Home / Models / Google / Gemma 3 27B

Gemma 3 27B pricing and routing profile

Gemma 3 27B from Google lists at $0.08 per million input tokens and $0.45 per million output tokens, with a 131,072-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.08
Output, per 1M tokens$0.45
Cached input, per 1M$0.04
Context window131K
Confidence signalAvailable

Tool callingStructured outputLog probabilities

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$0.0525
Chat reply (2,000 in, 400 out)$0.34
Retrieval-augmented answer (8,000 in, 500 out)$0.865

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Yes. At least one host return token log probabilities for Gemma 3 27B, which is the confidence signal Gimbix uses to let a cheaper model answer first.

Cheaper models that can answer first

Models priced below Gemma 3 27B that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
GLM 4.7 Flash$0.0605 / $0.4017%
Qwen3 Coder 30B A3B Instruct$0.07 / $0.2826%
Llama 3.2 3B Instruct$0.05 / $0.3332%
Gemma 4 26B A4B $0.0675 / $0.22534%
Granite 4.2 8B$0.06 / $0.2535%
Nemotron 3 Nano 30B A3B$0.05 / $0.2047%

Questions

How much does Gemma 3 27B cost?

Gemma 3 27B lists at $0.08 per million input tokens and $0.45 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $0.34 per 1,000 requests.

What is the context window of Gemma 3 27B?

131,072 tokens.

Can a cheaper model replace Gemma 3 27B?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Gemma 3 27B on one half of your requests and make at most three answers worse on the other.