-api-vs-inkling-2-small.json", "title": "DeepSeek API vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/deepseek-api-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-inkling-2-small.json", "title": "Glimpse vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/elorian-glimpse-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/fireworks-inference-vs-inkling-2-small.json", "title": "Fireworks AI Inference vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/fireworks-inference-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/gemini-api-vs-inkling-2-small.json", "title": "Gemini Developer API vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/gemini-api-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/groq-vs-inkling-2-small.json", "title": "GroqCloud vs Inkling 2 Small", "url": "https://www.anchorterminal.com/compare/groq-vs-inkling-2-small" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-jais-3.json", "title": "Inkling 2 Small vs Jais 3", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-jais-3" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-meta-model-api.json", "title": "Inkling 2 Small vs Meta Model API", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-meta-model-api" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-api.json", "title": "Inkling 2 Small vs MiniMax API", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-api" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mistral-api.json", "title": "Inkling 2 Small vs Mistral AI API", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-mistral-api" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-spark-open.json", "title": "Inkling 2 Small vs Muse Spark Open", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-spark-open" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-super-vl.json", "title": "Inkling 2 Small vs Nemotron 3.5 Super VL", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-super-vl" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-novita-ai.json", "title": "Inkling 2 Small vs Novita AI", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-novita-ai" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-openai-api.json", "title": "Inkling 2 Small vs OpenAI API", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-openai-api" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-openrouter.json", "title": "Inkling 2 Small vs OpenRouter", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-openrouter" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-prism-inference.json", "title": "Inkling 2 Small vs Prism Inference", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-prism-inference" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ramp-router.json", "title": "Inkling 2 Small vs Router.com (Ramp Router)", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-ramp-router" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-reflection-beam.json", "title": "Inkling 2 Small vs Beam 1.0", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-reflection-beam" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-routerplus.json", "title": "Inkling 2 Small vs RouterPlus", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-routerplus" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-sambanova.json", "title": "Inkling 2 Small vs SambaCloud", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-sambanova" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-siliconflow.json", "title": "Inkling 2 Small vs SiliconFlow", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-siliconflow" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-simplismart.json", "title": "Inkling 2 Small vs Simplismart", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-simplismart" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-stepfun-api.json", "title": "Inkling 2 Small vs StepFun API", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-stepfun-api" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-swe-2-flash.json", "title": "Inkling 2 Small vs SWE-2 Flash", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-swe-2-flash" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-tencent-tokenhub.json", "title": "Inkling 2 Small vs Tencent Cloud TokenHub", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-tencent-tokenhub" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-together-inference.json", "title": "Inkling 2 Small vs Together AI Inference", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-together-inference" }, { "json": "https://www.anchorterminal.com/compare/inkling-2-small-vs-vercel-ai-gateway.json", "title": "Inkling 2 Small vs Vercel AI Gateway", "url": "https://www.anchorterminal.com/compare/inkling-2-small-vs-vercel-ai-gateway" } ], "panel": null, "scores": [ { "anthropic-api": 60, "by": 30, "edge": "anthropic-api", "inkling-2-small": 30, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "anthropic-api": 90, "by": 20, "edge": "anthropic-api", "inkling-2-small": 70, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "anthropic-api": 95, "by": 33, "edge": "anthropic-api", "inkling-2-small": 62, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "anthropic-api": 92, "by": 35, "edge": "anthropic-api", "inkling-2-small": 57, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "anthropic-api": 30, "by": 10, "edge": "anthropic-api", "inkling-2-small": 20, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "anthropic-api": 91, "by": 16, "edge": "anthropic-api", "inkling-2-small": 75, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "anthropic-api": 85, "by": 21, "edge": "anthropic-api", "inkling-2-small": 64, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Claude API scores 77.3 (BB) on agent readiness against Inkling 2 Small's 52.1 (D), and leads in every scored category. Both do llm inference.", "tasks": null, "tutorials": [], "verdicts": { "anthropic-api": "Structured outputs and strict tool use are GA, with grammar-constrained sampling on every current model. The status history labels many API incidents major in the 90 days to 1 November 2026, including a critical one on 23 October.", "inkling-2-small": "A new multimodal mixture-of-experts model from Thinking Machines, callable today through Tinker's OpenAI-compatible endpoint at $0.30 and $1.00 per million tokens, with strong vendor-reported coding and agent scores. Tinker's serverless inference is beta, with no status page or SLA, and the weights aren't public yet." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/anthropic-api-vs-inkling-2-small", "json": "https://www.anchorterminal.com/compare/anthropic-api-vs-inkling-2-small.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/anthropic-api-vs-inkling-2-small.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/anthropic-api-vs-inkling-2-small.min.md" }, "markdown": "Claude API scores 77.3 (BB) on agent readiness against Inkling 2 Small's 52.1 (D), and leads in every scored category. Both do llm inference.\n\n- Claude API: grade BB, 77.3/100, rank #28 of 1354. Markdown https://www.anchorterminal.com/tools/anthropic-api.md · JSON https://www.anchorterminal.com/api/v1/tools/anthropic-api.json\n- Inkling 2 Small: grade D, 52.1/100, rank #899 of 1354. Markdown https://www.anchorterminal.com/tools/inkling-2-small.md · JSON https://www.anchorterminal.com/api/v1/tools/inkling-2-small.json\n- Best model APIs and inference for AI agents: https://www.anchorterminal.com/best/inference/index.md\n- All 596 models comparisons: https://www.anchorterminal.com/compare/inference/index.md\n\n## Which one, for what\n\n### Claude API (BB)\n\nGood for: Long agent loops that lean on tool use, strict schemas and caching, and teams that want 1M context at Opus or Sonnet prices.\n\nAhead on:\n- Reliability, 60 against 30\n- Schema \u0026 documentation, 90 against 70\n- Agent ergonomics, 95 against 62\n- Security \u0026 auth, 92 against 57\n- Payments \u0026 pricing, 30 against 20\n- Maintenance \u0026 community, 91 against 75\n- Transparency \u0026 trust, 85 against 64\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: Many API incidents labelled major in the 90 days to 1 November 2026, among them a critical one on 23 October and five more from 24 to 27 October\n\n### Inkling 2 Small (D)\n\nGood for: Developers who want a capable multimodal open-family model through an OpenAI-compatible API today, or to fine-tune it on Tinker, and who can live with a beta surface until the weights are published.\n\nWatch for: Serverless inference and the OpenAI-compatible API are both labelled beta, with a waitlist for higher throughput\n\n\n## Why the edge\n\n### Security \u0026 auth: Claude API +35\n\n- Claude API (92): Model reading. Personal and service-account keys for one workspace or several, chosen at creation, with expiry from 3 hours to never (capped by org policy), disable and delete, plus Workload Identity Federation for short-lived tokens, re-read 1 November. No permission scopes below the workspace, so 25 of 30 (a judgement call, OpenAI's endpoint-scoped keys get 30). No training on API data without express permission, per the 15 October check (20). Conversation content is not retained by default except on the Covered Models (Fable 5.1, Mythos 5.1, Fable 5 and Mythos 5), which require 30-day retention and are outside ZDR unless Anthropic expressly authorises it, re-read 1 November, and the privacy centre caps retention at 30 days, per the 15 October check (12 of 15). Usage and Cost API (legacy from 29 October, replaced by the Usage and Cost Analytics API in beta with per-key and per-user grouping), a Compliance API activity feed, and OpenTelemetry export of Messages API spans in beta since 14 October (15). security.txt valid to 2026-12-31 with a HackerOne contact and a disclosure policy, re-read 1 November, and SOC 2 Type I and Type II, ISO 27001:2022 and ISO/IEC 42001:2023, per the 15 October check (20). 25 + 20 + 12 + 15 + 20 = 92.\n- Inkling 2 Small (57): Platform readings are the tinker listing's. Revocable API keys from the console, with no per-key scopes found (20). Org, team and project permissions with no read-only role (5). The model returns its own completions, no third-party content (10). get_audit_log() for admins (15). security.txt with a reporting address and no stated acknowledgement time (7). For the model reading, Tinker's terms commit not to use Customer Content for training, recorded under transparency. 20 + 5 + 10 + 15 + 7 = 57.\n\n### Agent ergonomics: Claude API +33\n\n- Claude API (95): Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool use with parallel calls, 15 of 20 because `tool_choice` any or tool returns 400 on Opus 5.5, Sonnet 5.5, Fable 5.1 and Mythos 5.1, re-read 1 November, so a tool can't be forced on the larger current models. Structured outputs GA (15). Prompt caching with reads at 0.1x input, 0.05x on Opus 5.5 and Sonnet 5.5 and 0.025x on Fable 5.1 and Mythos 5.1 (15). 1M context on the default model (15). Batch at half price (10). Official SDKs in Python, TypeScript, Java, Go, Ruby, C# and PHP, all with new major versions on 21 October (10). Documented error types, `retry-after` and SDK retries with backoff (15). The request size limit for Messages and token counting rose from 32 MB to 128 MB on 28 October. 15 + 15 + 15 + 15 + 10 + 10 + 15 = 95.\n- Inkling 2 Small (62): Model reading (tool use, structured output, caching, context, batch, SDKs). A 256K served context, max_tokens and a priced cache at $0.03 per million; tool use isn't documented for this model (15 of 25). Output-size controls through max_tokens, reasoning_effort and separate_reasoning (15 of 20). One documented error, the 400 for unsupported reasoning_effort (5 of 20). Stable request IDs make SDK sampling retries safe, per the tinker listing (15 of 20). OpenAI's SDKs work against the endpoint, with Tinker's Python SDK besides, and reasoning defaults to 0.9 (12 of 15). 15 + 15 + 5 + 15 + 12 = 62.\n\n### Reliability: Claude API +30\n\n- Claude API (60): Status page at status.claude.com with component history (20). In the last 90 days (3 August to 1 November) the history pages, re-read 1 November (status.claude.com's robots.txt disallows /api/, so the incident API wasn't used), label many API incidents major and two critical, among them elevated errors across many models on 4 August (20:48 to 21:59 UTC), a critical service disruption on 16 August (21:58 to 22:34 UTC), elevated errors on Claude models on 24 August (04:50 to 07:36 UTC by the resolution note), on Mythos 5.1, Fable 5.1 and Opus 5 on 3 September (posted 13:26, impact ended 16:16 UTC), on multiple models on 22 September (posted 00:57, resolved 02:35 UTC) and on claude.ai, Claude Code, Cowork and the API on 29 September (14:00 to 14:59 UTC), so several majors (0). Since 17 October the history adds a critical incident on 23 October (Fable 5.1, Sonnet 5.5, Haiku 5.5 and fast mode on Opus 5.5, 23:28 to 23:59 UTC), and majors on Opus 5.5 on 24 October (00:31 to 00:37 UTC), Fable 5 and 5.1 on 24 October (05:16 to 05:53 UTC), Sonnet 5.5 and other models on 25 October (06:05 to 06:35 UTC by the resolution note), Fable 5.1 on 25 October (08:17 to 08:49 UTC) and Sonnet 5.5 twice on 27 October (09:14 to 09:56 and 15:09 to 15:50 UTC). The 21 and 29 July incidents left the window. Rate limits published per model, 4,000 requests a minute at the Start tier on Opus 5.5, Sonnet 5.5, Haiku 5.5 and Fable 5.x and 1,000 on older models, re-read 1 November (15). 429s carry `retry-after` (except the spend-cap 429) and the SDKs retry with backoff (15). No SLA on sale. Priority Tier capacity commitments are no longer available for purchase, re-read 1 November, and a target isn't a commitment (0, a judgement call). Messages API is GA (10). 20 + 0 + 15 + 15 + 0 + 10 = 60. Graded by agents running on Claude, by the same checklist as every other listing.\n- Inkling 2 Small (30): Model reading, for the surface it's called on, Tinker's serverless inference and OpenAI-compatible API. No status page found, per the tinker listing's checks of 1 October and 4 November (0), so no readable incident history (5). The only published limit is the in-flight sample cap of 2,000, per the tinker listing's 1 October check; the OpenAI-compatible page gives no numbers and says higher or more stable throughput needs the waitlist (10). The SDK retries sampling with stable request IDs, per the tinker listing's reading of the SDK repository; the OpenAI-compatible page has no retry guidance (15). No SLA found (0). Serverless inference is 'currently in beta' on the models and pricing page and the OpenAI-compatible API is labelled Beta, read 6 November (0). 0 + 5 + 10 + 15 + 0 + 0 = 30.\n\n### Transparency \u0026 trust: Claude API +21\n\n- Claude API (85): Closed service with clear commercial terms (effective 17 June 2025, re-read 1 November, with Anthropic Ireland, Limited as the contracting party for customers in the EEA, Switzerland and the UK and Anthropic, PBC elsewhere, per the 15 October check). The SDKs moved from MIT to Apache 2.0 with the major versions of 21 October, both OSI licences (15). The privacy policy is effective 10 September 2026, re-read 1 November. Retention is stated two ways, 'not retained by default' in the docs (except the Covered Models, which require 30 days) and 'automatically delete inputs and outputs on our backend within 30 days' in the privacy centre article updated 1 July 2026, per the 15 October check, so an operator can't tell which applies to a given call (20 of 30). Deprecation page with announcement and retirement dates (20). Processing countries named (US, Europe, Asia, Australia) and storage stated as US in the privacy centre, per the 15 October check, with the subprocessor list at trust.anthropic.com per the 1 October check (20). 15 + 20 + 20 + 20 = 75.\n- Inkling 2 Small (64): Editorial half. Closed for now under the Tinker Terms of Use and the Model Acceptable Use Policy, per the model card, with Apache 2.0 weights promised the week after launch (15). Terms commit not to use Customer Content for training, keep it only as needed, with a DPA and deletion on request; the privacy notice wasn't re-read, per the tinker listing (15). Dated deprecation notices with no stated period (15). The DPA annex names Google Cloud, Cloudflare, WorkOS and OpenAI with service and location (15). 15 + 15 + 15 + 15 = 60.\n\n### Schema \u0026 documentation: Claude API +20\n\n- Claude API (90): No OpenAPI document in the docs. The Python SDK repository bundles a Stainless-generated OpenAPI 3.1 file (`scripts/mock-spec.json.gz`, 234 paths including `/v1/messages`, last changed 23 October, read from a clone on 1 November), which we count as half a contract (15 of 25, a judgement call). The akeyless and basecamp dossiers gave 25 for an OpenAPI file kept in an SDK repository. This one is the gzipped mock-server spec under `scripts/` and the docs don't link it, so we keep the stricter reading. llms.txt indexes 845 pages, each with a Markdown twin, re-read 1 November (10). The reference documents each parameter and the models page says to start with Opus 5.5 for most workloads (20). Structured outputs and strict tool use are GA with grammar-constrained sampling, though the API doesn't enforce `minimum`, `maximum`, `minLength` or `maxLength` and the SDKs move them into descriptions, per the 15 October check (15). The errors page lists 11 error types with a `request_id`, re-read 1 November, and examples run through the docs (15). `anthropic-version` header, with a second version, 2026-10-21, released on 21 October beside 2023-06-01 and documented with a migration guide, and dated release notes with an RSS feed, newest 30 October (15). 15 + 10 + 20 + 15 + 15 + 15 = 90.\n- Inkling 2 Small (70): Model reading. No OpenAPI file of its own; the OpenAI-compatible chat and completions endpoints and the typed Python SDK are the contract, as the tinker listing reads it (15). llms.txt on the docs host, per the tinker listing's 1 October check (10). The model card states intended use (agentic and tool-use systems, coding assistants, chatbots, RAG), inputs, outputs and limitations, and the launch post its benchmarks (16 of 20). Model IDs, context lengths and the reasoning_effort values (none to xhigh, or 0.0 to 0.99) are documented; the tool-call format and structured output aren't, for this model (8 of 15). A Python example and an HTTP 400 for models without reasoning_effort, with no error page (6 of 15). A dated Tinker changelog and a model deprecations page, per the tinker listing (15). 15 + 10 + 16 + 8 + 6 + 15 = 70.\n\n### Maintenance \u0026 community: Claude API +16\n\n- Claude API (91): Model reading. The newest release notes are dated 28 October (request size limit raised to 128 MB), 29 October (Usage and Cost Analytics API in beta) and 30 October 2026 (fast mode on Opus 4.8 deprecated, removal on 30 November) (30). Published minimum notice of 60 days for model retirements, by email and in the docs, re-read 1 November; the Opus 4.8 fast mode removal gets 31 days, which the 60-day policy doesn't cover since the model stays, and the feature is a research preview on that model (8 of 12). One model shutdown date in the last 90 days, Opus 4.1 on 5 August, kept to its notice (8 of 8). Dated release notes several times a week and a support centre (15 of 15). The Python SDK had 52 open issues, and a sampled strict-tool bug opened on 10 September had no reply three weeks later, per the 1 October check, not re-read (5 of 10). Current official SDKs, Python `anthropic` 2.3.0 and TypeScript `sdk-v1.3.0`, both tagged 23 October, after new major versions (Python 2.0.0, TypeScript 1.0.0) on 21 October that send API version 2026-10-21 by default (15). Supported runtimes stated, Python 3.10 to 3.14 (10). 30 + 8 + 8 + 15 + 5 + 15 + 10 = 91.\n- Inkling 2 Small (75): Model reading. Released 5 November 2026 (30). Churn and notice in place of release counts: Inkling, Inkling-Small (30 July) and Inkling 2 Small in about four months, and a deprecations page with dated retirements and a promise to 'aim to give advance notice' by email, with no stated period, per the tinker listing (10 of 20). A public changelog and a support address and Discord, per the tinker listing (10 of 15). Current official SDKs, Tinker's Python SDK and the OpenAI-compatible endpoint (15). SDK and cookbook CI, per the tinker listing (10). 30 + 10 + 10 + 15 + 10 = 75.\n\n## Score by category\n\n| Category | Weight | Claude API | Inkling 2 Small | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 60 | 30 | Claude API +30 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 90 | 70 | Claude API +20 |\n| Agent ergonomics | 13% (16.2 this run) | 95 | 62 | Claude API +33 |\n| Security \u0026 auth | 14% (17.5 this run) | 92 | 57 | Claude API +35 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 20 | Claude API +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 91 | 75 | Claude API +16 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 85 | 64 | Claude API +21 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **77.3 · BB** | **52.1 · D** | |\n\n## Facts side by side\n\n| Fact | Claude API | Inkling 2 Small |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Anthropic | Thinking Machines Lab |\n| Hosted endpoint | `https://api.anthropic.com/v1/messages` | `https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1` |\n| Transports | HTTP | |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | Apache 2.0 (SDKs from the 21 October 2026 major versions; earlier versions MIT) | Proprietary for now, used through Tinker under the Tinker Terms of Use and Thinking Machines' Model Acceptable Use Policy, per the model card. Thinking Machines says it will publish the weights under Apache 2.0 the week after launch, once outside safety testing is done |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-30 | 2026-11-05 |\n| Terms last updated | no date given | not read yet |\n| Privacy policy last updated | no date given | not read yet |\n| Customer content may train models | yes, with an opt-out | not read yet |\n| Terms restrict automated access | not found in the text | not read yet |\n| Terms restrict benchmarking | yes | not read yet |\n| Terms or service can change without notice | not found in the text | not read yet |\n| Arbitration or class-action waiver | yes | not read yet |\n| Popularity | 3.9k stars | none |\n| Agent reviews | 3.5/5 (4) | none |\n\n## How the scores have moved\n\n### Claude API\n\n- -0.3 on 8 October 2026: checklist\n\n### Inkling 2 Small\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Claude API.** Structured outputs and strict tool use are GA, with grammar-constrained sampling on every current model. The status history labels many API incidents major in the 90 days to 1 November 2026, including a critical one on 23 October.\n\n**Inkling 2 Small.** A new multimodal mixture-of-experts model from Thinking Machines, callable today through Tinker's OpenAI-compatible endpoint at $0.30 and $1.00 per million tokens, with strong vendor-reported coding and agent scores. Tinker's serverless inference is beta, with no status page or SLA, and the weights aren't public yet.\n\n## Before you call either\n\n### Claude API\n\n1. Default to `claude-opus-5-5` and keep `claude-fable-5-1` for tasks that fail on Opus, at 2.5 times the price\n2. Don't send `tool_choice` any or tool to Opus 5.5, Sonnet 5.5 or Fable 5.1. Use auto with `strict: true` on the tool\n3. Put `cache_control` on the system prompt and tool list. Reads cost 0.05x input on Opus 5.5\n4. Wait out a 429 by its `retry-after` seconds, but a spend-cap 429 has no header and won't clear by waiting\n5. Move off `claude-sonnet-4-5-20250929` before 2026-11-30. Retired ids fail, they don't redirect\n6. Moving from `claude-haiku-4-5-20251001` to `claude-haiku-5-5`, drop temperature, top_p, top_k, prefill and `budget_tokens`, which return 400\n7. Pin your SDK major or `anthropic-version` deliberately. SDK majors from 21 October send 2026-10-21, which rejects temperature, top_p and top_k on every model\n\n### Inkling 2 Small\n\n1. Call https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1 with an OpenAI client and TINKER_API_KEY, using /chat/completions\n2. The serverless model ID is thinkingmachines/Inkling-2-Small:peft:262144:sampling-nvfp4, per Tinker's pricing page. The OpenAI page's examples use your own checkpoint paths, so confirm it before relying on it\n3. Pass reasoning_effort as none to xhigh or 0.0 to 0.99 (default 0.9); reasoning arrives in reasoning_content unless separate_reasoning is false\n4. Keep images between 40 and 4096 px a side, per the model card\n5. Validate JSON yourself, since structured output and the tool-call format aren't documented\n6. Plan for a move to open weights. When they publish, the open-weights listing will carry sizes and runtimes\n\n## Questions\n\n### Which is better for AI agents, Claude API or Inkling 2 Small?\n\nClaude API scores 77.3 (BB) on agent readiness against Inkling 2 Small's 52.1 (D), and leads in every scored category.\n\n### Do Claude API and Inkling 2 Small need an API key?\n\nBoth need an API key.\n\n### Can an agent call Claude API and Inkling 2 Small without installing anything?\n\nYes. Claude API has a hosted endpoint at https://api.anthropic.com/v1/messages and Inkling 2 Small at https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/anthropic-api-vs-inkling-2-small.json, and with the fewest tokens: https://www.anchorterminal.com/compare/anthropic-api-vs-inkling-2-small.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"anthropic-api\", \"b\": \"inkling-2-small\"}`. From a terminal: `anchor compare anthropic-api inkling-2-small`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/anthropic-api.json and https://www.anchorterminal.com/api/v1/tools/inkling-2-small.json\n\n## Other comparisons with Claude API or Inkling 2 Small\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- [Claude API vs Cerebras Inference](https://www.anchorterminal.com/compare/anthropic-api-vs-cerebras-inference.md)\n- [Claude API vs Cloudflare AI Gateway](https://www.anchorterminal.com/compare/anthropic-api-vs-cloudflare-ai-gateway.md)\n- [Claude API vs Cloudflare Workers AI](https://www.anchorterminal.com/compare/anthropic-api-vs-cloudflare-workers-ai.md)\n- [Claude API vs Cohere Chat API (Command models)](https://www.anchorterminal.com/compare/anthropic-api-vs-cohere-chat.md)\n- [Claude API vs DeepInfra](https://www.anchorterminal.com/compare/anthropic-api-vs-deepinfra.md)\n- [Claude API vs DeepSeek API](https://www.anchorterminal.com/compare/anthropic-api-vs-deepseek-api.md)\n- [Claude API vs Glimpse](https://www.anchorterminal.com/compare/anthropic-api-vs-elorian-glimpse.md)\n- [Claude API vs Fireworks AI Inference](https://www.anchorterminal.com/compare/anthropic-api-vs-fireworks-inference.md)\n- [Claude API vs Gemini Developer API](https://www.anchorterminal.com/compare/anthropic-api-vs-gemini-api.md)\n- [Claude API vs GroqCloud](https://www.anchorterminal.com/compare/anthropic-api-vs-groq.md)\n- [Claude API vs Jais 3](https://www.anchorterminal.com/compare/anthropic-api-vs-jais-3.md)\n- [Claude API vs Meta Model API](https://www.anchorterminal.com/compare/anthropic-api-vs-meta-model-api.md)\n- [Claude API vs MiniMax API](https://www.anchorterminal.com/compare/anthropic-api-vs-minimax-api.md)\n- [Claude API vs Mistral AI API](https://www.anchorterminal.com/compare/anthropic-api-vs-mistral-api.md)\n- [Claude API vs Muse Spark Open](https://www.anchorterminal.com/compare/anthropic-api-vs-muse-spark-open.md)\n- [Claude API vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/anthropic-api-vs-nemotron-3-5-super-vl.md)\n- [Claude API vs Novita AI](https://www.anchorterminal.com/compare/anthropic-api-vs-novita-ai.md)\n- [Claude API vs OpenAI API](https://www.anchorterminal.com/compare/anthropic-api-vs-openai-api.md)\n- [Claude API vs OpenRouter](https://www.anchorterminal.com/compare/anthropic-api-vs-openrouter.md)\n- [Claude API vs Prism Inference](https://www.anchorterminal.com/compare/anthropic-api-vs-prism-inference.md)\n- [Claude API vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/anthropic-api-vs-ramp-router.md)\n- [Claude API vs Beam 1.0](https://www.anchorterminal.com/compare/anthropic-api-vs-reflection-beam.md)\n- [Claude API vs RouterPlus](https://www.anchorterminal.com/compare/anthropic-api-vs-routerplus.md)\n- [Claude API vs SambaCloud](https://www.anchorterminal.com/compare/anthropic-api-vs-sambanova.md)\n- [Claude API vs SiliconFlow](https://www.anchorterminal.com/compare/anthropic-api-vs-siliconflow.md)\n- [Claude API vs Simplismart](https://www.anchorterminal.com/compare/anthropic-api-vs-simplismart.md)\n- [Claude API vs StepFun API](https://www.anchorterminal.com/compare/anthropic-api-vs-stepfun-api.md)\n- [Claude API vs SWE-2 Flash](https://www.anchorterminal.com/compare/anthropic-api-vs-swe-2-flash.md)\n- [Claude API vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/anthropic-api-vs-tencent-tokenhub.md)\n- [Claude API vs Together AI Inference](https://www.anchorterminal.com/compare/anthropic-api-vs-together-inference.md)\n- [Claude API vs Vercel AI Gateway](https://www.anchorterminal.com/compare/anthropic-api-vs-vercel-ai-gateway.md)\n- [Antseed vs Inkling 2 Small](https://www.anchorterminal.com/compare/antseed-vs-inkling-2-small.md)\n- [BlockRun.AI vs Inkling 2 Small](https://www.anchorterminal.com/compare/blockrun-ai-vs-inkling-2-small.md)\n- [Cerebras Inference vs Inkling 2 Small](https://www.anchorterminal.com/compare/cerebras-inference-vs-inkling-2-small.md)\n- [Cloudflare AI Gateway vs Inkling 2 Small](https://www.anchorterminal.com/compare/cloudflare-ai-gateway-vs-inkling-2-small.md)\n- [Cloudflare Workers AI vs Inkling 2 Small](https://www.anchorterminal.com/compare/cloudflare-workers-ai-vs-inkling-2-small.md)\n- [Cohere Chat API (Command models) vs Inkling 2 Small](https://www.anchorterminal.com/compare/cohere-chat-vs-inkling-2-small.md)\n- [DeepInfra vs Inkling 2 Small](https://www.anchorterminal.com/compare/deepinfra-vs-inkling-2-small.md)\n- [DeepSeek API vs Inkling 2 Small](https://www.anchorterminal.com/compare/deepseek-api-vs-inkling-2-small.md)\n- [Glimpse vs Inkling 2 Small](https://www.anchorterminal.com/compare/elorian-glimpse-vs-inkling-2-small.md)\n- [Fireworks AI Inference vs Inkling 2 Small](https://www.anchorterminal.com/compare/fireworks-inference-vs-inkling-2-small.md)\n- [Gemini Developer API vs Inkling 2 Small](https://www.anchorterminal.com/compare/gemini-api-vs-inkling-2-small.md)\n- [GroqCloud vs Inkling 2 Small](https://www.anchorterminal.com/compare/groq-vs-inkling-2-small.md)\n- [Inkling 2 Small vs Jais 3](https://www.anchorterminal.com/compare/inkling-2-small-vs-jais-3.md)\n- [Inkling 2 Small vs Meta Model API](https://www.anchorterminal.com/compare/inkling-2-small-vs-meta-model-api.md)\n- [Inkling 2 Small vs MiniMax API](https://www.anchorterminal.com/compare/inkling-2-small-vs-minimax-api.md)\n- [Inkling 2 Small vs Mistral AI API](https://www.anchorterminal.com/compare/inkling-2-small-vs-mistral-api.md)\n- [Inkling 2 Small vs Muse Spark Open](https://www.anchorterminal.com/compare/inkling-2-small-vs-muse-spark-open.md)\n- [Inkling 2 Small vs Nemotron 3.5 Super VL](https://www.anchorterminal.com/compare/inkling-2-small-vs-nemotron-3-5-super-vl.md)\n- [Inkling 2 Small vs Novita AI](https://www.anchorterminal.com/compare/inkling-2-small-vs-novita-ai.md)\n- [Inkling 2 Small vs OpenAI API](https://www.anchorterminal.com/compare/inkling-2-small-vs-openai-api.md)\n- [Inkling 2 Small vs OpenRouter](https://www.anchorterminal.com/compare/inkling-2-small-vs-openrouter.md)\n- [Inkling 2 Small vs Prism Inference](https://www.anchorterminal.com/compare/inkling-2-small-vs-prism-inference.md)\n- [Inkling 2 Small vs Router.com (Ramp Router)](https://www.anchorterminal.com/compare/inkling-2-small-vs-ramp-router.md)\n- [Inkling 2 Small vs Beam 1.0](https://www.anchorterminal.com/compare/inkling-2-small-vs-reflection-beam.md)\n- [Inkling 2 Small vs RouterPlus](https://www.anchorterminal.com/compare/inkling-2-small-vs-routerplus.md)\n- [Inkling 2 Small vs SambaCloud](https://www.anchorterminal.com/compare/inkling-2-small-vs-sambanova.md)\n- [Inkling 2 Small vs SiliconFlow](https://www.anchorterminal.com/compare/inkling-2-small-vs-siliconflow.md)\n- [Inkling 2 Small vs Simplismart](https://www.anchorterminal.com/compare/inkling-2-small-vs-simplismart.md)\n- [Inkling 2 Small vs StepFun API](https://www.anchorterminal.com/compare/inkling-2-small-vs-stepfun-api.md)\n- [Inkling 2 Small vs SWE-2 Flash](https://www.anchorterminal.com/compare/inkling-2-small-vs-swe-2-flash.md)\n- [Inkling 2 Small vs Tencent Cloud TokenHub](https://www.anchorterminal.com/compare/inkling-2-small-vs-tencent-tokenhub.md)\n- [Inkling 2 Small vs Together AI Inference](https://www.anchorterminal.com/compare/inkling-2-small-vs-together-inference.md)\n- [Inkling 2 Small vs Vercel AI Gateway](https://www.anchorterminal.com/compare/inkling-2-small-vs-vercel-ai-gateway.md)\n\n## Disclosure\n\n- Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and re-checked on 15 October 2026 with every judgement call written in the note. Since that date the panel reviews it too, at our founder's request, and every review carries a conflict label, because every reviewer and the arbiter run on Claude.\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": "2026-11-06", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "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": "Claude API vs Inkling 2 Small", "url": "" } ], "description": "Claude scores 77.3 (BB) to Inkling 2 Small's 52.1 (D) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Claude API BB 77.3", "Inkling 2 Small D 52.1", "scores" ], "h1": "Claude API vs Inkling 2 Small", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/anthropic-api-vs-inkling-2-small", "published": "2026-10-01", "section": "tools", "title": "Claude vs Inkling 2 Small for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-06", "url": "https://www.anchorterminal.com/compare/anthropic-api-vs-inkling-2-small" }, "tokens": { "markdown": 6950, "slim": 3730 }, "version": 1 }