How much does Gemma 4 27B cost?

Gemma 4 27B is published as open weights (Apache 2.0) — there is no per-token API price. You self-host the model and pay infrastructure cost (GPU rental and operating overhead). Effective cost on commodity 24-48GB GPUs typically lands at $0.10-$0.50 per million output tokens.

What is the context window of Gemma 4 27B?

Gemma 4 27B supports a context window of 128K tokens (128,000 tokens) and can generate up to 8K output tokens per request.

What is Gemma 4 27B best for?

Gemma 4 27B is best for: Self-hosted general purpose. It supports chat, function_calling, code capabilities. It is open-source under the Apache 2.0 license.

Gemma 4 27B

Googleopen-sourceOpen Source

Google's open-weight flagship under Apache 2.0: April 2026. Designed for self-host with strong instruction-following and tool calling.

Context Window

128K

tokens

Max Output

tokens

Input Price

Self-host

open weights

Output Price

Self-host

infra cost only

Speed

142

tokens/sec

Released

Apr 2026

2026-04-09

Blended Cost

—

self-host

Value Score

—

n/a self-host

Capabilities

ChatFunction CallingCode Generation

Benchmarks

Quality Index

MMLU Pro

79.2

HumanEval (Coding)

81.4

MATH

73.6

Arena ELO

1351

Price vs Quality

Context Window in Context

Grok 3131K
▸ Gemma 4 27B128K
GPT-4o128K
GPT-4o Mini128K
Mistral Large 2128K
DeepSeek V3128K
DeepSeek R1128K
Command R+128K

Bar length is logarithmic — each full step is 10× the tokens. Shown against the models with the nearest context windows, not the directory extremes.

Try in Playground Use via Swfte Connect Google Docs

Compare With

Open Source: Licensed under Apache 2.0

Not on our gateway yet

Gemma 4 27B is open-weight, so you can run it yourself. Swfte Connect turns your deployment into a managed endpoint that speaks the same API as every other model in this directory.

The request

curl https://api.swfte.com/agents/v2/gateway/chat/completions \
  -H "Authorization: Bearer $SWFTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google:gemma-4-27b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Deploy this model with Swfte Connect

About Gemma 4 27B

Gemma 4 27B is a open-source AI model by Google, released on April 9, 2026. It supports a context window of 128K tokens and can generate up to 8K output tokens.

Gemma 4 27B is published as open weights (Apache 2.0) for self-hosting. There is no per-token API price. Cost depends on your inference infrastructure: GPU rental, throughput per GPU, and operating overhead. For commodity 24-48GB GPUs the effective cost typically lands in the $0.10-$0.50 per million output tokens range, well below the cheapest hosted alternatives.

Gemma 4 27B is available as an open-source model under the Apache 2.0 license, meaning you can self-host it for predictable costs or use it through API providers like Swfte Connect.

Using Gemma 4 27B with Swfte

Access Gemma 4 27B through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try Gemma 4 27B in our AI Playground before integrating.