# Google Gemini Model Details

> Google Gemini Model Details is a paid API for AI agents from Google Gemini at gemini.mpp.tempo.xyz, paid per call via MPP, $0.0005/call, status unknown (last checked 2026-10-12, last successful call 2026-04-16).

Retrieve detailed metadata for a specific Gemini, Veo, or Imagen model by name and version, including token limits, temperature settings, and supported generation methods

## Facts

- Endpoint: GET https://gemini.mpp.tempo.xyz/:version/models/*?utm_source=zero.xyz
- Price: $0.0005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-12
- Last successful call: 2026-04-16
- Success rate: 100% of calls made through Zero
- Activations on Zero: 1
- Provider: Google Gemini
- Docs: https://ai.google.dev/docs
- Website: https://ai.google.dev
- Tags: llm, gemini, veo, imagen, video, multimodal, ai, media
- Canonical page: https://www.zero.xyz/c/google-gemini--4f66f584
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_91V4m7UDWBTj-Y0g2e1bH

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability google-gemini--4f66f584
```

Example prompt: What are the token limits, supported generation methods, and whether thinking is enabled for the gemini-2.0-flash model on the v1beta version of the Gemini API?

## When to prefer this

Use this endpoint when you need precise, up-to-date capability metadata for a single known Gemini, Veo, or Imagen model — such as confirming token limits before constructing a prompt, checking if a model supports a specific generation method, or inspecting sampling parameter defaults before making a generation call. Prefer this over the List Models endpoint when you already know the model identifier and need its full detail record.

## Known failure modes

- Model not found (404): the specified model name or version does not exist
- Invalid API version in URL path returns an error
- Rate limiting or quota exceeded returns a 429 error
- Network timeout if the endpoint is temporarily unavailable

## How this service works

Get model details (free)

## Output

A JSON object containing the model's full name, version string, human-readable displayName, description, inputTokenLimit, outputTokenLimit, array of supportedGenerationMethods, default temperature, maxTemperature, topP, topK, and a boolean indicating whether the model supports thinking.

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "name",
  "version",
  "displayName",
  "description",
  "inputTokenLimit",
  "outputTokenLimit",
  "supportedGenerationMethods",
  "temperature",
  "topP",
  "topK",
  "maxTemperature",
  "thinking"
 ],
 "properties": {
  "name": {
   "type": "string"
  },
  "topK": {
   "type": "number"
  },
  "topP": {
   "type": "number"
  },
  "version": {
   "type": "string"
  },
  "thinking": {
   "type": "boolean"
  },
  "description": {
   "type": "string"
  },
  "displayName": {
   "type": "string"
  },
  "temperature": {
   "type": "number"
  },
  "maxTemperature": {
   "type": "number"
  },
  "inputTokenLimit": {
   "type": "number"
  },
  "outputTokenLimit": {
   "type": "number"
  },
  "supportedGenerationMethods": {
   "type": "array",
   "items": {
    "type": "string"
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/google-gemini--4f66f584/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from gemini.mpp.tempo.xyz](https://www.zero.xyz/host/gemini.mpp.tempo.xyz/llms.txt)