# Amazon Bedrock model customisation (slim)

> Managed supervised fine-tuning, reinforcement fine-tuning and distillation of Amazon Nova, Meta Llama and selected open-weight models on Amazon Bedrock, run as asynchronous jobs through the Bedrock control-plane API, the AWS SDKs and CLI, or OpenAI-compatible endpoints.

- Full: https://www.anchorterminal.com/tools/amazon-bedrock-customization.md (~9,300 tokens) · this version ~1,830 tokens · JSON https://www.anchorterminal.com/tools/amazon-bedrock-customization.json · canonical https://www.anchorterminal.com/tools/amazon-bedrock-customization
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

**BB · 75.8/100 · rank #39 of 842 · #1 in Fine-tuning · agent-ready · confidence medium**


Assessment: 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.

## Facts

- Kind: HTTP API · vendor: Amazon Web Services · category: Fine-tuning · legal entity: Amazon Web Services, Inc. · provenance 88/100
- Endpoint: `https://bedrock.{region}.amazonaws.com/model-customization-jobs` (HTTP)
- Auth: OAuth or key · pricing: Pay per use · x402: no · licence: unknown
- Probe metrics: not measured yet (probes haven't run)
- Methods: Supervised fine-tuning, reinforcement fine-tuning with a Lambda or model-judge reward function, distillation, and continued pre-training in the API enum
- Base models: Nova 2 Lite, Nova Lite, Micro, Pro and Canvas, Claude 3 Haiku, Llama 3.1 8B and 70B, Llama 3.2 1B, 3B, 11B and 90B, Llama 3.3 70B, Titan Image Generator G1 v2, Titan Multimodal Embeddings G1. Reinforcement only for Nova 2 Lite, gpt-oss-20B and Qwen3 32B
- Regions: us-east-1 for Nova, us-west-2 for Llama, Claude 3 Haiku, gpt-oss-20B and Qwen3 32B, both for the Titan models
- Weights: No export found. Custom models are stored and managed by AWS, and can be copied to another Region or shared with another AWS account
- Serving: On-demand deployment at base-model token prices for Nova Lite, Nova 2 Lite, Micro, Pro and Llama 3.3 70B. Provisioned Throughput by the model-unit hour otherwise ($24 an hour for Llama 3.1 8B with no commitment)
- Storage: $1.95 per custom model per month
- Reinforcement fine-tuning price: $80 per training hour for Nova 2 Lite, gpt-oss-20b and Qwen3 32B
- Data source: JSONL in Amazon S3 in the job's Region, or Bedrock invocation logs. The OpenAI-compatible route uploads through the Files API
- Quotas: 10 scheduled customisation jobs, 2 custom models in creating status, 100 custom models and 10 custom model deployments per Region. 20,000 records per Nova 2 Lite job and 10,000 per Llama 3.3 70B job
- Free tier: None for customisation on the pricing page. New AWS accounts get up to $200 in Free Tier credits over six months
- Prices: Nova 2 Lite, supervised fine-tuning $3.78 per 1M tokens; Nova Pro, supervised fine-tuning $8 per 1M tokens; Nova Lite, supervised fine-tuning $2 per 1M tokens; Nova Micro, supervised fine-tuning $1 per 1M tokens; Llama 3.1 70B Instruct, fine-tuning $7.99 per 1M tokens; Llama 3.1 8B Instruct, fine-tuning $1.49 per 1M tokens; Llama 3.2 90B Instruct, fine-tuning $7.90 per 1M tokens; Llama 3.2 11B Instruct, fine-tuning $3.50 per 1M tokens; Llama 3.2 3B Instruct, fine-tuning $1.10 per 1M tokens; Llama 3.2 1B Instruct, fine-tuning $0.50 per 1M tokens

- Scores: Reliability 95, Performance pending, Schema & documentation 87, Agent ergonomics 77, Security & auth 87, Payments & pricing 30, Task success pending, Maintenance & community 45, Transparency & trust 83 · total over the 7 assessed categories
- Why: Reliability, Graded on the hosted lines. · Schema & documentation, AWS publishes the Bedrock service model (API version 2023-04-20, 108 operations) that the SDKs are generated from, and the API reference giv… · Agent ergonomics, List calls return job summaries, not full job objects, and `maxResults` runs from 1 to 1,000. No field selection (15 of 25). · Security & auth, IAM with Signature Version 4, roles and short-lived credentials, and policies per action and resource. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, The newest customisation API change found is `ModelPackageArn` on `CreateCustomModel` in boto3 1.43.17, uploaded on 28 May 2026, 133 days be… · Transparency & trust, Closed service under the AWS Customer Agreement and Service Terms.
- Sources: 38, open questions: 11, both in the full twin
- Capabilities: finetune.sft, finetune.rl
- JSON: https://www.anchorterminal.com/api/v1/tools/amazon-bedrock-customization.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/amazon-bedrock-customization.svg` or a link to https://www.anchorterminal.com/tools/amazon-bedrock-customization from a page on aws.amazon.com or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

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

## Connect

```bash
pip install boto3   # or: npm i @aws-sdk/client-bedrock
```

```bash
curl -X POST "https://bedrock.us-east-1.amazonaws.com/model-customization-jobs" \
  --aws-sigv4 "aws:amz:us-east-1:bedrock" --user "$AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY" \
  -H "content-type: application/json" \
  -d '{"jobName":"my-tune","customModelName":"my-nova-tune","roleArn":"arn:aws:iam::123456789012:role/BedrockCustomisationRole","baseModelIdentifier":"amazon.nova-2-lite-v1:0:256k","clientRequestToken":"my-tune-001","trainingDataConfig":{"s3Uri":"s3://my-bucket/train.jsonl"},"outputDataConfig":{"s3Uri":"s3://my-bucket/output/"}}'
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/amazon-bedrock-customization

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Axolotl | B | 64.8 | finetune.sft, finetune.rl | https://www.anchorterminal.com/tools/axolotl.min.md |
| Vertex AI Gemini tuning | B | 64.2 | finetune.sft, finetune.rl | https://www.anchorterminal.com/tools/vertex-ai-tuning.min.md |
| Microsoft Foundry fine-tuning (Azure OpenAI) | C | 61.1 | finetune.sft, finetune.rl | https://www.anchorterminal.com/tools/azure-foundry-fine-tuning.min.md |
| Fireworks AI Fine-tuning | C | 59 | finetune.sft, finetune.rl | https://www.anchorterminal.com/tools/fireworks-fine-tuning.min.md |
| Unsloth | D | 51.5 | finetune.sft, finetune.rl | https://www.anchorterminal.com/tools/unsloth.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)