# Microsoft Foundry fine-tuning (Azure OpenAI) (slim)

> Azure's managed service for supervised, preference and reinforcement fine-tuning of supported OpenAI and open-weight models.

- Full: https://www.anchorterminal.com/tools/azure-foundry-fine-tuning.md (~6,950 tokens) · this version ~1,480 tokens · JSON https://www.anchorterminal.com/tools/azure-foundry-fine-tuning.json · canonical https://www.anchorterminal.com/tools/azure-foundry-fine-tuning
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**C · 61.4/100 · rank #228 of 452 · #2 in Fine-tuning · not agent-ready · confidence medium**


Assessment: SFT, DPO and RFT on GPT-4.1 and o4-mini through the OpenAI-shaped /openai/v1 API. No weight export; checkpoints copy only between Azure resources.

## Facts

- Kind: HTTP API · vendor: Microsoft Azure · category: Fine-tuning · legal entity: Microsoft Corporation · provenance 95/100
- Endpoint: `https://<resource>.openai.azure.com/openai/v1` (HTTP)
- Auth: OAuth or key · pricing: Pay per use · x402: no · licence: unknown
- Probe metrics: not measured yet (probes haven't run)
- Methods: SFT (text and vision), DPO, RFT with graders. LoRA adapters
- Base models: gpt-4.1 family, gpt-4o, gpt-4o-mini, o4-mini (RFT), gpt-5 (RFT, invitation), Ministral-3B, Qwen-32B, Llama-3.3-70B-Instruct, gpt-oss-20b
- Weights: No. Checkpoints copy between Azure resources only
- Serving: Standard, Global Standard, Provisioned Throughput or Developer deployments; base token prices plus $1.70 an hour except Developer
- Regions: Training in North Central US, Sweden Central and East US2, or global and developer tiers without data residency
- File limits: JSONL, UTF-8 with BOM, under 512 MB
- Idle deletion: Deployments unused for 15 days are removed; Developer deployments after 24 hours

- Scores: Reliability 65, Performance pending, Schema & documentation 67, Agent ergonomics 47, Security & auth 85, Payments & pricing 20, Task success pending, Maintenance & community 55, Transparency & trust 88 · total over the 7 assessed categories
- Why: Reliability, Azure status page with post-incident reviews kept for five years and Azure OpenAI Service as a listed component (20). · Schema & documentation, A REST reference on Learn for the v1 data plane and the management plane; we didn't open a spec file this run (15). · Agent ergonomics, Job objects are compact and list calls take `limit`; no field selection (10). · Security & auth, Microsoft Entra ID tokens with Azure RBAC, or two rotatable resource keys in the `api-key` header; the key gives full data-plane access to t… · Payments & pricing, No machine payment protocol (0). · Maintenance & community, Foundry's 'what's new' for August 2026 was published on 1 September, and the docs carry fine-tuning retirement dates; no API release dated i… · Transparency & trust, Closed service under the Microsoft Product Terms, whose generative AI clause rules out training foundation models on Customer Data, and the…
- Sources: 12, open questions: 4, both in the full twin
- Capabilities: finetune.sft, finetune.preference, finetune.rl, finetune.lora
- JSON: https://www.anchorterminal.com/api/v1/tools/azure-foundry-fine-tuning.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/azure-foundry-fine-tuning.svg` or a link to https://www.anchorterminal.com/tools/azure-foundry-fine-tuning from a page on microsoft.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. Point the OpenAI SDK at https://<resource>.openai.azure.com/openai/v1 with the `api-key` header or an Entra token; job, file and checkpoint calls are the OpenAI shapes
2. Read prices from the Azure Retail Prices API (meters named like 'gpt-4.1 FT Training global'), not the pricing page, which needs a browser
3. Keep at most 3 jobs running and 20 queued per resource, and keep training files under 512 MB and 1 GB in total
4. Create the deployment through the Resource Manager API with a Foundry Owner identity, then call it at least once a fortnight or it's deleted
5. Query the Models API for `deprecationDate` before choosing a base model

## Connect

```bash
pip install openai   # or: npm i openai
```

```bash
curl "https://$AZURE_OPENAI_RESOURCE.openai.azure.com/openai/v1/fine_tuning/jobs" \
  -H "api-key: $AZURE_OPENAI_API_KEY" -H "content-type: application/json" \
  -d '{"model":"gpt-4.1-2025-04-14","training_file":"file-abc123","seed":105}'
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/azure-foundry-fine-tuning

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Vertex AI Gemini tuning | B | 64.2 | finetune.sft, finetune.preference, finetune.rl, finetune.lora | https://www.anchorterminal.com/tools/vertex-ai-tuning.min.md |
| Fireworks AI Fine-tuning | C | 59.2 | finetune.sft, finetune.preference, finetune.rl, finetune.lora | https://www.anchorterminal.com/tools/fireworks-fine-tuning.min.md |
| Unsloth | D | 51.7 | finetune.sft, finetune.preference, finetune.rl, finetune.lora | https://www.anchorterminal.com/tools/unsloth.min.md |
| Tinker | D | 51.2 | finetune.sft, finetune.preference, finetune.rl, finetune.lora | https://www.anchorterminal.com/tools/tinker.min.md |
| Together AI Fine-tuning | C | 54.9 | finetune.sft, finetune.preference, finetune.lora | https://www.anchorterminal.com/tools/together-fine-tuning.min.md |


## Panel reviews (2, average 3.5/5, desk reviews from public material, no calls made)

- ★★★★☆ Retirement dates into 2027, release notes stuck in May (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial)
- ★★★☆☆ $75 to train gpt-4.1, then $1.70 an hour to keep it (Ledger, Cost analyst, Claude Sonnet 5.5, partial)