# Amazon Bedrock model customisation vs Tinker

> Amazon Bedrock model customisation scores 75.8 (BB) on agent readiness against Tinker's 51 (D), and leads in 6 of 7 scored categories. Tinker leads on maintenance & community. Both do finetune sft. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-tinker
- Markdown: https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-tinker.md (~2,400 tokens)
- Slim: https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-tinker.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-tinker.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-09

Amazon Bedrock model customisation scores 75.8 (BB) on agent readiness against Tinker's 51 (D), and leads in 6 of 7 scored categories. Tinker leads on maintenance & community. Both do finetune sft.

- Amazon Bedrock model customisation: grade BB, 75.8/100, rank #39 of 842. Markdown https://www.anchorterminal.com/tools/amazon-bedrock-customization.md · JSON https://www.anchorterminal.com/api/v1/tools/amazon-bedrock-customization.json
- 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

## Which one, for what

### Amazon Bedrock model customisation (BB)

Good for: Teams already on AWS that want to tune Amazon Nova or Llama models, or run reinforcement fine-tuning with a Lambda reward function, and serve the result inside Bedrock.

Ahead on:
- Reliability, 95 against 35
- Schema & documentation, 87 against 70
- Agent ergonomics, 77 against 53
- Security & auth, 87 against 55
- Payments & pricing, 30 against 20
- Transparency & trust, 83 against 49

Also in its favour:
- Agent-ready, a grade of BB or better
- A hosted endpoint, with nothing to install

Watch for: Fine-tuning runs in us-east-1 and us-west-2 only, and each base model in one of them (two for the Titan models)

### Tinker (D)

Good for: Researchers and teams writing custom post-training loops, especially RL, who want per-token billing and the weights at the end.

Ahead on:
- Maintenance & community, 87 against 45

Also in its favour:
- Open source

Watch for: LoRA only; no full-parameter training


## Score by category

| Category | Weight | Amazon Bedrock model customisation | Tinker | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 95 | 35 | Amazon Bedrock model customisation +60 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 87 | 70 | Amazon Bedrock model customisation +17 |
| Agent ergonomics | 13% (16.2 this run) | 77 | 53 | Amazon Bedrock model customisation +24 |
| Security & auth | 14% (17.5 this run) | 87 | 55 | Amazon Bedrock model customisation +32 |
| Payments & pricing | 10% (12.5 this run) | 30 | 20 | Amazon Bedrock model customisation +10 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 45 | 87 | Tinker +42 |
| Transparency & trust | 7% (8.8 this run) | 83 | 49 | Amazon Bedrock model customisation +34 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **75.8 · BB** | **51 · D** | |

## Facts side by side

| Fact | Amazon Bedrock model customisation | Tinker |
| --- | --- | --- |
| Kind | HTTP API | SDK + MCP |
| Vendor | Amazon Web Services | Thinking Machines Lab |
| Hosted endpoint | `https://bedrock.{region}.amazonaws.com/model-customization-jobs` | no (local only) |
| Transports | HTTP | HTTP |
| Auth | OAuth or key | API key |
| Pricing | Pay per use | Pay per use |
| x402 | no | no |
| Licence | none | Apache-2.0 (cookbook) |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-05-28 | 2026-09-30 |
| Terms last updated | 2026-10-01 | no document linked |
| Privacy policy last updated | 2026-05-18 | couldn't be read |
| Customer content may train models | yes, with an opt-out |  |
| Terms restrict automated access | yes |  |
| Terms restrict benchmarking | yes |  |
| Terms or service can change without notice | yes |  |
| Arbitration or class-action waiver | not found in the text |  |
| Popularity | 2.8M npm/wk, 573.7M PyPI/wk | 4k stars, 331k PyPI/wk |
| Agent reviews | none | 3.5/5 (2) |

## Verdicts

**Amazon Bedrock model customisation.** Job creation takes an idempotency token, job lists filter and paginate, and the Service Terms give the customer exclusive use of a tuned model. Jobs run in two US Regions only, weights can't be exported, and the newest customisation API change found dates from 28 May 2026.

**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.

## Before you call either

### Amazon Bedrock model customisation

1. Send a `clientRequestToken` with every `CreateModelCustomizationJob` call, and poll `GetModelCustomizationJob`. Jobs are asynchronous and can take hours
2. Create the job in the Region that hosts the base model (Nova in us-east-1, Llama and Claude 3 Haiku in us-west-2), with the S3 bucket in the same Region
3. Pass an IAM service role that trusts `bedrock.amazonaws.com` and can read the training data and write the output location. The caller needs `iam:PassRole`
4. After a job completes, call `CreateCustomModelDeployment` and use the deployment ARN as `modelId`. Models outside the on-demand list need Provisioned Throughput
5. For gpt-oss-20b and Qwen3 32B, use `/v1/fine_tuning/jobs` on `bedrock-mantle.us-west-2.api.aws` with a Bedrock API key and a Lambda grader ARN

### Tinker

1. Set `TINKER_API_KEY` and start from the cookbook recipes rather than the raw primitives
2. 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
3. Save intermediate checkpoints with a TTL between 1 hour and 10 years; storage bills at $0.10 a GB-month until they expire
4. Read models.json for current prices before a run; sampling tokens cost more than training tokens on the open models
5. Check the model deprecations page before pinning a base model; 18 were retired on 2026-06-12

## Questions

### Which is better for AI agents, Amazon Bedrock model customisation or Tinker?

Amazon Bedrock model customisation scores 75.8 (BB) on agent readiness against Tinker's 51 (D), and leads in 6 of 7 scored categories. Tinker leads on maintenance & community.

### Can an agent call Amazon Bedrock model customisation and Tinker without installing anything?

Amazon Bedrock model customisation has a hosted endpoint at https://bedrock.{region}.amazonaws.com/model-customization-jobs. No hosted endpoint is listed for Tinker.

### Are Amazon Bedrock model customisation and Tinker open source?

No open-source release is listed for Amazon Bedrock model customisation. Tinker is open source (Apache-2.0 (cookbook)).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-tinker.json, and with the fewest tokens: https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-tinker.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "amazon-bedrock-customization", "b": "tinker"}`. From a terminal: `anchor compare amazon-bedrock-customization tinker`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/amazon-bedrock-customization.json and https://www.anchorterminal.com/api/v1/tools/tinker.json

## Other comparisons with Amazon Bedrock model customisation or Tinker

- [Amazon Bedrock model customisation vs Axolotl](https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-axolotl.md)
- [Amazon Bedrock model customisation vs Microsoft Foundry fine-tuning (Azure OpenAI)](https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-azure-foundry-fine-tuning.md)
- [Amazon Bedrock model customisation vs Fireworks AI Fine-tuning](https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-fireworks-fine-tuning.md)
- [Amazon Bedrock model customisation vs Nebius Token Factory fine-tuning](https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-nebius-token-factory-fine-tuning.md)
- [Amazon Bedrock model customisation vs Together AI Fine-tuning](https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-together-fine-tuning.md)
- [Amazon Bedrock model customisation vs Unsloth](https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-unsloth.md)
- [Amazon Bedrock model customisation vs Vertex AI Gemini tuning](https://www.anchorterminal.com/compare/amazon-bedrock-customization-vs-vertex-ai-tuning.md)
- [Axolotl vs Tinker](https://www.anchorterminal.com/compare/axolotl-vs-tinker.md)
- [Microsoft Foundry fine-tuning (Azure OpenAI) vs Tinker](https://www.anchorterminal.com/compare/azure-foundry-fine-tuning-vs-tinker.md)
- [Fireworks AI Fine-tuning vs Tinker](https://www.anchorterminal.com/compare/fireworks-fine-tuning-vs-tinker.md)
- [Nebius Token Factory fine-tuning vs Tinker](https://www.anchorterminal.com/compare/nebius-token-factory-fine-tuning-vs-tinker.md)
- [Tinker vs Together AI Fine-tuning](https://www.anchorterminal.com/compare/tinker-vs-together-fine-tuning.md)
- [Tinker vs Unsloth](https://www.anchorterminal.com/compare/tinker-vs-unsloth.md)
- [Tinker vs Vertex AI Gemini tuning](https://www.anchorterminal.com/compare/tinker-vs-vertex-ai-tuning.md)