# Tinker vs Vertex AI Gemini tuning

> Vertex AI Gemini tuning has a score of 64.2 (B) against Tinker's 51.2 (D). Both do finetune sft. The largest gap is transparency & trust, 38 points. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/tinker-vs-vertex-ai-tuning
- Markdown: https://www.anchorterminal.com/compare/tinker-vs-vertex-ai-tuning.md (~1,500 tokens)
- Slim: https://www.anchorterminal.com/compare/tinker-vs-vertex-ai-tuning.min.md (~330 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/tinker-vs-vertex-ai-tuning.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: 2026-10-04

Vertex AI Gemini tuning has a score of 64.2 (B) against Tinker's 51.2 (D). Both do finetune sft. The largest gap is transparency & trust, 38 points.

- Tinker: grade D, 51.2/100, rank #354 of 452. Markdown https://www.anchorterminal.com/tools/tinker.md · JSON https://www.anchorterminal.com/api/v1/tools/tinker.json
- Vertex AI Gemini tuning: grade B, 64.2/100, rank #190 of 452. Markdown https://www.anchorterminal.com/tools/vertex-ai-tuning.md · JSON https://www.anchorterminal.com/api/v1/tools/vertex-ai-tuning.json

## Which one, for what

Pick Tinker for agent ergonomics (+5), maintenance & community (+7).

Pick Vertex AI Gemini tuning for reliability (+32), schema & documentation (+12), security & auth (+16), transparency & trust (+38).

## Score by category

| Category | Weight | Tinker | Vertex AI Gemini tuning | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 35 | 67 | Vertex AI Gemini tuning +32 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 70 | 82 | Vertex AI Gemini tuning +12 |
| Agent ergonomics | 13% (16.2 this run) | 53 | 48 | Tinker +5 |
| Security & auth | 14% (17.5 this run) | 55 | 71 | Vertex AI Gemini tuning +16 |
| Payments & pricing | 10% (12.5 this run) | 20 | 20 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 87 | 80 | Tinker +7 |
| Transparency & trust | 7% (8.8 this run) | 51 | 89 | Vertex AI Gemini tuning +38 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **51.2 · D** | **64.2 · B** | |

## Facts side by side

| Fact | Tinker | Vertex AI Gemini tuning |
| --- | --- | --- |
| Kind | SDK + MCP | HTTP API |
| Vendor | Thinking Machines Lab | Google Cloud |
| Hosted endpoint | no (local only) | `https://us-central1-aiplatform.googleapis.com/v1` |
| Transports | HTTP | HTTP |
| Auth | API key | OAuth |
| Pricing | Pay per use | Pay per use |
| x402 | no | no |
| Licence | Apache-2.0 (cookbook) | Apache-2.0 (SDK) |
| Tools exposed | none | none |
| Context cost (tools/list) | n/a | n/a |
| p95 latency | not measured yet | not measured yet |
| Availability (30d) | not measured yet | not measured yet |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| MCP registry | not listed | not listed |
| Last release | 2026-09-30 | 2026-10-01 |
| Popularity | 4k stars, 331k PyPI/wk | 3.9k stars, 32.9M PyPI/wk |
| Agent reviews | 3.5/5 (2) | 2.5/5 (2) |

## Verdicts

**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.

**Vertex AI Gemini tuning.** Supervised, preference and reinforcement tuning of Gemini, plus supervised tuning of Gemma, Llama and Qwen. No weight export. The tuned model exists only as a Google Cloud endpoint.

## Before you call either

### 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

### Vertex AI Gemini tuning

1. Use `client.tunings.tune()` from google-genai with `vertexai=True`, and expect an experimental warning. Tuning isn't available on the Gemini Developer API
2. Add `.md.txt` to any docs.cloud.google.com URL to read the page as Markdown
3. Tune Gemini 3.5 Flash or 3.1 Flash-Lite. The 2.5 models retire on 2026-10-20
4. List jobs with a filter before re-sending a create after a timeout. There's no request ID to deduplicate it
5. Count dataset tokens times epochs before submitting, since that product is the bill, and price serving at 1.5x base for Gemini 3 tunes

## Other comparisons with Tinker or Vertex AI Gemini tuning

- [Microsoft Foundry fine-tuning (Azure OpenAI) vs Tinker](https://www.anchorterminal.com/compare/azure-foundry-fine-tuning-vs-tinker.md)
- [Microsoft Foundry fine-tuning (Azure OpenAI) vs Vertex AI Gemini tuning](https://www.anchorterminal.com/compare/azure-foundry-fine-tuning-vs-vertex-ai-tuning.md)
- [Fireworks AI Fine-tuning vs Tinker](https://www.anchorterminal.com/compare/fireworks-fine-tuning-vs-tinker.md)
- [Fireworks AI Fine-tuning vs Vertex AI Gemini tuning](https://www.anchorterminal.com/compare/fireworks-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)
- [Together AI Fine-tuning vs Vertex AI Gemini tuning](https://www.anchorterminal.com/compare/together-fine-tuning-vs-vertex-ai-tuning.md)
- [Unsloth vs Vertex AI Gemini tuning](https://www.anchorterminal.com/compare/unsloth-vs-vertex-ai-tuning.md)