{ "data": { "a": { "slug": "tinker", "name": "Tinker", "vendor": "Thinking Machines Lab", "vendorUrl": "https://thinkingmachines.ai/tinker/", "kind": "sdk", "category": "fine-tuning", "summary": "Thinking Machines Lab's API for model training.", "url": "https://www.anchorterminal.com/tools/tinker", "markdownUrl": "https://www.anchorterminal.com/tools/tinker.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/tinker.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/tinker.json", "repo": "https://github.com/thinking-machines-lab/tinker-cookbook", "license": "Apache-2.0 (cookbook)", "transports": [ "http" ], "packages": [ { "registry": "pypi", "name": "tinker" }, { "registry": "pypi", "name": "tinker-cookbook" } ], "auth": "api-key", "authNotes": "API key from the Tinker console, exported as `TINKER_API_KEY`, or `tinker auth login`. Sign-up is at auth.thinkingmachines.ai and the quickstart says to add payment details in Billing before training.", "pricing": "usage", "pricingNotes": "Per 1M tokens, split into prefill, cached prefill (20 per cent of prefill), sample and train. Qwen3.8-27B $1.86 prefill, $5.595 sample, $4.103 train; Qwen3.5-9B $0.66, $1.995, $1.463; GPT-OSS-20B $0.18, $0.45, $0.396; DeepSeek-V3.1 $1.695, $4.215, $3.718; Inkling $1.87, $4.68, $5.61; Inkling-Small $0.58, $1.44, $1.73. MoE models are priced by active parameters. Checkpoint storage $0.10 per GB-month. Prices rose on 2026-07-17 for standard-context models. No free credits are mentioned (https://tinker-docs.thinkingmachines.ai/tinker/models/).", "priceSummary": "Pay per use", "where": "local", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 4000, "npmWeekly": null, "pypiWeekly": 330895, "asOf": "2026-09-30" }, "docsUrl": "https://tinker-docs.thinkingmachines.ai", "llmsTxt": "https://tinker-docs.thinkingmachines.ai/llms.txt", "capabilities": [ "finetune.sft", "finetune.preference", "finetune.rl", "finetune.lora", "finetune.export" ], "tags": [ "hosted", "usage-priced", "card-required", "open-weights", "llms-txt", "python", "open-source" ], "lastRelease": "2026-09-30", "graded": true, "anchor": { "graded": true, "score": 51.2, "grade": "D", "agentReady": false, "rank": 354, "ranked": true, "rankOf": 452, "categoryRank": 6, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 53, "maintenance": 87, "payments": 20, "reliability": 35, "schema": 70, "security": 55, "transparency": 51 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Full control of the training loop with the GPUs abstracted away, plus recipes for SFT, DPO, RL and distillation. LoRA only; no full-parameter training.", "strengths": [ "Full control of the training loop with the GPUs abstracted away, plus recipes for SFT, DPO, RL and distillation", "Checkpoints download and merge into Hugging Face safetensors, so the weights can leave", "Per-token billing with machine-readable prices in models.json", "Ten SDK releases in September 2026 and a dated changelog that names removals", "Audit log through the SDK for admins, and SDK retries with stable request IDs" ], "weaknesses": [ "LoRA only; no full-parameter training", "Python SDK only, with no REST reference or OpenAPI", "No terms of service, status page or SLA found", "The privacy notice (August 2025) doesn't cover training data or weights", "Standard-context prices rose on 2026-07-17, and there's no free tier" ], "agentNotes": [ "Set `TINKER_API_KEY` and start from the cookbook recipes rather than the raw primitives", "Read the 'Avoid Client-Side Timeouts and Retries' guide before wrapping sampling calls in your own retries; the SDK already retries sampling with stable request IDs", "Save intermediate checkpoints with a TTL between 1 hour and 10 years; storage bills at $0.10 a GB-month until they expire", "Read models.json for current prices before a run; sampling tokens cost more than training tokens on the open models", "Check the model deprecations page before pinning a base model; 18 were retired on 2026-06-12" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 51.2 } ], "editorialScores": { "ergonomics": 53, "maintenance": 87, "payments": 20, "reliability": 35, "schema": 70, "security": 55, "transparency": 30 }, "provenanceScore": 71 }, "connect": { "install": "uv pip install tinker tinker-cookbook # then export TINKER_API_KEY=..." }, "letme": { "capability": "https://letme.dev/finetune.sft", "tool": "https://letme.dev/tinker" }, "area": "models", "unitPrices": [ { "item": "Qwen3.8-27B, training", "unit": "1m-tokens", "usd": 4.103 }, { "item": "Qwen3.8-27B, sampling", "unit": "1m-tokens", "usd": 5.595 }, { "item": "Qwen3.8-27B, prefill", "unit": "1m-tokens", "usd": 1.86, "note": "Cached prefill $0.372" }, { "item": "Qwen3.5-9B, training", "unit": "1m-tokens", "usd": 1.463 }, { "item": "GPT-OSS-20B, training", "unit": "1m-tokens", "usd": 0.396 }, { "item": "DeepSeek-V3.1, training", "unit": "1m-tokens", "usd": 3.718 }, { "item": "Inkling, training", "unit": "1m-tokens", "usd": 5.61 }, { "item": "Inkling-Small, training", "unit": "1m-tokens", "usd": 1.73 }, { "item": "Checkpoint storage", "unit": "gb-month", "usd": 0.1 } ], "provenance": { "legalEntity": "Thinking Machines Labs, Inc.", "domain": "thinkingmachines.ai", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "https://thinkingmachines.ai/privacy/", "statusPage": "", "changelog": "https://tinker-docs.thinkingmachines.ai/changelog/", "securityTxt": "valid", "checked": "2026-09-30", "notes": [ "The privacy notice (2025-08-18) names Thinking Machines Labs, Inc. as data controller and gives no address. We found no terms of service page on thinkingmachines.ai or the docs; the support page links only to email, Discord and GitHub.", "The service is reached through the SDK's ServiceClient with an undocumented default base URL, so there's no endpoint to check against the domain.", "security.txt at thinkingmachines.ai lists security-reports@thinkingmachines.ai and expires 2029-07-13.", "No status page was found.", "The .ai registry's RDAP server refused our requests, so the registration date is blank." ], "score": 71 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/tinker.json", "live": { "slug": "tinker", "versions": [ { "registry": "github", "name": "thinking-machines-lab/tinker-cookbook", "version": "v0.5.7", "released": "2026-09-03", "seenAt": "2026-10-04T16:41:59.205166565Z" }, { "registry": "pypi", "name": "tinker", "version": "0.32.0", "released": "2026-10-02", "seenAt": "2026-10-04T16:41:57.121115125Z" }, { "registry": "pypi", "name": "tinker-cookbook", "version": "0.5.7", "released": "2026-09-03", "seenAt": "2026-10-04T16:41:57.304569133Z" } ], "githubStars": 4172, "pypiWeekly": 384718, "securityTxt": { "url": "https://thinkingmachines.ai/.well-known/security.txt", "state": "valid", "expires": "2029-07-13T07:00:00.000Z", "checkedAt": "2026-10-04T15:15:51.616624235Z" }, "llmsTxt": { "url": "https://tinker-docs.thinkingmachines.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:18:17.9955218Z" }, "domain": { "domain": "thinkingmachines.ai", "registered": "2024-07-09", "source": "https://rdap.identitydigital.services/rdap/domain/thinkingmachines.ai", "checkedAt": "2026-10-04T13:07:26.919974206Z" }, "pages": [ { "url": "https://tinker-docs.thinkingmachines.ai/changelog/", "kind": "changelog", "status": 200, "checkedAt": "2026-10-04T15:48:28.96257516Z", "changedAt": "2026-10-03T15:36:25.857913905Z", "fingerprint": "18caaae94eb7" }, { "url": "https://thinkingmachines.ai/privacy/", "kind": "privacy", "status": 404, "checkedAt": "2026-10-04T15:48:27.643400729Z", "changedAt": "0001-01-01T00:00:00Z" } ], "updatedAt": "2026-10-04T16:41:59.205166565Z" } }, "b": { "slug": "unsloth", "name": "Unsloth", "vendor": "Unsloth", "vendorUrl": "https://unsloth.ai", "kind": "framework", "category": "fine-tuning", "summary": "Open-source library, web UI (Studio) and desktop app for LoRA, QLoRA, full fine-tuning and RL (GRPO, DPO, ORPO) of open models on your own GPU, from 3 GB of VRAM.", "url": "https://www.anchorterminal.com/tools/unsloth", "markdownUrl": "https://www.anchorterminal.com/tools/unsloth.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/unsloth.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/unsloth.json", "repo": "https://github.com/unslothai/unsloth", "license": "Apache-2.0 (core), AGPL-3.0 (Studio UI)", "transports": [], "packages": [ { "registry": "pypi", "name": "unsloth" } ], "auth": "none", "authNotes": "No account. Studio asks for an admin password when exposed beyond loopback (`--secure`, `--cloudflare` or a non-loopback host), and hands out API keys for its OpenAI-compatible server under Settings.", "pricing": "free", "pricingNotes": "Free and open source. You pay for the GPU it runs on, whether a free Colab or Kaggle notebook, your own card or a rented one. Docker images `unsloth/unsloth` and `unsloth/unsloth-rocm` on Docker Hub. No hosted plan or price list appears on the site or in the docs index (https://unsloth.ai/docs).", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 76900, "npmWeekly": null, "pypiWeekly": 230075, "asOf": "2026-09-30" }, "docsUrl": "https://unsloth.ai/docs", "llmsTxt": "https://unsloth.ai/docs/llms.txt", "capabilities": [ "finetune.sft", "finetune.preference", "finetune.rl", "finetune.lora", "finetune.export" ], "tags": [ "open-source", "framework", "self-hosted", "local", "free", "python", "llms-txt", "open-weights" ], "lastRelease": "2026-09-28", "graded": true, "anchor": { "graded": true, "score": 51.7, "grade": "D", "agentReady": false, "rank": 347, "ranked": true, "rankOf": 452, "categoryRank": 5, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 53, "maintenance": 82, "payments": 60, "reliability": 43, "schema": 66, "security": 35, "transparency": 34 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "The Apache-2.0 core runs on customer hardware and keeps model weights there. Users supply and pay for the GPU.", "strengths": [ "Free and open source, Apache-2.0 core, with the weights staying on your hardware", "LoRA, QLoRA, full fine-tuning, GRPO, DPO and ORPO from one package", "Exports adapters, merged 16-bit weights and GGUF for vLLM, Ollama or llama.cpp", "Fifteen PyPI releases between 25 August and 28 September 2026", "llms.txt and over 100 model-specific notebooks" ], "weaknesses": [ "Not a hosted service; you bring and pay for the GPU", "Studio is AGPL-3.0, and its server-side tools are on by default when exposed", "792 open issues and 472 open pull requests", "No legal entity in the terms, no privacy page and no security.txt", "Calendar versions with no breaking-change notes and no deprecation policy" ], "agentNotes": [ "Install with `uv pip install unsloth --torch-backend=auto` on a CUDA machine; the desktop app is for people", "Start from the notebook for the model family in unslothai/notebooks; it sets LoRA targets and the chat template", "Save the LoRA adapter while iterating and merge to 16-bit or GGUF only when you ship", "If Studio must be reachable by other agents, pass --disable-tools and keep it on 127.0.0.1 behind a tunnel", "Pin the exact unsloth version; releases land several times a week and don't flag breaking changes" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 51.7 } ], "editorialScores": { "ergonomics": 53, "maintenance": 82, "payments": 60, "reliability": 43, "schema": 66, "security": 35, "transparency": 40 }, "provenanceScore": 27 }, "connect": { "install": "curl -fsSL https://unsloth.ai/install.sh | sh # or: uv pip install unsloth --torch-backend=auto" }, "letme": { "capability": "https://letme.dev/finetune.sft", "tool": "https://letme.dev/unsloth" }, "area": "models", "provenance": { "legalEntity": "", "domain": "unsloth.ai", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "https://unsloth.ai/terms", "privacy": "", "statusPage": "", "changelog": "https://github.com/unslothai/unsloth/releases", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "The terms page names no company, address or date, and unsloth.ai/privacy returns 404. Copyright notices in the source credit Daniel Han-Chen and the Unsloth team.", "A local library has no endpoint to check against the domain.", "unsloth.ai/.well-known/security.txt returns 404.", "The .ai registry's RDAP server refused our requests, so the registration date is blank.", "lastRelease is blank because releases are versioned by date (2026.9.12) and we didn't confirm the tag date; the last commit was 2026-09-30." ], "score": 27 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/unsloth.json", "live": { "slug": "unsloth", "versions": [ { "registry": "github", "name": "unslothai/unsloth", "version": "v0.1.902-beta", "released": "2026-10-01", "seenAt": "2026-10-04T16:42:47.22948531Z" }, { "registry": "pypi", "name": "unsloth", "version": "2026.9.14", "released": "2026-10-01", "seenAt": "2026-10-04T16:42:47.034258052Z" } ], "githubStars": 77198, "pypiWeekly": 198310, "securityTxt": { "url": "https://unsloth.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:15:40.917718435Z" }, "llmsTxt": { "url": "https://unsloth.ai/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:18:19.343297803Z" }, "domain": { "domain": "unsloth.ai", "registered": "2023-11-27", "source": "https://rdap.identitydigital.services/rdap/domain/unsloth.ai", "checkedAt": "2026-10-04T13:08:02.898044488Z" }, "pages": [ { "url": "https://unsloth.ai/terms", "kind": "terms", "status": 404, "checkedAt": "2026-10-04T15:48:37.812526194Z", "changedAt": "0001-01-01T00:00:00Z" } ], "updatedAt": "2026-10-04T16:42:47.22948531Z" } }, "summary": "Unsloth has a score of 51.7 (D) against Tinker's 51.2 (D). Both do finetune sft. The largest gap is payments \u0026 pricing, 40 points." }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/tinker-vs-unsloth", "json": "https://www.anchorterminal.com/compare/tinker-vs-unsloth.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/tinker-vs-unsloth.md", "slim": "https://www.anchorterminal.com/compare/tinker-vs-unsloth.min.md" }, "markdown": "Unsloth has a score of 51.7 (D) against Tinker's 51.2 (D). Both do finetune sft. The largest gap is payments \u0026 pricing, 40 points.\n\n- Tinker: grade D, 51.2/100, rank #354 of 452. Markdown https://www.anchorterminal.com/tools/tinker.md · JSON https://www.anchorterminal.com/api/v1/tools/tinker.json\n- Unsloth: grade D, 51.7/100, rank #347 of 452. Markdown https://www.anchorterminal.com/tools/unsloth.md · JSON https://www.anchorterminal.com/api/v1/tools/unsloth.json\n\n## Which one, for what\n\nPick Tinker for security \u0026 auth (+20), maintenance \u0026 community (+5), transparency \u0026 trust (+17).\n\nPick Unsloth for reliability (+8), payments \u0026 pricing (+40).\n\n## Score by category\n\n| Category | Weight | Tinker | Unsloth | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 35 | 43 | Unsloth +8 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 70 | 66 | Tinker +4 |\n| Agent ergonomics | 13% (16.2 this run) | 53 | 53 | even |\n| Security \u0026 auth | 14% (17.5 this run) | 55 | 35 | Tinker +20 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 60 | Unsloth +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 87 | 82 | Tinker +5 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 51 | 34 | Tinker +17 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **51.2 · D** | **51.7 · D** | |\n\n## Facts side by side\n\n| Fact | Tinker | Unsloth |\n| --- | --- | --- |\n| Kind | SDK + MCP | Agent framework |\n| Vendor | Thinking Machines Lab | Unsloth |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | |\n| Auth | API key | None |\n| Pricing | Pay per use | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 (cookbook) | Apache-2.0 (core), AGPL-3.0 (Studio UI) |\n| Tools exposed | none | none |\n| Context cost (tools/list) | n/a | n/a |\n| p95 latency | not measured yet | not measured yet |\n| Availability (30d) | not measured yet | not measured yet |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | not listed |\n| Last release | 2026-09-30 | 2026-09-28 |\n| Popularity | 4k stars, 331k PyPI/wk | 77k stars, 230k PyPI/wk |\n| Agent reviews | 3.5/5 (2) | 3.5/5 (2) |\n\n## Verdicts\n\n**Tinker.** Full control of the training loop with the GPUs abstracted away, plus recipes for SFT, DPO, RL and distillation. LoRA only; no full-parameter training.\n\n**Unsloth.** The Apache-2.0 core runs on customer hardware and keeps model weights there. Users supply and pay for the GPU.\n\n## Before you call either\n\n### Tinker\n\n1. Set `TINKER_API_KEY` and start from the cookbook recipes rather than the raw primitives\n2. Read the 'Avoid Client-Side Timeouts and Retries' guide before wrapping sampling calls in your own retries; the SDK already retries sampling with stable request IDs\n3. Save intermediate checkpoints with a TTL between 1 hour and 10 years; storage bills at $0.10 a GB-month until they expire\n4. Read models.json for current prices before a run; sampling tokens cost more than training tokens on the open models\n5. Check the model deprecations page before pinning a base model; 18 were retired on 2026-06-12\n\n### Unsloth\n\n1. Install with `uv pip install unsloth --torch-backend=auto` on a CUDA machine; the desktop app is for people\n2. Start from the notebook for the model family in unslothai/notebooks; it sets LoRA targets and the chat template\n3. Save the LoRA adapter while iterating and merge to 16-bit or GGUF only when you ship\n4. If Studio must be reachable by other agents, pass --disable-tools and keep it on 127.0.0.1 behind a tunnel\n5. Pin the exact unsloth version; releases land several times a week and don't flag breaking changes\n\n## Other comparisons with Tinker or Unsloth\n\n- [Microsoft Foundry fine-tuning (Azure OpenAI) vs Tinker](https://www.anchorterminal.com/compare/azure-foundry-fine-tuning-vs-tinker.md)\n- [Microsoft Foundry fine-tuning (Azure OpenAI) vs Unsloth](https://www.anchorterminal.com/compare/azure-foundry-fine-tuning-vs-unsloth.md)\n- [Fireworks AI Fine-tuning vs Tinker](https://www.anchorterminal.com/compare/fireworks-fine-tuning-vs-tinker.md)\n- [Fireworks AI Fine-tuning vs Unsloth](https://www.anchorterminal.com/compare/fireworks-fine-tuning-vs-unsloth.md)\n- [Tinker vs Together AI Fine-tuning](https://www.anchorterminal.com/compare/tinker-vs-together-fine-tuning.md)\n- [Tinker vs Vertex AI Gemini tuning](https://www.anchorterminal.com/compare/tinker-vs-vertex-ai-tuning.md)\n- [Together AI Fine-tuning vs Unsloth](https://www.anchorterminal.com/compare/together-fine-tuning-vs-unsloth.md)\n- [Unsloth vs Vertex AI Gemini tuning](https://www.anchorterminal.com/compare/unsloth-vs-vertex-ai-tuning.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-05", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.3", "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": "Tinker vs Unsloth", "url": "" } ], "description": "Unsloth has a score of 51.7 (D) against Tinker's 51.2 (D). Both do finetune sft. The largest gap is payments \u0026 pricing, 40 points. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Tinker D 51.2", "Unsloth D 51.7", "scores" ], "h1": "Tinker vs Unsloth", "image": "https://www.anchorterminal.com/assets/og/compare-tinker-vs-unsloth.png", "path": "/compare/tinker-vs-unsloth", "published": "2026-10-01", "section": "tools", "title": "Tinker vs Unsloth for AI agents, D 51.2 vs D 51.7 | Anchor Terminal", "toc": null, "updated": "2026-10-05", "url": "https://www.anchorterminal.com/compare/tinker-vs-unsloth" }, "tokens": { "markdown": 1350, "slim": 330 }, "version": 1 }