# Gemma-2 Instruct (27B)

Gemma-2 Instruct (27B) is a language model from Google with a 8K-token context window. Provider list price is $0.80 per million input tokens and $0.80 per million output; on Allocate you pay $0.86 and $0.86 with the 7% transaction fee. The weights are open under Gemma terms, so you can fine-tune it and own the result.

## Pricing

| | Provider list | On Allocate |
| --- | --- | --- |
| Input, per M tokens | $0.80 | $0.86 |
| Output, per M tokens | $0.80 | $0.86 |

Token usage bills at the provider list price plus the 7% transaction fee. Prices checked 2026-07-08.

## Facts

| Field | Value |
| --- | --- |
| Lab | Google |
| Modality | Language |
| Context window | 8K tokens |
| License | Gemma terms |
| Open weights | Yes |
| Fine-tunable | Yes, on your data |
| Catalog id | google/gemma-2-27b-it |

## What a real workload costs

Take 1,000,000 requests a month at 1,200 input and 350 output tokens each: 1,200M input and 350M output tokens. At list prices that is 1,200 × $0.80 + 350 × $0.80 = $1,240 a month. Billed on Allocate it is $1,327 with the 7% transaction fee.

## Common questions

### How much does Gemma-2 Instruct (27B) cost per million tokens?

Provider list price is $0.80 per million input tokens and $0.80 per million output tokens. On Allocate you pay list plus the 7% transaction fee: $0.86 in and $0.86 out.

### What context window does Gemma-2 Instruct (27B) have?

8,192 tokens (8K). At roughly 0.75 words per token, that is about 6k words of English text per request.

### Can I fine-tune Gemma-2 Instruct (27B)?

Yes. Gemma-2 Instruct (27B) is an open-weights model under the Gemma terms license. Read the license terms before fine-tuning for commercial use. On Allocate the trained weights stay inside your boundary and belong to you.

### How do I call Gemma-2 Instruct (27B) on Allocate?

Send google/gemma-2-27b-it in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.

---

[HTML page](https://allocate.network/models/google-gemma-2-27b-it) · [Machine-readable catalog](https://allocate.network/catalog.json)