# Gemma 3 27B It API

Google's Gemma 3 27B It, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send gemma-3-27b-it as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

## Facts

- Model name: gemma-3-27b-it
- Maker: Google
- Context window: 40K tokens
- Input price: $0.100 per million tokens
- Output price: $0.200 per million tokens
- Providers: 1 independent provider
- Regions: us

## Providers

- [Pera](https://liquidinference.ai/providers/f651491e-f85b-4f03-b80c-32876aeb80ce.md): us, $0.100 input and $0.200 output per million tokens, $0.100 cache read per million tokens, 40K tokens of context

## Scores

- HLE: 4.4, #217 of 273
- GPQA: 42.8, #223 of 250
- AA-LCR: 7.3, #225 of 237
- SciCode: 23.3, #120 of 123
- Terminal-Bench Hard: 3.8, #146 of 166
- LiveCodeBench: 13.7, #121 of 130
- AIME 2025: 20.7, #83 of 100
- MMLU-Pro: 66.9, #103 of 133
- τ²-Bench: 10.5, #164 of 169
- IFBench: 31.8, #157 of 178
- SimpleQA Verified: 10.4, #121 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

## Request

```sh
curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-3-27b-it",
    "messages": [{"role":"user","content":"Say hello."}]
  }'
```

## Questions

### What is Gemma 3 27B It?

Served by intent-router: each job goes to the cheapest healthy upstream for this model.

### How much does Gemma 3 27B It cost?

Offers now ask $0.100 per million input tokens and $0.200 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.

### What is the context length of Gemma 3 27B It?

The largest offer takes 40,000 input tokens. One job can generate up to 32,768 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.

### What can Gemma 3 27B It do?

Its providers list Vision, JSON object, JSON schema, Frequency penalty, Presence penalty, Seed, Stop sequences, Top-p sampling, Text, Tools.

### What inputs and outputs does Gemma 3 27B It support?

Text · Images → Text.

### Which providers serve Gemma 3 27B It?

1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.

### How do I call Gemma 3 27B It?

Send "gemma-3-27b-it" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.

### When was Gemma 3 27B It listed?

The exchange first listed it on 10/8/2026. This is not its release date.

## Related pages

- [This page in a browser](https://liquidinference.ai/models/gemma-3-27b-it)
- [Gemma 4 26B a4b It:thinking](https://liquidinference.ai/models/gemma-4-26b-a4b-it%3Athinking.md)
- [Diffusiongemma](https://liquidinference.ai/models/diffusiongemma.md)
- [Gemma 3 4B It](https://liquidinference.ai/models/gemma-3-4b-it.md)
- [Gemma 4 12B It Semancer](https://liquidinference.ai/models/gemma-4-12b-it-semancer.md)
- [Gemma 4 12B It](https://liquidinference.ai/models/gemma-4-12b-it.md)
- [Gemma 4 12B It Station Keeper](https://liquidinference.ai/models/gemma-4-12b-it-station-keeper.md)
- [Set up a client](https://liquidinference.ai/connect/gemma-3-27b-it)
- [All models](https://liquidinference.ai/models)
- [Providers](https://liquidinference.ai/providers.md)
- [Discover the best model for your budget](https://liquidinference.ai/discover)
- [Quickstart](https://liquidinference.ai/docs/quickstart.md)
- [llms.txt: the index of every page, as Markdown](https://liquidinference.ai/llms.txt)
- [llms-full.txt: every page in one file](https://liquidinference.ai/llms-full.txt)