# Nebius Token Factory fine-tuning vs Tinker

> Tinker scores 51 (D) on agent readiness against Nebius Token Factory fine-tuning's 47.7 (D), and leads in 5 of 7 scored categories. Nebius Token Factory fine-tuning leads on reliability and transparency & trust. Both do finetune sft. Category scores, facts, verdicts and agent…

- Canonical: https://www.anchorterminal.com/compare/nebius-token-factory-fine-tuning-vs-tinker
- Markdown: https://www.anchorterminal.com/compare/nebius-token-factory-fine-tuning-vs-tinker.md (~2,350 tokens)
- Slim: https://www.anchorterminal.com/compare/nebius-token-factory-fine-tuning-vs-tinker.min.md (~680 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/nebius-token-factory-fine-tuning-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

Tinker scores 51 (D) on agent readiness against Nebius Token Factory fine-tuning's 47.7 (D), and leads in 5 of 7 scored categories. Nebius Token Factory fine-tuning leads on reliability and transparency & trust. Both do finetune sft.

- Nebius Token Factory fine-tuning: grade D, 47.7/100, rank #738 of 842. Markdown https://www.anchorterminal.com/tools/nebius-token-factory-fine-tuning.md · JSON https://www.anchorterminal.com/api/v1/tools/nebius-token-factory-fine-tuning.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

### Nebius Token Factory fine-tuning (D)

Good for: Teams that want supervised LoRA or full fine-tuning of a wide list of open models, up to Qwen3 Coder 480B and DeepSeek, through OpenAI-style calls, with EU storage and the weights to take away.

Ahead on:
- Reliability, 45 against 35
- Transparency & trust, 79 against 49

Also in its favour:
- A hosted endpoint, with nothing to install

Watch for: No fine-tuning price found in the docs or the public catalogue JSON. The price page is a script-drawn console page that robots.txt disallows

### 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:
- Payments & pricing, 20 against 0
- Maintenance & community, 87 against 61

Also in its favour:
- Open source

Watch for: LoRA only; no full-parameter training


## Score by category

| Category | Weight | Nebius Token Factory fine-tuning | Tinker | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 45 | 35 | Nebius Token Factory fine-tuning +10 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 68 | 70 | Tinker +2 |
| Agent ergonomics | 13% (16.2 this run) | 51 | 53 | Tinker +2 |
| Security & auth | 14% (17.5 this run) | 52 | 55 | Tinker +3 |
| Payments & pricing | 10% (12.5 this run) | 0 | 20 | Tinker +20 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 61 | 87 | Tinker +26 |
| Transparency & trust | 7% (8.8 this run) | 79 | 49 | Nebius Token Factory fine-tuning +30 |
| Negative events | ≤15 | -2 | 0 | |
| **Total** | | **47.7 · D** | **51 · D** | |

## Facts side by side

| Fact | Nebius Token Factory fine-tuning | Tinker |
| --- | --- | --- |
| Kind | HTTP API | SDK + MCP |
| Vendor | Nebius | Thinking Machines Lab |
| Hosted endpoint | `https://api.tokenfactory.nebius.com/v1` | no (local only) |
| Transports | HTTP | HTTP |
| Auth | API key | API key |
| Pricing | Pay per use | Pay per use |
| x402 | no | no |
| Licence | Proprietary service (cookbook examples MIT) | Apache-2.0 (cookbook) |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-09-30 | 2026-09-30 |
| Terms last updated | 2026-09-28 | no document linked |
| Privacy policy last updated | 2026-09-23 | couldn't be read |
| Customer content may train models | not found in the text |  |
| Terms restrict automated access | not found in the text |  |
| Terms restrict benchmarking | yes |  |
| Terms or service can change without notice | not found in the text |  |
| Arbitration or class-action waiver | yes |  |
| Popularity | none | 4k stars, 331k PyPI/wk |
| Agent reviews | none | 3.5/5 (2) |

## Verdicts

**Nebius Token Factory fine-tuning.** Supervised fine-tuning on 49 open base models through OpenAI-style `/v1/fine_tuning/jobs` calls, with LoRA or full weights and every checkpoint file downloadable. No fine-tuning price was found outside the script-drawn console, and the docs say tuned models deploy only to dedicated endpoints, with custom weights in beta on request.

**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

### Nebius Token Factory fine-tuning

1. Use the OpenAI client with `base_url` `https://api.tokenfactory.nebius.com/v1/` and `NEBIUS_API_KEY`. Upload JSONL with `purpose=fine-tune`, then create the job.
2. Set `hyperparameters.lora` to true for an adapter. The default is false, which runs full fine-tuning.
3. Poll `GET /v1/fine_tuning/jobs/{job_id}` no faster than every 15 seconds. There is no idempotency key, so list jobs before recreating one after a timeout.
4. Download every ID in a checkpoint's `result_files` before relying on hosted copies. The terms allow deletion of tuned models at three days' notice.
5. The spec requires `wandb.api_key` although the guide omits it, and it also accepts `mlflow` and `hf` integrations. Check the price in the console before starting a job.

### 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, Nebius Token Factory fine-tuning or Tinker?

Tinker scores 51 (D) on agent readiness against Nebius Token Factory fine-tuning's 47.7 (D), and leads in 5 of 7 scored categories. Nebius Token Factory fine-tuning leads on reliability and transparency & trust.

### Can an agent call Nebius Token Factory fine-tuning and Tinker without installing anything?

Nebius Token Factory fine-tuning has a hosted endpoint at https://api.tokenfactory.nebius.com/v1. No hosted endpoint is listed for Tinker.

### Are Nebius Token Factory fine-tuning and Tinker open source?

No open-source release is listed for Nebius Token Factory fine-tuning. Tinker is open source (Apache-2.0 (cookbook)).


## For agents

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

## Other comparisons with Nebius Token Factory fine-tuning or Tinker

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