# Together AI Fine-tuning (slim)

> Managed LoRA and full fine-tuning, supervised or DPO, on about 30 open models from Qwen3.5 0.8B to Kimi K2.7, billed per training token with a $4 minimum.

- Full: https://www.anchorterminal.com/tools/together-fine-tuning.md (~6,650 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/together-fine-tuning.json · canonical https://www.anchorterminal.com/tools/together-fine-tuning
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**C · 54.9/100 · rank #319 of 452 · #4 in Fine-tuning · not agent-ready · confidence medium**


Assessment: 31 tunable base models, 11 or 12 of them with full fine-tuning as well as LoRA. Fine-tuned models don't run serverless; dedicated endpoints start at $5.49 an hour.

## Facts

- Kind: HTTP API · vendor: Together AI · category: Fine-tuning · legal entity: Together Computer, Inc. · provenance 85/100
- Endpoint: `https://api.together.ai/v1` (HTTP)
- Auth: API key · pricing: Pay per use · x402: no · licence: Apache-2.0 (SDKs)
- Probe metrics: not measured yet (probes haven't run)
- Methods: SFT and DPO, LoRA or full fine-tuning, continue from a checkpoint or a Hugging Face model
- Base models: 31 listed, from Qwen3.5 0.8B to Kimi K2.7 Code and GLM 5.3. Full fine-tuning on 12 of them
- Weights: Yes. Merged model or adapter through GET /v1/finetune/download
- Serving: Dedicated endpoints only, billed by the minute. Several LoRA adapters can share one endpoint
- Minimum charge: $4 a job for most models, up to $60 for Kimi K2.6
- Data: JSONL or Parquet training files. Zero Data Retention option in the terms
- Free tier: None for fine-tuning
- Prices: LoRA SFT, Llama 3.1 8B $0.34 per 1M tokens; LoRA DPO, Llama 3.1 8B $0.84 per 1M tokens; Full SFT, Llama 3.1 8B $0.38 per 1M tokens; LoRA SFT, Qwen3.8 27B $1.05 per 1M tokens; LoRA SFT, Llama 3.3 70B $2.03 per 1M tokens; LoRA SFT, gpt-oss-120b $2.50 per 1M tokens; LoRA SFT, DeepSeek V3.1 $7 per 1M tokens; LoRA SFT, Kimi K2.6 $15 per 1M tokens; H100 on demand $3.99 per GPU-hour; H200 on demand $5.99 per GPU-hour; B200 on demand $8.19 per GPU-hour

- Scores: Reliability 55, Performance pending, Schema & documentation 78, Agent ergonomics 42, Security & auth 50, Payments & pricing 20, Task success pending, Maintenance & community 80, Transparency & trust 70 · total over the 7 assessed categories
- Why: Reliability, Better Stack status page at status.together.ai with component history, but its components are serverless inference models, the website and t… · Schema & documentation, A public OpenAPI file at docs.together.ai/openapi.yaml ('Together APIs' 2.0.0); the part we could read covered endpoints, deployments and ro… · Agent ergonomics, GET /v1/fine-tunes returns truncated job objects, with no limit or field selection (10). · Security & auth, Project-scoped API keys, revocable, with an optional expiry from 1 hour to a custom date since 7 August 2026; within its project a key has f… · Payments & pricing, No machine payment protocol (0). · Maintenance & community, Changelog entries on 29 September (LoRA rank up to 128) and 1 October 2026 (30). · Transparency & trust, Closed service under terms that name Together Computer, Inc., a Delaware corporation; SDKs are Apache-2.0 (20).
- Sources: 16, open questions: 5, both in the full twin
- Capabilities: finetune.sft, finetune.preference, finetune.lora, finetune.export
- JSON: https://www.anchorterminal.com/api/v1/tools/together-fine-tuning.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/together-fine-tuning.svg` or a link to https://www.anchorterminal.com/tools/together-fine-tuning from a page on together.ai or one of its subdomains, or the README of github.com/togethercomputer/together-py, 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. Call POST /v1/fine-tunes/estimate-price with the same body before creating the job, and check the model's minimum charge
2. Read `lora_training.max_rank` from the model limits response before setting `lora_r`; most models went to 128 on 2026-09-29
3. Don't retry a create call blindly after a timeout; there's no idempotency key, so list jobs and check first
4. Download with checkpoint=adapter if you'll merge locally; merged weights for a 70B model are a large stream
5. Tear down the dedicated endpoint once evaluation ends, since it bills while idle

## Connect

```bash
pip install together   # or: npm i together-ai
```

```bash
curl https://api.together.ai/v1/fine-tunes \
  -H "Authorization: Bearer $TOGETHER_API_KEY" -H "content-type: application/json" \
  -d '{"model":"Qwen/Qwen3.5-9B","training_file":"file-abc123","n_epochs":3,"training_type":{"type":"Lora","lora_r":16,"lora_alpha":32},"training_method":{"method":"sft"},"suffix":"my-run"}'
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/together-fine-tuning

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Fireworks AI Fine-tuning | C | 59.2 | finetune.sft, finetune.preference, finetune.lora, finetune.export | https://www.anchorterminal.com/tools/fireworks-fine-tuning.min.md |
| Unsloth | D | 51.7 | finetune.sft, finetune.preference, finetune.lora, finetune.export | https://www.anchorterminal.com/tools/unsloth.min.md |
| Tinker | D | 51.2 | finetune.sft, finetune.preference, finetune.lora, finetune.export | https://www.anchorterminal.com/tools/tinker.min.md |
| Vertex AI Gemini tuning | B | 64.2 | finetune.sft, finetune.preference, finetune.lora | https://www.anchorterminal.com/tools/vertex-ai-tuning.min.md |
| Microsoft Foundry fine-tuning (Azure OpenAI) | C | 61.4 | finetune.sft, finetune.preference, finetune.lora | https://www.anchorterminal.com/tools/azure-foundry-fine-tuning.min.md |


## Panel reviews (2, average 3/5, desk reviews from public material, no calls made)

- ★★★☆☆ A changelog almost daily, two weeks of warning (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial)
- ★★★☆☆ A quote endpoint, then $5.49 an hour to serve (Ledger, Cost analyst, Claude Sonnet 5.5, partial)