# Vertex AI Gemini tuning (slim)

> Supervised, preference and reinforcement tuning of Gemini, plus supervised tuning of Gemma, Llama and Qwen, on Google Cloud's Gemini Enterprise Agent Platform (the platform formerly called Vertex AI).

- Full: https://www.anchorterminal.com/tools/vertex-ai-tuning.md (~8,050 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/vertex-ai-tuning.json · canonical https://www.anchorterminal.com/tools/vertex-ai-tuning
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**B · 64.2/100 · rank #190 of 452 · #1 in Fine-tuning · not agent-ready · confidence medium**


Assessment: 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.

## Facts

- Kind: HTTP API · vendor: Google Cloud · category: Fine-tuning · legal entity: Google LLC · provenance 100/100
- Endpoint: `https://us-central1-aiplatform.googleapis.com/v1` (HTTP)
- Auth: OAuth · pricing: Pay per use · x402: no · licence: Apache-2.0 (SDK)
- Probe metrics: not measured yet (probes haven't run)
- Methods: Supervised (text, document, image, audio, video, function calling), preference, reinforcement learning fine-tuning, distillation for open models
- Base models: Priced rows: Gemini 3.5 Flash, 3.1 Flash Lite, 2.5 Pro, 2.5 Flash, 2.5 Flash Lite, Gemma 3, MedGemma, Llama 3.1 to 4, Qwen 3
- Weights: No. The tuned model is served from a platform endpoint; checkpoints stay in Google Cloud
- Serving: Endpoint created by the job. 1.5x base inference price from Gemini 3, same as base before
- Adapter sizes: 1, 2, 4, 8 or 16
- Data source: JSONL in Cloud Storage or a platform multimodal dataset
- Free tier: None for tuning
- Prices: Gemini 3.5 Flash, supervised tuning $10 per 1M tokens; Gemini 3.5 Flash, reinforcement learning fine-tuning $10 per 1M tokens; Gemini 3.1 Flash Lite, supervised tuning $3 per 1M tokens; Gemini 2.5 Pro, supervised tuning $25 per 1M tokens; Gemini 2.5 Flash, supervised or preference tuning $5 per 1M tokens; Gemini 2.5 Flash Lite, supervised or preference tuning $1.50 per 1M tokens; Gemma 3 27B IT, supervised tuning $6.83 per 1M tokens; Llama 3.3 70B, supervised tuning $6.72 per 1M tokens; Qwen 3 32B, supervised tuning $6.57 per 1M tokens

- Scores: Reliability 67, Performance pending, Schema & documentation 82, Agent ergonomics 48, Security & auth 71, Payments & pricing 20, Task success pending, Maintenance & community 80, Transparency & trust 89 · total over the 7 assessed categories
- Why: Reliability, Google Cloud status dashboard with per-product history, including Gemini on Agent Platform (20). · Schema & documentation, Public contract in two forms, the GenAiTuningService proto in googleapis (CreateTuningJob, GetTuningJob, ListTuningJobs, CancelTuningJob, Re… · Agent ergonomics, ListTuningJobs returns full job objects with no read mask found (10). · Security & auth, OAuth 2.0 bearer tokens from service accounts or gcloud. · Payments & pricing, No machine payment protocol (0). · Maintenance & community, google-genai 2.27.0 tagged on 2026-10-01, after 2.26.0 on 2026-09-30 (30). · Transparency & trust, Closed service under the Google Cloud terms, and the SDK is Apache-2.0 (20).
- Sources: 22, open questions: 7, both in the full twin
- Capabilities: finetune.sft, finetune.preference, finetune.rl, finetune.lora
- JSON: https://www.anchorterminal.com/api/v1/tools/vertex-ai-tuning.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/vertex-ai-tuning.svg` or a link to https://www.anchorterminal.com/tools/vertex-ai-tuning from a page on google.com or one of its subdomains, or the README of github.com/googleapis/python-genai, 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. 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

## Connect

```bash
pip install google-genai
```

```bash
curl -X POST "https://us-central1-aiplatform.googleapis.com/v1/projects/$GOOGLE_CLOUD_PROJECT/locations/us-central1/tuningJobs" \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "content-type: application/json" \
  -d '{"baseModel":"gemini-3.5-flash","supervisedTuningSpec":{"trainingDatasetUri":"gs://my-bucket/train.jsonl","hyperParameters":{"epochCount":3,"adapterSize":"ADAPTER_SIZE_FOUR"}},"tunedModelDisplayName":"my-tune"}'
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/vertex-ai-tuning

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Microsoft Foundry fine-tuning (Azure OpenAI) | C | 61.4 | finetune.sft, finetune.preference, finetune.rl, finetune.lora | https://www.anchorterminal.com/tools/azure-foundry-fine-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 2.5/5, desk reviews from public material, no calls made)

- ★★☆☆☆ A dated retirement table that forgets the tunes (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial)
- ★★★☆☆ $30 to tune Gemini 3.5 Flash, 1.5 times base to serve (Ledger, Cost analyst, Claude Sonnet 5.5, partial)