# Gemini Decision 1 (slim)

> Gemini Decision 1 is Google's model for closed-set decisions. It scores yes/no, multiple-choice and rubric questions in one pass and returns probabilities, not text, over text, images, audio, video and PDFs, at $0.10 per million input tokens.

- Full: https://www.anchorterminal.com/tools/gemini-decision-1.md (~9,850 tokens) · this version ~1,830 tokens · JSON https://www.anchorterminal.com/tools/gemini-decision-1.json · canonical https://www.anchorterminal.com/tools/gemini-decision-1
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-13 · pricing https://www.anchorterminal.com/tools/gemini-decision-1#pricing · reviews https://www.anchorterminal.com/tools/gemini-decision-1#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**B · 63.2/100 · rank #630 of 1524 · #13 in Decision models · not agent-ready · confidence medium** · same model listed separately: Gemini Developer API, Model API (https://www.anchorterminal.com/tools/gemini-api.min.md)


Assessment: Google's decision model scores up to 1,000 yes/no, choice and rubric questions per request over a 262,144-token multimodal input, at $0.10 per million input tokens, no output charge and a free tier. It is on a v1beta endpoint with no caching or batch discount, so repeated input is paid in full, and every speed and accuracy figure is Google's.

## Facts

- Kind: Model API · vendor: Google · category: Decision models · legal entity: Google LLC · provenance 89/100
- Local only (HTTP)
- Auth: API key · pricing: Pay per use · x402: no · licence: Closed model, used through the Gemini API's Decisions endpoint under Google's terms. The google-genai SDK that calls it is Apache-2.0
- Benchmark probes: not run yet, so Performance is pending
- Surface graded: The Decisions endpoint of the Gemini Developer API (v1beta), read from Google's announcement, the Decisions guide, the model page and the pricing page on 11 November 2026, and the request and response types in google-genai 3.2.0. Platform readings (status page, keys, terms, retention, deprecations) are the Gemini API listing's of 1 November. No account was made and nothing was called
- Model ID: gemini-decision-1, sent as models/gemini-decision-1 in the SDK's request type
- Question types: noul (yes/no, a calibrated P(true) between 0.01 and 0.99, with optional true and false criteria), choice (2 to 255 mutually exclusive options, the winner and a normalised probability for each) and score (an ordered rubric of 2 to 255 levels from 0, a probability-weighted score and a probability per level). Every answer carries a confidence from 0 to 1
- Google's figures: Vendor-reported: 150 to 250 ms end to end and 50 to 100 ms median model compute for contexts up to 16K tokens, nearly flat from 1 to 100 questions; leads Google's suite with the lowest calibration error; nearly five times cheaper than Gemini 3.5 Flash-Lite on the same suite. Gemini Notebook routing up to 40% lower latency for everyday queries
- Where: Gemini API and Google AI Studio now. Gemini in Google Cloud coming soon. Third-party integrations, OpenRouter among them, described as rolling out
- Limits: 262,144 tokens shared by the input and all questions. 1 to 1,000 questions, keys matching [A-Za-z0-9_-] up to 64 characters. Inline data to 100 MB a request (50 MB for PDFs), Files API URIs, or public or signed HTTPS URLs up to 15 MB each; no YouTube or gs:// sources. Image and video resolution low, medium, high or ultra_high (images only)
- Request and response: POST /v1beta/decisions with model, input (a string, a block or blocks of text, image, audio, video or PDF) and questions. The response has answers keyed by question id and usage by modality, with output tokens always 0. Conversation history goes in as text
- Errors: Safety blocks, limit breaches and key failures return HTTP 400, with codes safety, prohibited_content, blocklist, image_safety and content_blocked
- Not supported: Context caching, Batch API, Flex and Priority inference, function calling, structured outputs, text generation, thinking, grounding and the Live API, per the model page
- Pricing: $0.10 per million input tokens on the paid tier for every modality, $0 output, free of charge on the free tier, per the pricing page
- Launch stage: Not stated in the post, the guide or the model page. The endpoint is on v1beta and the model has one version
- Prices: Gemini Decision 1 input $0.10 per 1M tokens; Gemini Decision 1 output free per 1M tokens

- Scores: Reliability 40, Performance pending, Schema & documentation 80, Agent ergonomics 85, Security & auth 45, Payments & pricing 60, Task success pending, Maintenance & community 79, Transparency & trust 70 · total over the 7 assessed categories
- Why: Reliability, Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. · Schema & documentation, Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. · Agent ergonomics, Read on the tool lines, as the other decision-model listings are. · Security & auth, Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. · Payments & pricing, Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. · Maintenance & community, Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. · Transparency & trust, Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint.
- Sources: 9, open questions: 5, both in the full twin
- Capabilities: inference.decision
- JSON: https://www.anchorterminal.com/api/v1/tools/gemini-decision-1.json
- Its vendor verifies the listing with `verify_listing` or `POST https://www.anchorterminal.com/api/v1/verify` (the full twin says how); no effect on the grade.

## Before you call it

1. Call POST /v1beta/decisions or `client.decisions.create` (SDK 3.2 or later), not generateContent or the Interactions API
2. Put every question about the same input in one request: there's no caching, and repeated input is billed in full
3. Pass media inline (100 MB, 50 MB for PDFs), as a Files API URI or as an HTTPS URL up to 15 MB; YouTube and gs:// links are refused
4. Branch on the HTTP 400 error code (safety, prohibited_content, blocklist, image_safety, content_blocked) before retrying
5. Keep question keys to [A-Za-z0-9_-] and 64 characters, and options or levels between 2 and 255

## Connect

```bash
curl -X POST "https://generativelanguage.googleapis.com/v1beta/decisions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" -H "content-type: application/json" \
  -d '{"model":"models/gemini-decision-1","input":"The blue mug I ordered arrived cracked.","questions":{"damaged":{"type":"noul","instructions":"Did the item arrive damaged?"},"team":{"type":"choice","instructions":"Which team handles this?","criteria":{"returns":"Damaged or wrong items","billing":"Charges and refunds"}}}}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| OpenAI Decisions API | A | 78.5 | inference.decision | https://www.anchorterminal.com/tools/openai-decisions-api.min.md |
| Drex 1.5 | BB | 73.6 | inference.decision | https://www.anchorterminal.com/tools/nace-drex.min.md |
| Decider | BB | 72.8 | inference.decision | https://www.anchorterminal.com/tools/decider.min.md |
| Laya | BB | 72.4 | inference.decision | https://www.anchorterminal.com/tools/convai-laya.min.md |
| pplx-decider | BB | 71.8 | inference.decision | https://www.anchorterminal.com/tools/pplx-decider.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)