> ## Documentation Index
> Fetch the complete documentation index at: https://docs.venice.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Google Gemma 4 31B Instruct API

> Google Gemma 4 31B Instruct API on Venice: 256K context, $0.12 input and $0.36 output per 1M tokens. Private, with zero data retention.

> [accordion] Plain-text specification
>
> ## Google Gemma 4 31B Instruct API
>
> Google Gemma 4 31B Instruct is a large language model by Google, available on the Venice API as `google-gemma-4-31b-it`. It runs privately, with zero data retention.
>
> Gemma 4 31B is a dense model from Google DeepMind with 31B parameters, delivering frontier-level reasoning performance. It handles text, image, and video input, supports 256K context, function calling, and configurable thinking modes.
>
> ### Google Gemma 4 31B Instruct API pricing
>
> | Model ID | Variant | Privacy | Price |
> | - | - | - | - |
> | `google-gemma-4-31b-it` | Standard | Private | $0.12 / $0.36 per 1M |
>
> ### Google Gemma 4 31B Instruct specifications
>
> | Spec | Value |
> | - | - |
> | Provider | Google |
> | Released | Apr 3, 2026 |
> | Privacy | Private |
> | Status | Stable |
> | Open weights | Yes |
> | Context window | 256K tokens |
> | Max output | 16K tokens |
> | Reasoning effort | none, low, medium, high |
> | Served precision | FP4 |
>
> ### How to use the Google Gemma 4 31B Instruct API
>
> Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "google-gemma-4-31b-it"` and your API key.
>
> ```bash theme={"system"}
> curl https://api.venice.ai/api/v1/chat/completions \
>   -H "Authorization: Bearer $VENICE_API_KEY" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "model": "google-gemma-4-31b-it",
>     "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
>     "reasoning_effort": "low"
>   }'
> ```
>
> ### Related models
>
> * [Google Gemma 3 27B Instruct API](https://docs.venice.ai/models/google-gemma-3-27b-instruct.md): $0.12 / $0.20 per 1M
> * [DeepSeek V4 Flash 0423 API](https://docs.venice.ai/models/deepseek-v4-flash-0423.md): $0.138 / $0.275 per 1M
> * [GLM 4.7 Flash Heretic API](https://docs.venice.ai/models/glm-4-7-flash-heretic.md): $0.07 / $0.40 per 1M
> * [DeepSeek V4 Flash 0731 API](https://docs.venice.ai/models/deepseek-v4-flash-0731.md): $0.13 / $0.26 per 1M
> * [GPT-6 Luna API](https://docs.venice.ai/models/gpt-6-luna.md): $0.10 / $0.50 per 1M


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.