{ "data": { "a": { "slug": "axolotl", "name": "Axolotl", "vendor": "Axolotl AI", "vendorUrl": "https://axolotl.ai", "kind": "framework", "category": "fine-tuning", "summary": "Open-source command-line tool and Python package for fine-tuning open language models from one YAML config, covering LoRA, QLoRA, full fine-tuning, preference tuning and GRPO on the owner's GPUs.", "url": "https://www.anchorterminal.com/tools/axolotl", "markdownUrl": "https://www.anchorterminal.com/tools/axolotl.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/axolotl.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/axolotl.json", "repo": "https://github.com/axolotl-ai-cloud/axolotl", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "pypi", "name": "axolotl" }, { "registry": "oci", "name": "axolotlai/axolotl" } ], "auth": "none", "authNotes": "No account or key of its own. Gated models and Hub uploads use the owner's Hugging Face token, and Weights \u0026 Biases, MLflow or Trackio logging uses those services' own credentials from the environment.", "pricing": "free", "pricingNotes": "Free and Apache-2.0, with no price list or hosted plan on axolotl.ai. The owner pays for the GPU, whether local, a rented machine or Hugging Face Jobs billed by the minute. Dedicated support is by email with no published price.", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or the source (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 12541, "npmWeekly": null, "pypiWeekly": 2124, "asOf": "2026-10-08" }, "docsUrl": "https://docs.axolotl.ai/", "capabilities": [ "finetune.sft", "finetune.lora", "finetune.preference", "finetune.rl", "finetune.export" ], "tags": [ "open-source", "framework", "self-hosted", "local", "free", "python", "docker", "open-weights" ], "lastRelease": "2026-09-30", "graded": true, "anchor": { "graded": true, "score": 64.8, "grade": "B", "agentReady": false, "rank": 307, "ranked": true, "rankOf": 842, "categoryRank": 2, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 60, "maintenance": 88, "payments": 60, "reliability": 64, "schema": 80, "security": 52, "transparency": 56 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "Axolotl runs a whole fine-tuning job from one YAML file and ships a JSON Schema of its config plus bundled agent docs. It is 0.x software with telemetry on by default, no terms or privacy policy, and the owner supplies the GPU.", "bestFor": "A team that wants a repeatable, config-driven fine-tune of an open model on its own or rented GPUs, including multi-GPU and multi-node runs.", "strengths": [ "Apache-2.0, free, and the weights stay on the owner's hardware", "`axolotl config-schema` prints the full config as JSON Schema, and `axolotl agent-docs` prints bundled Markdown references by topic", "SFT, LoRA, QLoRA, DPO, IPO, KTO, ORPO, GRPO and reward modelling from one config format", "Three releases in the 90 days to 8 October 2026, each with a Deprecations section naming removed options", "Telemetry is documented field by field and `AXOLOTL_DO_NOT_TRACK=1` turns it off" ], "weaknesses": [ "Telemetry to PostHog is on by default and delays training start by 10 seconds until the variable is set either way", "No terms of service, privacy policy, legal entity or security.txt found on axolotl.ai", "Version 0.20.0, with removals in minor releases (FSDP1 in 0.20.0, `relora_steps` renamed in 0.17.0 with no shim)", "Three of the last six push runs of the Tests workflow on main passed, and the nightly run against upstream failed on 7 and 8 October 2026", "Not a hosted service, so there is no job API, status page or SLA" ], "agentNotes": [ "Set `AXOLOTL_DO_NOT_TRACK=1` before any command, or training waits 10 seconds and sends usage events to PostHog", "Run `axolotl agent-docs` and `axolotl config-schema --field \u003cname\u003e` before writing a config; both work offline from the installed package", "Install torch first, then `uv pip install --no-build-isolation axolotl[deepspeed]`, on Python 3.12 or later with PyTorch 2.13 or later", "Take example configs from the same release tag as the installed version; minor releases remove and rename config keys", "Resume an interrupted run with `axolotl train config.yml --resume-from-checkpoint \u003cpath\u003e`, then `axolotl merge-lora` and `axolotl export` only when shipping" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.8 } ], "editorialScores": { "ergonomics": 60, "maintenance": 88, "payments": 60, "reliability": 64, "schema": 80, "security": 52, "transparency": 75 }, "provenanceScore": 36 }, "connect": { "install": "uv pip install torch==2.14.0 torchvision \u0026\u0026 uv pip install --no-build-isolation axolotl[deepspeed] # or: docker run --gpus '\"all\"' --ipc=host --rm -it axolotlai/axolotl:main-latest", "headless": { "command": "axolotl train config.yml", "env": { "AXOLOTL_DO_NOT_TRACK": "1" } } }, "letme": { "capability": "https://letme.dev/finetune.sft", "tool": "https://letme.dev/axolotl" }, "area": "models", "provenance": { "legalEntity": "", "domain": "axolotl.ai", "domainRegistered": "2022-08-02", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/axolotl-ai-cloud/axolotl/releases", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "No legal entity is named on axolotl.ai, in the docs or in the repository. The GitHub organisation is axolotl-ai-cloud and the citation file credits the Axolotl maintainers and contributors.", "The vendor publishes no terms of service or privacy policy (axolotl.ai/terms and /privacy return 404), so both links are left out. The telemetry page is the only data-handling statement.", "Local software has no endpoint to check against the domain.", "axolotl.ai/.well-known/security.txt and /security.txt return 404. The repository's `.github/SECURITY.md` gives an email address for reports.", "RDAP shows axolotl.ai registered on 2 August 2022 and transferred on 11 April 2024." ], "score": 36 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/axolotl.json" }, "answer": "Axolotl scores 64.8 (B) on agent readiness against Tinker's 51 (D), and leads in 6 of 7 scored categories.", "b": { "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, "grade": "D", "agentReady": false, "rank": 677, "ranked": true, "rankOf": 842, "categoryRank": 8, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 53, "maintenance": 87, "payments": 20, "reliability": 35, "schema": 70, "security": 55, "transparency": 49 }, "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.", "bestFor": "Researchers and teams writing custom post-training loops, especially RL, who want per-token billing and the weights at the end.", "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": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 51 } ], "editorialScores": { "ergonomics": 53, "maintenance": 87, "payments": 20, "reliability": 35, "schema": 70, "security": 55, "transparency": 30 }, "provenanceScore": 67 }, "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": 67 }, "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": "2026-10-08T16:32:11.324997657Z" }, { "registry": "pypi", "name": "tinker", "version": "0.32.0", "released": "2026-10-02", "seenAt": "2026-10-08T16:32:09.236417949Z" }, { "registry": "pypi", "name": "tinker-cookbook", "version": "0.5.7", "released": "2026-09-03", "seenAt": "2026-10-08T16:32:09.427353039Z" } ], "githubStars": 4179, "pypiWeekly": 421815, "securityTxt": { "url": "https://thinkingmachines.ai/.well-known/security.txt", "state": "valid", "expires": "2029-07-13T07:00:00.000Z", "checkedAt": "2026-10-08T15:38:33.720455026Z" }, "llmsTxt": { "url": "https://tinker-docs.thinkingmachines.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-08T14:00:56.670858456Z" }, "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": "2026-10-08T18:25:16.191875788Z", "changedAt": "2026-10-06T16:13:08.925985263Z", "fingerprint": "18093297ee7c" }, { "url": "https://thinkingmachines.ai/privacy/", "kind": "privacy", "status": 404, "checkedAt": "2026-10-08T18:25:14.907567846Z", "changedAt": "0001-01-01T00:00:00Z" } ], "updatedAt": "2026-10-08T18:25:16.191875788Z" } }, "facts": [ { "a": "Agent framework", "b": "SDK + MCP", "name": "Kind" }, { "a": "Axolotl AI", "b": "Thinking Machines Lab", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "API key", "name": "Auth" }, { "a": "Free", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "Apache-2.0 (cookbook)", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-09-30", "b": "2026-09-30", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "13k stars, 2.1k PyPI/wk", "b": "4k stars, 331k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3.5/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Axolotl scores 64.8 (B) on agent readiness against Tinker's 51 (D), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, Axolotl or Tinker?" }, { "answer": "Yes. Axolotl is open source (Apache-2.0). Tinker is open source (Apache-2.0 (cookbook)).", "question": "Are Axolotl and Tinker open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 64 against 35", "Schema \u0026 documentation, 80 against 70", "Agent ergonomics, 60 against 53", "Payments \u0026 pricing, 60 against 20", "Transparency \u0026 trust, 56 against 49" ], "also": [ "No key needed to call it" ], "goodFor": "A team that wants a repeatable, config-driven fine-tune of an open model on its own or rented GPUs, including multi-GPU and multi-node runs.", "slug": "axolotl", "watchFor": "Telemetry to PostHog is on by default and delays training start by 10 seconds until the variable is set either way" }, { "aheadOn": null, "also": null, "goodFor": "Researchers and teams writing custom post-training loops, especially RL, who want per-token billing and the weights at the end.", "slug": "tinker", "watchFor": "LoRA only; no full-parameter training" } ], "job": { "capability": "finetune.sft", "name": "Finetune sft" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-axolotl.json", "title": "Amazon Bedrock model customisation vs Axolotl", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-axolotl" }, { "json": "https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-tinker.json", "title": "Amazon Bedrock model customisation vs Tinker", "url": "https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-tinker" }, { "json": "https://www.anchorterminal.com/compare/axolotl-vs-azure-foundry-fine-tuning.json", "title": "Axolotl vs Microsoft Foundry fine-tuning (Azure OpenAI)", "url": "https://www.anchorterminal.com/compare/axolotl-vs-azure-foundry-fine-tuning" }, { "json": "https://www.anchorterminal.com/compare/axolotl-vs-fireworks-fine-tuning.json", "title": "Axolotl vs Fireworks AI Fine-tuning", "url": "https://www.anchorterminal.com/compare/axolotl-vs-fireworks-fine-tuning" }, { "json": "https://www.anchorterminal.com/compare/axolotl-vs-nebius-token-factory-fine-tuning.json", "title": "Axolotl vs Nebius Token Factory fine-tuning", "url": "https://www.anchorterminal.com/compare/axolotl-vs-nebius-token-factory-fine-tuning" }, { "json": "https://www.anchorterminal.com/compare/axolotl-vs-together-fine-tuning.json", "title": "Axolotl vs Together AI Fine-tuning", "url": "https://www.anchorterminal.com/compare/axolotl-vs-together-fine-tuning" }, { "json": "https://www.anchorterminal.com/compare/axolotl-vs-unsloth.json", "title": "Axolotl vs Unsloth", "url": "https://www.anchorterminal.com/compare/axolotl-vs-unsloth" }, { "json": "https://www.anchorterminal.com/compare/axolotl-vs-vertex-ai-tuning.json", "title": "Axolotl vs Vertex AI Gemini tuning", "url": "https://www.anchorterminal.com/compare/axolotl-vs-vertex-ai-tuning" }, { "json": "https://www.anchorterminal.com/compare/azure-foundry-fine-tuning-vs-tinker.json", "title": "Microsoft Foundry fine-tuning (Azure OpenAI) vs Tinker", "url": "https://www.anchorterminal.com/compare/azure-foundry-fine-tuning-vs-tinker" }, { "json": "https://www.anchorterminal.com/compare/fireworks-fine-tuning-vs-tinker.json", "title": "Fireworks AI Fine-tuning vs Tinker", "url": "https://www.anchorterminal.com/compare/fireworks-fine-tuning-vs-tinker" }, { "json": "https://www.anchorterminal.com/compare/nebius-token-factory-fine-tuning-vs-tinker.json", "title": "Nebius Token Factory fine-tuning vs Tinker", "url": "https://www.anchorterminal.com/compare/nebius-token-factory-fine-tuning-vs-tinker" }, { "json": "https://www.anchorterminal.com/compare/tinker-vs-together-fine-tuning.json", "title": "Tinker vs Together AI Fine-tuning", "url": "https://www.anchorterminal.com/compare/tinker-vs-together-fine-tuning" }, { "json": "https://www.anchorterminal.com/compare/tinker-vs-unsloth.json", "title": "Tinker vs Unsloth", "url": "https://www.anchorterminal.com/compare/tinker-vs-unsloth" }, { "json": "https://www.anchorterminal.com/compare/tinker-vs-vertex-ai-tuning.json", "title": "Tinker vs Vertex AI Gemini tuning", "url": "https://www.anchorterminal.com/compare/tinker-vs-vertex-ai-tuning" } ], "scores": [ { "axolotl": 64, "by": 29, "edge": "axolotl", "key": "reliability", "name": "Reliability", "tinker": 35, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "axolotl": 80, "by": 10, "edge": "axolotl", "key": "schema", "name": "Schema \u0026 documentation", "tinker": 70, "weight": 13 }, { "axolotl": 60, "by": 7, "edge": "axolotl", "key": "ergonomics", "name": "Agent ergonomics", "tinker": 53, "weight": 13 }, { "axolotl": 52, "by": 3, "edge": "tinker", "key": "security", "name": "Security \u0026 auth", "tinker": 55, "weight": 14 }, { "axolotl": 60, "by": 40, "edge": "axolotl", "key": "payments", "name": "Payments \u0026 pricing", "tinker": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "axolotl": 88, "by": 1, "edge": "axolotl", "key": "maintenance", "name": "Maintenance \u0026 community", "tinker": 87, "weight": 7 }, { "axolotl": 56, "by": 7, "edge": "axolotl", "key": "transparency", "name": "Transparency \u0026 trust", "tinker": 49, "weight": 7 } ], "summary": "Axolotl scores 64.8 (B) on agent readiness against Tinker's 51 (D), and leads in 6 of 7 scored categories. Both do finetune sft.", "verdicts": { "axolotl": "Axolotl runs a whole fine-tuning job from one YAML file and ships a JSON Schema of its config plus bundled agent docs. It is 0.x software with telemetry on by default, no terms or privacy policy, and the owner supplies the GPU.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/axolotl-vs-tinker", "json": "https://www.anchorterminal.com/compare/axolotl-vs-tinker.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/axolotl-vs-tinker.md", "slim": "https://www.anchorterminal.com/compare/axolotl-vs-tinker.min.md" }, "markdown": "Axolotl scores 64.8 (B) on agent readiness against Tinker's 51 (D), and leads in 6 of 7 scored categories. Both do finetune sft.\n\n- Axolotl: grade B, 64.8/100, rank #307 of 842. Markdown https://www.anchorterminal.com/tools/axolotl.md · JSON https://www.anchorterminal.com/api/v1/tools/axolotl.json\n- Tinker: grade D, 51/100, rank #677 of 842. Markdown https://www.anchorterminal.com/tools/tinker.md · JSON https://www.anchorterminal.com/api/v1/tools/tinker.json\n\n## Which one, for what\n\n### Axolotl (B)\n\nGood for: A team that wants a repeatable, config-driven fine-tune of an open model on its own or rented GPUs, including multi-GPU and multi-node runs.\n\nAhead on:\n- Reliability, 64 against 35\n- Schema \u0026 documentation, 80 against 70\n- Agent ergonomics, 60 against 53\n- Payments \u0026 pricing, 60 against 20\n- Transparency \u0026 trust, 56 against 49\n\nAlso in its favour:\n- No key needed to call it\n\nWatch for: Telemetry to PostHog is on by default and delays training start by 10 seconds until the variable is set either way\n\n### Tinker (D)\n\nGood for: Researchers and teams writing custom post-training loops, especially RL, who want per-token billing and the weights at the end.\n\nWatch for: LoRA only; no full-parameter training\n\n\n## Score by category\n\n| Category | Weight | Axolotl | Tinker | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 64 | 35 | Axolotl +29 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 80 | 70 | Axolotl +10 |\n| Agent ergonomics | 13% (16.2 this run) | 60 | 53 | Axolotl +7 |\n| Security \u0026 auth | 14% (17.5 this run) | 52 | 55 | Tinker +3 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 20 | Axolotl +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 88 | 87 | Axolotl +1 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 56 | 49 | Axolotl +7 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **64.8 · B** | **51 · D** | |\n\n## Facts side by side\n\n| Fact | Axolotl | Tinker |\n| --- | --- | --- |\n| Kind | Agent framework | SDK + MCP |\n| Vendor | Axolotl AI | Thinking Machines Lab |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | HTTP |\n| Auth | None | API key |\n| Pricing | Free | Pay per use |\n| x402 | no | no |\n| Licence | Apache-2.0 | Apache-2.0 (cookbook) |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-09-30 | 2026-09-30 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | couldn't be read |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Popularity | 13k stars, 2.1k PyPI/wk | 4k stars, 331k PyPI/wk |\n| Agent reviews | none | 3.5/5 (2) |\n\n## Verdicts\n\n**Axolotl.** Axolotl runs a whole fine-tuning job from one YAML file and ships a JSON Schema of its config plus bundled agent docs. It is 0.x software with telemetry on by default, no terms or privacy policy, and the owner supplies the GPU.\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## Before you call either\n\n### Axolotl\n\n1. Set `AXOLOTL_DO_NOT_TRACK=1` before any command, or training waits 10 seconds and sends usage events to PostHog\n2. Run `axolotl agent-docs` and `axolotl config-schema --field \u003cname\u003e` before writing a config; both work offline from the installed package\n3. Install torch first, then `uv pip install --no-build-isolation axolotl[deepspeed]`, on Python 3.12 or later with PyTorch 2.13 or later\n4. Take example configs from the same release tag as the installed version; minor releases remove and rename config keys\n5. Resume an interrupted run with `axolotl train config.yml --resume-from-checkpoint \u003cpath\u003e`, then `axolotl merge-lora` and `axolotl export` only when shipping\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## Questions\n\n### Which is better for AI agents, Axolotl or Tinker?\n\nAxolotl scores 64.8 (B) on agent readiness against Tinker's 51 (D), and leads in 6 of 7 scored categories.\n\n### Are Axolotl and Tinker open source?\n\nYes. Axolotl is open source (Apache-2.0). Tinker is open source (Apache-2.0 (cookbook)).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/axolotl-vs-tinker.json, and with the fewest tokens: https://www.anchorterminal.com/compare/axolotl-vs-tinker.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"axolotl\", \"b\": \"tinker\"}`. From a terminal: `anchor compare axolotl tinker`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/axolotl.json and https://www.anchorterminal.com/api/v1/tools/tinker.json\n\n## Other comparisons with Axolotl or Tinker\n\n- [Amazon Bedrock model customisation vs Axolotl](https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-axolotl.md)\n- [Amazon Bedrock model customisation vs Tinker](https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-tinker.md)\n- [Axolotl vs Microsoft Foundry fine-tuning (Azure OpenAI)](https://www.anchorterminal.com/compare/axolotl-vs-azure-foundry-fine-tuning.md)\n- [Axolotl vs Fireworks AI Fine-tuning](https://www.anchorterminal.com/compare/axolotl-vs-fireworks-fine-tuning.md)\n- [Axolotl vs Nebius Token Factory fine-tuning](https://www.anchorterminal.com/compare/axolotl-vs-nebius-token-factory-fine-tuning.md)\n- [Axolotl vs Together AI Fine-tuning](https://www.anchorterminal.com/compare/axolotl-vs-together-fine-tuning.md)\n- [Axolotl vs Unsloth](https://www.anchorterminal.com/compare/axolotl-vs-unsloth.md)\n- [Axolotl vs Vertex AI Gemini tuning](https://www.anchorterminal.com/compare/axolotl-vs-vertex-ai-tuning.md)\n- [Microsoft Foundry fine-tuning (Azure OpenAI) vs Tinker](https://www.anchorterminal.com/compare/azure-foundry-fine-tuning-vs-tinker.md)\n- [Fireworks AI Fine-tuning vs Tinker](https://www.anchorterminal.com/compare/fireworks-fine-tuning-vs-tinker.md)\n- [Nebius Token Factory fine-tuning vs Tinker](https://www.anchorterminal.com/compare/nebius-token-factory-fine-tuning-vs-tinker.md)\n- [Tinker vs Together AI Fine-tuning](https://www.anchorterminal.com/compare/tinker-vs-together-fine-tuning.md)\n- [Tinker vs Unsloth](https://www.anchorterminal.com/compare/tinker-vs-unsloth.md)\n- [Tinker vs Vertex AI Gemini tuning](https://www.anchorterminal.com/compare/tinker-vs-vertex-ai-tuning.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Axolotl vs Tinker", "url": "" } ], "description": "Axolotl scores 64.8 (B) on agent readiness against Tinker's 51 (D), and leads in 6 of 7 scored categories. Both do finetune sft. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Axolotl B 64.8", "Tinker D 51", "scores" ], "h1": "Axolotl vs Tinker", "image": "https://www.anchorterminal.com/assets/og/compare-axolotl-vs-tinker.png", "path": "/compare/axolotl-vs-tinker", "published": "2026-10-01", "section": "tools", "title": "Axolotl vs Tinker for AI agents, B 64.8 vs D 51 | Anchor Terminal", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/axolotl-vs-tinker" }, "tokens": { "markdown": 2000, "slim": 530 }, "version": 1 }