# Gemini Decision 1 vs Drex 1.5

> Drex 1.5 scores 73.6 (BB) to Gemini Decision 1's 63.2 (B) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/gemini-decision-1-vs-nace-drex
- Markdown: https://www.anchorterminal.com/compare/gemini-decision-1-vs-nace-drex.md (~5,450 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-13

Drex 1.5 scores 73.6 (BB) on agent readiness against Gemini Decision 1's 63.2 (B), and leads in 4 of 7 scored categories. Gemini Decision 1 leads on maintenance & community. Both do decision models.

- Gemini Decision 1: grade B, 63.2/100, rank #630 of 1524. Markdown https://www.anchorterminal.com/tools/gemini-decision-1.md · JSON https://www.anchorterminal.com/api/v1/tools/gemini-decision-1.json
- Drex 1.5: grade BB, 73.6/100, rank #167 of 1524. Markdown https://www.anchorterminal.com/tools/nace-drex.md · JSON https://www.anchorterminal.com/api/v1/tools/nace-drex.json
- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md
- All 241 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md

## Which one, for what

### Gemini Decision 1 (B)

Good for: Routing, tool selection, policy checks and rubric grading over mixed media, where many fixed questions share one input and generated text isn't needed.

Ahead on:
- Maintenance & community, 79 against 61

Watch for: No context caching, Batch API, Flex or Priority: the guide says repeated input across requests counts in full

### Drex 1.5 (BB)

Good for: Routing, triage and yes or no gates inside an agent, where the caller supplies the options and acts on the probabilities. Suited to hosted use at a low per-token price, or to open weights where the licence fits.

Ahead on:
- Reliability, 80 against 40
- Schema & documentation, 88 against 80
- Security & auth, 70 against 45

Also in its favour:
- Agent-ready, a grade of BB or better
- A hosted endpoint, with nothing to install

Watch for: drex-v1.0 was retired on 21 October 2026, 27 days after release, and its requests now go to Drex Max at Max's limits and price, with no notice period published.


## Why the edge

### Reliability: Drex 1.5 +40

- Gemini Decision 1 (40): Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Status page at aistudio.google.com/status with no readable components or history (10 of 20) and no readable incident record (5 of 30). Rate-limit tiers and spend limits published for the platform, but the public rate-limit page, read on 11 November, has no row for Decision 1 and sends you to AI Studio (5 of 15). Backoff guidance for 429 and 503 and SDK retries (15). No SLA (0). The guide and the model page, read on 11 November, state no launch stage; the endpoint is v1beta and the model has one version, so half, as Gemini 4 Carbon was read (5 of 10). 10 + 5 + 5 + 15 + 0 + 5 = 40.
- Drex 1.5 (80): A public BetterStack status page with an API and dashboard component that serves /v1/systemone, at 100 per cent uptime over 90 days on 1 November 2026 (20). Its incident list is now readable and shows one incident in the window, Document processing down on 26 October 2026, which is Nace's separate Perception product, not the Drex API. Drex has been public since 24 September, 38 days, so the record is still short and the line stays 20 of 30, as it was on 10 October. Rate limits are published with numbers for the free and paid tiers (15). A 429 carries Retry-After and retry-after-ms, a 529 says to retry shortly, the docs advise capped backoff with jitter, and a decision call changes no stored state (15). No SLA for any tier was found, and the Trust Centre gives recovery objectives on request only (0). No beta or preview label was found on the API or its docs (10). Total 80.

### Security & auth: Drex 1.5 +25

- Gemini Decision 1 (45): Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Keys bound to a service account and restricted to the Gemini API, with no scopes and a token accepted in the URL (15 of 30, the platform's deduction). The pricing page, read on 11 November, says free-tier content is used to improve Google's products and paid-tier content isn't (10 of 20, the platform's reading). Abuse retention with no number (5 of 15). Request logs for billed projects are described for Generate Content; the Decisions guide says nothing on logging (10 of 15). security.txt and a reward programme, no certification naming the API (5 of 20). 15 + 10 + 5 + 10 + 5 = 45.
- Drex 1.5 (70): Read for a model API, for retention, training and zero-retention options, on the lines used for the other decision models listed as models (the OpenAI Decisions API, Perplexity's Decider and Cloudflare's Clef). Bearer keys in the nace_sk_ format are revocable and can be rotated without downtime, and an account is capped at three active keys. No scopes are documented (20). The Console terms, privacy notice and DPA of 26 October 2026, which cover Drex, say Customer Content isn't used to train, fine-tune, evaluate or improve shared models without written opt-in, on every account. Standard retention keeps inputs and outputs until the customer deletes them, deletion completes within 72 hours and backups expire within 35 days. Zero Retention applies only to supported operations on workspaces bound to customer-managed storage, and the Drex docs don't say decision calls are among them (15 of 20). The decision call returns only probabilities over options the caller supplies, with no free text. The checklist gives 10 to a tool that returns no untrusted content, and that is the award here (10). Each response carries a request id, and the dashboard Usage page exports a CSV by key and bucket (15). security.txt is valid until 9 October 2027. The SOC 2 Type 2 listing and the pentest report sit behind an access request and were not read. No bug bounty or public advisory page was found (10 of 20). 20+15+10+15+10 = 70.

### Maintenance & community: Gemini Decision 1 +18

- Gemini Decision 1 (79): Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Released on 11 November 2026, the day of this check (30). Deprecations with earliest dates and no stated minimum notice (4 of 12). Shutdowns in the last 90 days kept to their table (4 of 8). Dated changelogs: google-genai 3.2.0's entry adds the Decisions API; the platform changelog wasn't re-read today (11 of 15). SDK replies not sampled (5 of 10). google-genai 3.2.0 tagged the same day with `client.decisions.create`; the JavaScript SDK is per Google's post (15). Runtimes stated on the platform (10). 30 + 4 + 4 + 11 + 5 + 15 + 10 = 79. The model is hours old, so these lines are the platform's habits more than this model's record.
- Drex 1.5 (61): Read as a model, for deprecation notice and model churn rather than release counts, on the lines used for the other decision models listed as models (the OpenAI Decisions API, Perplexity's Decider and Cloudflare's Clef). Drex Max v1.1 went live on the API on 28 October 2026, after Drex 2.0 on 6 October and Drex Max on 13 October (30). Pinned ids stay on their version only while it is active, and the terms of 26 October promise reasonable efforts to give advance notice of non-backward-compatible changes to a generally available API, with no minimum period. drex-v1.0 was retired on 21 October, 27 days after release, and its requests are now answered by Drex Max with Max's limits and price. No announcement or notice period for it was found (3 of 12), the reading given to Perplexity's Decider, whose retired names were moved on release day. Six model ids since 24 September, two of them already retired, and a retired id answered by a different model, which is churn (2 of 8). No public changelog. The models reference keeps a dated model table, a retired-model table and what changed in 2.0 and 1.5. The docs link support and the site a community channel, and replies weren't sampled (6 of 15). Python and TypeScript nace-sdk and the nace-mcp server were current at 0.1.0 on 8 October, per the 10 October check, not re-read on 1 November because PyPI and npm don't resolve from our shell (15). The GitHub repository has tests and bounded requirements, with 44 commits since 10 October and pull requests merged through #12, but no CI workflow or lock file (5 of 10). 30+3+2+6+15+5 = 61.

### Schema & documentation: Drex 1.5 +8

- Gemini Decision 1 (80): Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. No published machine-readable contract for the Decisions endpoint; the request and response types are generated and typed in google-genai 3.2.0, Apache-2.0 (10 of 25). llms.txt with Markdown twins on the platform (10). The guide and model page say what the endpoint is for and list what it doesn't do (no caching, Batch, Flex, Priority, function calling, structured outputs or text generation; no YouTube or gs:// sources; history only as text) (18 of 20). Fields carry stated rules: question keys match [A-Za-z0-9_-]+ up to 64 characters, 1 to 1,000 questions, 2 to 255 options or levels, option keys 1 to 128 characters, P(true) between 0.01 and 0.99, nesting to 100 levels (14 of 15). Python, JavaScript and REST examples, and errors documented as HTTP 400 with codes safety, prohibited_content, blocklist, image_safety and content_blocked (13 of 15). Dated SDK changelog and the platform's dated changelog (15). 10 + 10 + 18 + 14 + 13 + 15 = 80.
- Drex 1.5 (88): A public OpenAPI 3.1 document at console.nace.ai/openapi.json, 47 paths on 1 November with POST /v1/systemone, /v1/decisions and GET /v1/models (25). llms.txt is served at drex.nace.ai/llms.txt. The docs have a Copy Markdown control, but the Markdown URLs we tried returned errors (10). The docs say what Drex is for and what it cannot do, since it generates no text and picks only from the options a caller supplies. No page lists languages or weak areas, and none says when not to use it (15 of 20). Questions are typed as noul, choice or score, with named options and a 512-question limit. The state is free-form JSON by design (13 of 15). Examples in curl, TypeScript, Python and the CLI, and an error reference with types, messages and headers (15). Pinned model ids and a dated alias history earn 10 of the 15 for versioning and changelog. No public changelog was found, so 5 is withheld (10). Total 88.

## Score by category

| Category | Weight | Gemini Decision 1 | Drex 1.5 | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 40 | 80 | Drex 1.5 +40 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 80 | 88 | Drex 1.5 +8 |
| Agent ergonomics | 13% (16.2 this run) | 85 | 85 | even |
| Security & auth | 14% (17.5 this run) | 45 | 70 | Drex 1.5 +25 |
| Payments & pricing | 10% (12.5 this run) | 60 | 60 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 79 | 61 | Gemini Decision 1 +18 |
| Transparency & trust | 7% (8.8 this run) | 70 | 73 | Drex 1.5 +3 |
| Negative events | ≤15 | 0 | -2 | |
| **Total** | | **63.2 · B** | **73.6 · BB** | |

## Facts side by side

| Fact | Gemini Decision 1 | Drex 1.5 |
| --- | --- | --- |
| Kind | Model API | Model API |
| Vendor | Google | Nace AI, Inc. (Nace.AI) |
| Hosted endpoint | no (local only) | `https://console.nace.ai/v1/systemone` |
| Transports | HTTP | HTTP |
| Auth | API key | API key |
| Pricing | Pay per use | Freemium |
| Price for decision models | free | not published |
| x402 | no | 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 | Hosted API under the Nace.AI Console Terms of Service, published 26 October 2026. Weights under the Nace AI Open RAIL-M licence (modified, version 1.0, October 2026), which is not an open-source licence. Businesses above $1 million in revenue or funding need a separate commercial licence, and competing products are excluded. The bundled code/kev package, derived from Jared Palmer's Kev (https://github.com/jaredpalmer/kev), and the GitHub repository are Apache-2.0, and the agent skill is MIT. |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-11-11 | 2026-09-28 |
| Terms last updated | 2026-04-28 | 2026-10-09 |
| Privacy policy last updated | 2026-10-01 | 2026-10-09 |
| Customer content may train models | yes | yes, with an opt-out |
| Terms restrict automated access | yes | not found in the text |
| Terms restrict benchmarking | yes | yes |
| Terms or service can change without notice | not found in the text | yes |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | none | 318 npm/wk, 156 PyPI/wk |
| Agent reviews | none | 3.5/5 (4) |

## How the scores have moved

### Gemini Decision 1

- +2.5 on 13 November 2026 (C to B): checklist

### Drex 1.5

- +2.5 on 13 November 2026: checklist
- +1.6 on 1 November 2026 (B to BB): terms, correction
- -0.2 on 28 October 2026: correction

## Verdicts

**Gemini Decision 1.** 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.

**Drex 1.5.** The hosted endpoint has a public OpenAPI document, published limits and per-token prices from $0.03 per million input tokens with no output charge, and new terms, privacy notice and DPA that agree on no training. Versions turn over fast. drex-v1.0 was retired after 27 days and is answered by a different model, with no notice period published.

## Before you call either

### Gemini Decision 1

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

### Drex 1.5

1. Call https://console.nace.ai/v1/systemone with Authorization: Bearer nace_sk_..., and pin a model id (drex-v1.5, drex-v2.0 or drex-max-v1.1) rather than drex-latest, which now points to drex-v2.0.
2. Stop on 402 insufficient_credit or 402 payment_required until credit is topped up or the unpaid invoice is paid.
3. Retry 429 and 529 after retry-after-ms. On a 422 for an unknown model, use one of the ids the error message lists.
4. Keep state below 131,072 tokens and the body below 1,048,576 bytes, and send at most 512 questions per request.
5. Keep the key on a server. A key in browser code is exposed, and the /v1 routes send no Access-Control-Allow-Origin header.
6. Check usage.input_tokens and the usage CSV after retries, since /v1/systemone documents no idempotency key.

## Tutorials

- [Detect an urgent incident with Drex](https://www.anchorterminal.com/tutorials/nace-drex/), for Drex 1.5

## Questions

### Which is better for AI agents, Gemini Decision 1 or Drex 1.5?

Drex 1.5 scores 73.6 (BB) on agent readiness against Gemini Decision 1's 63.2 (B), and leads in 4 of 7 scored categories. Gemini Decision 1 leads on maintenance & community.

### Do Gemini Decision 1 and Drex 1.5 need an API key?

Both need an API key.

### Can an agent call Gemini Decision 1 and Drex 1.5 without installing anything?

No hosted endpoint is listed for Gemini Decision 1. Drex 1.5 has a hosted endpoint at https://console.nace.ai/v1/systemone.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/gemini-decision-1-vs-nace-drex.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gemini-decision-1-vs-nace-drex.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "gemini-decision-1", "b": "nace-drex"}`. From a terminal: `anchor compare gemini-decision-1 nace-drex`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gemini-decision-1.json and https://www.anchorterminal.com/api/v1/tools/nace-drex.json

## Other comparisons with Gemini Decision 1 or Drex 1.5

- [Celeris-1 Decision vs Gemini Decision 1](https://www.anchorterminal.com/compare/celeris-1-decision-vs-gemini-decision-1.md)
- [Celeris-1 Decision vs Drex 1.5](https://www.anchorterminal.com/compare/celeris-1-decision-vs-nace-drex.md)
- [Clef vs Gemini Decision 1](https://www.anchorterminal.com/compare/cloudflare-clef-vs-gemini-decision-1.md)
- [Clef vs Drex 1.5](https://www.anchorterminal.com/compare/cloudflare-clef-vs-nace-drex.md)
- [Laya vs Gemini Decision 1](https://www.anchorterminal.com/compare/convai-laya-vs-gemini-decision-1.md)
- [Laya vs Drex 1.5](https://www.anchorterminal.com/compare/convai-laya-vs-nace-drex.md)
- [Decider vs Gemini Decision 1](https://www.anchorterminal.com/compare/decider-vs-gemini-decision-1.md)
- [Decider vs Drex 1.5](https://www.anchorterminal.com/compare/decider-vs-nace-drex.md)
- [Decision 3.0 vs Gemini Decision 1](https://www.anchorterminal.com/compare/decision-3-vs-gemini-decision-1.md)
- [Decision 3.0 vs Drex 1.5](https://www.anchorterminal.com/compare/decision-3-vs-nace-drex.md)
- [Gemini Decision 1 vs GLiClass](https://www.anchorterminal.com/compare/gemini-decision-1-vs-gliclass.md)
- [Gemini Decision 1 vs Granite Switch 4.1](https://www.anchorterminal.com/compare/gemini-decision-1-vs-granite-switch.md)
- [Gemini Decision 1 vs Kev](https://www.anchorterminal.com/compare/gemini-decision-1-vs-jaredpalmer-kev.md)
- [Gemini Decision 1 vs Liquid d1](https://www.anchorterminal.com/compare/gemini-decision-1-vs-liquid-d1.md)
- [Gemini Decision 1 vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/gemini-decision-1-vs-microsoft-decision-1.md)
- [Gemini Decision 1 vs OpenAI Decisions API](https://www.anchorterminal.com/compare/gemini-decision-1-vs-openai-decisions-api.md)
- [Gemini Decision 1 vs pplx-decider](https://www.anchorterminal.com/compare/gemini-decision-1-vs-pplx-decider.md)
- [Gemini Decision 1 vs pplx-decider-flash](https://www.anchorterminal.com/compare/gemini-decision-1-vs-pplx-decider-flash.md)
- [Gemini Decision 1 vs RightNow System Zero](https://www.anchorterminal.com/compare/gemini-decision-1-vs-rightnow-system-zero.md)
- [Gemini Decision 1 vs ScaleDown](https://www.anchorterminal.com/compare/gemini-decision-1-vs-scaledown.md)
- [Gemini Decision 1 vs SPEV](https://www.anchorterminal.com/compare/gemini-decision-1-vs-sprag-spev.md)
- [Gemini Decision 1 vs kettei](https://www.anchorterminal.com/compare/gemini-decision-1-vs-sqwish-kettei.md)
- [Gemini Decision 1 vs Strands Decider 2B](https://www.anchorterminal.com/compare/gemini-decision-1-vs-strands-decider.md)
- [Gemini Decision 1 vs Jev](https://www.anchorterminal.com/compare/gemini-decision-1-vs-typesafe-jev.md)
- [Gemini Decision 1 vs Vela 2.0](https://www.anchorterminal.com/compare/gemini-decision-1-vs-vela.md)
- [GLiClass vs Drex 1.5](https://www.anchorterminal.com/compare/gliclass-vs-nace-drex.md)
- [Granite Switch 4.1 vs Drex 1.5](https://www.anchorterminal.com/compare/granite-switch-vs-nace-drex.md)
- [Kev vs Drex 1.5](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-nace-drex.md)
- [Liquid d1 vs Drex 1.5](https://www.anchorterminal.com/compare/liquid-d1-vs-nace-drex.md)
- [Microsoft-Decision-1 vs Drex 1.5](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-nace-drex.md)
- [Drex 1.5 vs OpenAI Decisions API](https://www.anchorterminal.com/compare/nace-drex-vs-openai-decisions-api.md)
- [Drex 1.5 vs pplx-decider](https://www.anchorterminal.com/compare/nace-drex-vs-pplx-decider.md)
- [Drex 1.5 vs pplx-decider-flash](https://www.anchorterminal.com/compare/nace-drex-vs-pplx-decider-flash.md)
- [Drex 1.5 vs RightNow System Zero](https://www.anchorterminal.com/compare/nace-drex-vs-rightnow-system-zero.md)
- [Drex 1.5 vs ScaleDown](https://www.anchorterminal.com/compare/nace-drex-vs-scaledown.md)
- [Drex 1.5 vs SPEV](https://www.anchorterminal.com/compare/nace-drex-vs-sprag-spev.md)
- [Drex 1.5 vs kettei](https://www.anchorterminal.com/compare/nace-drex-vs-sqwish-kettei.md)
- [Drex 1.5 vs Strands Decider 2B](https://www.anchorterminal.com/compare/nace-drex-vs-strands-decider.md)
- [Drex 1.5 vs Jev](https://www.anchorterminal.com/compare/nace-drex-vs-typesafe-jev.md)
- [Drex 1.5 vs Vela 2.0](https://www.anchorterminal.com/compare/nace-drex-vs-vela.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp