Google: Gemma 3 27B: AI model
Gemma 3 27B is Google's open-weight multimodal model with vision-language input, a 128K context and 140+ language coverage. Reachable from inside Iran through Hormouz.
- Context window:
- 131,072 tokens
- Input:
- $0.08/1M tokens
- Output:
- $0.45/1M tokens
- Type:
- text, image
- Vision
- Tools
- Streaming
- Long context
Gemma 3 27B is Google's open-weight model in the Gemma 3 family and the successor to Gemma 2. It introduces multimodality, accepting vision-language input and producing text output, and understands more than 140 languages.
It handles context windows up to about 128K tokens and brings improved maths, reasoning and chat, including structured outputs and function calling. As an open-weight model it is a flexible base for fine-tuning and self-hosting, and here it is served through Hormouz.
Pricing is usage-based: $0.08 per million input tokens and $0.16 per million output tokens. Hormouz provides stable access to Gemma 3 27B from inside Iran, with no foreign credit card or circumvention tooling required.
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,...
Quickstart
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemma-3-27b-it",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | |
|---|---|
| Type | Text, Image |
| Context window | 131,072 tokens |
| Pricing | $0.08/M in · $0.45/M out |
| API | Chat Completions |
| Capabilities | Streaming · Vision · Tools |
Sizes in this family
| Size | Context window | Pricing |
|---|---|---|
| 4B | 131,072 | $0.05/M in · $0.10/M out |
| 12B | 131,072 | $0.05/M in · $0.15/M out |
| 27B | 131,072 | $0.08/M in · $0.45/M out |
Benchmarks
Reasoning
Coding
Agentic
Source: Artificial Analysis
Code example
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemma-3-27b-it",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
model="google/gemma-3-27b-it",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
model: "google/gemma-3-27b-it",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the Google: Gemma 3 27B API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches Google: Gemma 3 27B and 600+ other models, and you pay only for what you use.
- No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- How much does Gemma 3 27B cost?
- Billing is usage-based: $0.08 per million input tokens and $0.16 per million output tokens. There is no fixed monthly fee. You pay only for what you use, at the rates shown in the Hormouz dashboard.
- How do I access Gemma 3 27B from inside Iran?
- Create an account on Hormouz and generate an API key. Hormouz provides a stable path to Gemma 3 27B from inside Iran, with no foreign credit card or circumvention tooling required.
- Is Gemma 3 27B compatible with OpenAI code?
- Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing OpenAI SDKs and code run without a rewrite.
- Is Gemma 3 27B multimodal and open-weight?
- Yes. It is an open-weight model that accepts vision-language input and produces text, understands 140+ languages, and supports structured outputs and function calling, with a context window up to about 128K tokens.
Updated 2026-10-13