# Gemini Decision 1: API Pricing, Agent Routing and Mac Limits

- URL: https://ai-on-mac.com/articles/gemini-decision-1-en/
- Language: English (United States)
- Published: 2026-11-13
- Updated: 2026-11-13
- Category: Model News
- German version: https://ai-on-mac.com/artikel/gemini-decision-1/
- Publisher: Julian Dominic Altmann, AI on Mac / KI auf dem Mac (https://ai-on-mac.com)

> Gemini Decision 1 costs $0.10 per million input tokens. Explore structured decisions, shared-input pricing, agent routing and Apple Silicon limits.

**Verdict:** A cloud decision layer for classification and routing, not a locally runnable generative model.

Google released Gemini Decision 1 on November 11, 2026. Its purpose is to make bounded decisions rather than write answers: classify a request, select a tool, or grade a document. It supports multimodal input and costs **$0.10 per million input tokens**, with no billed output tokens. [Google launch](https://blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api/) · [Pricing](https://aistudio.google.com/docs/pricing#gemini-decision)

Verified November 13, 2026. This analysis is based on public documentation and calculated cost scenarios, not our own model performance measurements.

## Specifications and availability

| Item | Gemini Decision 1 |
|---|---|
| Native ID | `gemini-decision-1` |
| Gateway ID | `google/gemini-decision-1` |
| Context | 262,144 tokens including questions |
| Inputs | Text, images, audio, video, PDF |
| Output | Typed decisions and probabilities |
| Questions | 1–1,000 per request |
| Choice options / rubric levels | 2–255 |
| Input price | $0.10 / million tokens |
| Output tokens | 0 |
| Context caching / Batch API | Not supported |
| Downloadable weights | No public release confirmed |

Sources: [Google Decisions API](https://aistudio.google.com/docs/decisions-api), [OpenRouter](https://openrouter.ai/google/gemini-decision-1). The question count is subject to the total context limit.

## A dedicated decision layer

An agent often needs to branch before it generates an answer. A general-purpose LLM can emit a JSON category, but generating and parsing text is unnecessary for many bounded classification tasks. The Decisions API evaluates the options directly and returns structured results.

| Question type | Result | Example |
|---|---|---|
| `noul` | Probability of yes | Does the request require code? |
| `choice` | Chosen option and probability distribution | Which handler should run? |
| `score` | Expected score on an ordered rubric | How complex is this task? |

  ![The noul, choice and score decision types.](https://ai-on-mac.com/images/gemini-decision-1/types-light.svg)

*Three supported question types, based on Google's API documentation.*

A probability of yes near zero can indicate a strong negative prediction rather than uncertainty. Confidence provides a separate signal for escalation. Questions operate on the same input independently, so they cannot inspect one another's answers. A sequential decision workflow requires application-side orchestration. [API guide](https://aistudio.google.com/docs/decisions-api)

## Pricing: how much do requests cost?

The direct Gemini Developer API charges $0.10 per million input tokens on its standard paid tier. Google offers a free tier within its usage limits; neither context caching nor Batch API is supported for this model.

Assuming 2,000 billable input tokens per request:

| Monthly requests | Input tokens | Model cost (USD) |
|---:|---:|---:|
| 1,000 | 2 million | 0.20 |
| 10,000 | 20 million | 2.00 |
| 100,000 | 200 million | 20.00 |
| 1,000,000 | 2 billion | 200.00 |

The estimates use requests × tokens × $0.10 / 1,000,000. They exclude taxes, gateway charges, retries and subsequent inference. See [Google pricing](https://aistudio.google.com/docs/pricing#gemini-decision).

### Shared input changes the economics

Suppose a document contains 10,000 tokens and must be evaluated against 20 independent questions containing 100 tokens each. Separate requests consume 202,000 tokens and cost $0.0202. A combined request consumes an estimated 12,000 tokens and costs $0.0012.

  ![Separate requests use 202,000 tokens versus 12,000 for a combined request.](https://ai-on-mac.com/images/gemini-decision-1/shared-input-light.svg)

*Illustrative calculation: 94.1% lower input cost for the same independent questions.*

The saving is approximately 94.1%. This is not a measured bill: actual formatting adds overhead, and all questions must fit the context window. Unlike cross-request caching, the benefit comes from reusing the shared input within a single call.

For N documents of D tokens, Q questions and T tokens per question, the combined cost in dollars is N × (D + Q × T) × 0.10 / 1,000,000. Separate requests cost N × Q × (D + T) × 0.10 / 1,000,000.

## Agent routing on Apple Silicon

A developer assistant might use a local model for simple questions, a cloud coding model for implementation and a larger reasoning model for difficult investigations. Gemini Decision 1 can classify requests at the entry point, while the application owns the execution policy.

  ![Mac application, remote decision service and local, cloud or human execution paths.](https://ai-on-mac.com/images/gemini-decision-1/routing-light.svg)

*Illustrative hybrid routing architecture, not an official Google system diagram.*

Low-confidence decisions should enter a review or fallback path. Do not treat classifier outputs as authorization for high-impact tool calls: access control must remain independent.

The following Python example uses the documented Google GenAI SDK interface (version 3.2 or later). Install with `python3 -m pip install -U google-genai` and set `GEMINI_API_KEY`.

```python
from google import genai

client = genai.Client(http_options={"api_version": "v1beta"})
result = client.decisions.create(
    model="gemini-decision-1",
    input="Find the cause of a Python race condition.",
    questions={
        "coding": {
            "type": "noul",
            "instructions": "Does this request require software debugging?"
        }
    }
)
answer = result.answers["coding"]
if answer.noul >= 0.90 and answer.confidence >= 0.85:
    print("coding")
else:
    print("review")
```

The example follows Google's [API documentation](https://aistudio.google.com/docs/decisions-api), but was not executed against the live service. The thresholds are illustrative, not validated production settings.

## API providers and performance

Google's native endpoint is `https://generativelanguage.googleapis.com/v1beta/decisions`. OpenRouter uses a separate decisions endpoint; do not assume an OpenAI-compatible chat client will work. Vercel offers the model through AI SDK and decision interfaces, with audio, video and PDF support through AI SDK 7. [OpenRouter](https://openrouter.ai/google/gemini-decision-1) · [Vercel](https://vercel.com/changelog/gemini-decision-1-now-available-on-ai-gateway)

Google reports 150–250 milliseconds of end-to-end latency under its launch evaluation conditions. These figures should not be generalized to arbitrary media sizes or gateway connections. [Google launch](https://blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api/). Independent comparable measurements remain limited.

| Decision model (OpenRouter) | Input / million tokens (USD) | Context |
|---|---:|---:|
| Gemini Decision 1 | 0.10 | 262,144 |
| Liquid d1.1 | 0.02 | 65,536 |
| Perplexity Decider V1.2 | 0.02 | approx. 262K |

  ![Gemini costs $0.10 per million input tokens, versus $0.02 each for Liquid and Perplexity.](https://ai-on-mac.com/images/gemini-decision-1/pricing-light.svg)

*OpenRouter listed prices, rounded as displayed; this is not a quality ranking.*

Sources: [Gemini](https://openrouter.ai/google/gemini-decision-1), [Liquid](https://openrouter.ai/liquid/d1.1/), [Perplexity](https://openrouter.ai/perplexity/pplx-decider-v1.2/). Gemini's nominal input rate is five times the displayed rate for either alternative. Their input modalities and accuracy can differ. Benchmark the same workloads before choosing a provider.

## Local deployment and privacy

No publicly downloadable weights have been confirmed for Gemini Decision 1. It is therefore not a documented local inference option for MLX, Ollama or llama.cpp. Apple Silicon can run the downstream model while Gemini Decision 1 handles selected remote classifications. The routing request itself still crosses the device's privacy boundary.

OpenRouter explicitly marks Gemini Decision 1 as unavailable through EU in-region routing. Google's [API terms](https://aistudio.google.com/docs/terms) distinguish service tiers and regions; paid service data handling does not establish exclusive EU residency. Applications processing sensitive information need appropriate contractual and technical guarantees for their specific deployment.

## Evaluate the whole workflow

A useful initial test includes at least several hundred labeled examples, covering ordinary, ambiguous and rare requests. Compare precision, recall and F1 by category; automated coverage versus routing errors; median and P95 latency; total token usage and downstream retries. A confidence threshold trades automation against errors. Evaluate probability calibration with [reliability diagrams](https://scikit-learn.org/stable/modules/calibration.html) and a proper scoring rule.

The relevant cost is the complete pipeline, not just the router's nominal token price. If a misrouted request causes extra model calls, a cheap classifier can increase costs. For fully offline applications, a local classifier or local LLM is a more appropriate baseline.

Related: [Gemini API pricing](https://ai-on-mac.com/articles/google-gemini-pricing-cost-2026/), [TypeSafe Jev Router](https://ai-on-mac.com/articles/jev-router-typesafe-openrouter-en/) and [Gemma 4 local setup](https://ai-on-mac.com/articles/gemma4-mac-setup/).

## Sources

1. https://blog.google/innovation-and-ai/technology/developers-tools/gemini-decisions-api/
2. https://aistudio.google.com/docs/decisions-api
3. https://aistudio.google.com/docs/pricing#gemini-decision
4. https://openrouter.ai/google/gemini-decision-1
5. https://vercel.com/changelog/gemini-decision-1-now-available-on-ai-gateway
6. https://aistudio.google.com/docs/terms
7. https://openrouter.ai/docs/guides/features/in-region-routing
8. https://openrouter.ai/liquid/d1.1/
9. https://openrouter.ai/perplexity/pplx-decider-v1.2/
10. https://scikit-learn.org/stable/modules/calibration.html
