> ## 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.

> ## Agent Instructions
> The Venice API is OpenAI-compatible: use any OpenAI SDK with the base URL `https://api.venice.ai/api/v1` and a Venice API key, or pay per request from a USDC wallet through x402 with no account.
> Read model IDs from `GET /models` or `GET /models/traits` at runtime instead of hardcoding them from memory or from these pages. Models are added and retired often.
> Every model's price is in https://docs.venice.ai/pricing.md. Quote video and audio jobs with `POST /video/quote` or `POST /audio/quote` before you queue them.
> Search these docs from an MCP client at https://docs.venice.ai/mcp. The full agent guide is https://docs.venice.ai/agents.md.

# Google Gemma 3 27B Instruct API

> Google Gemma 3 27B Instruct API on Venice: 198K context, $0.12 input and $0.20 output per 1M tokens. Private, with zero data retention.



## Google Gemma 3 27B Instruct API

Google Gemma 3 27B Instruct is a large language model by Google, available on the Venice API as `google-gemma-3-27b-it`. This model is private and no prompt data is stored in any capacity.

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's open source model, successor to Gemma 2.

### Google Gemma 3 27B Instruct API pricing

| Model ID | Variant | Privacy | Price |
| - | - | - | - |
| `google-gemma-3-27b-it` | Standard | Private | $0.12 / $0.20 per 1M |

### Google Gemma 3 27B Instruct specifications

| Spec | Value |
| - | - |
| Provider | Google |
| Released | Nov 4, 2025 |
| Privacy | Private |
| Status | Stable |
| Open weights | [google/gemma-3-27b-it](https://huggingface.co/google/gemma-3-27b-it) |
| Context window | 198K tokens |
| Max output | 16K tokens |
| Served precision | FP8 |
| [GPQA Diamond](https://docs.venice.ai/models/methodology.md#benchmarks) | 48.0% ±7.0 (95% interval), run by Venice through the API on Oct 21, 2026 |

### How to use the Google Gemma 3 27B Instruct API

Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "google-gemma-3-27b-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-3-27b-it",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
  }'
```

### Related models

* [Google Gemma 4 31B Instruct API](https://docs.venice.ai/models/google-gemma-4-31b-instruct.md): $0.12 / $0.36 per 1M
* [OpenAI GPT OSS 120B API](https://docs.venice.ai/models/openai-gpt-oss-120b.md): $0.07 / $0.30 per 1M
* [Mistral Small 3.2 24B Instruct API](https://docs.venice.ai/models/mistral-small-3-2-24b-instruct.md): $0.0938 / $0.25 per 1M
* [NVIDIA Nemotron 3 Nano 30B API](https://docs.venice.ai/models/nvidia-nemotron-3-nano-30b.md): $0.075 / $0.30 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


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