Google: Gemma 4 26B A4B (free)
Google: Gemma 4 26B A4B (free) is the free-tier variant of google's Gemma 4 26B A4B model, available at $0 per million tokens for both input and output. It supports multimodal inputs including text, image, and video, and offers a 262,144-token context window. This model has not yet been included in our standard benchmark testing suite, so we do not have per-dimension scores or an overall ranking for this variant. The paid version, Gemma 4 26B A4B, has been tested and scored an average of 4.25 across our 12-benchmark suite — placing it among the higher-performing models at its price tier. The free variant is structurally the same model accessed through a different pricing tier, typically subject to rate limits.
Performance
We have not benchmarked Google: Gemma 4 26B A4B (free) directly in our 12-test suite, so we cannot report per-benchmark scores or rankings for this variant. The paid Gemma 4 26B A4B has been tested and scored an average of 4.25 — which places it competitively within the broader tested set. If you need per-benchmark performance data to evaluate this model, refer to the Gemma 4 26B A4B profile, which shares the same underlying model architecture. The free variant's performance characteristics are expected to mirror the paid version, but we recommend validating on your specific workload.
Pricing
This is a free model — $0 per million input and output tokens. There is no direct cost to use it, though free-tier access typically comes with rate limits and lower priority queuing compared to paid API access. For teams exploring the model's capabilities before committing to paid access via Gemma 4 26B A4B ($0.35/M output), the free tier offers a zero-cost evaluation path. For production workloads where reliability and throughput matter, the paid Gemma 4 26B A4B variant at $0.35/M output is the appropriate choice. At 10 million output tokens per month, the paid tier costs $3.50; at 100 million tokens, $35.00.
Google: Gemma 4 26B A4B (free)
External Benchmarks
Pricing
Input
$0.00/MTok
Output
$0.00/MTok
modelpicker.net
Real-World Costs
Pricing vs Performance
Output cost per million tokens (log scale) vs average score across our 12 internal benchmarks
Try It
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="YOUR_OPENROUTER_KEY",
)
response = client.chat.completions.create(
model="google/gemma-4-26b-a4b-it:free",
messages=[
{"role": "user", "content": "Hello, Google: Gemma 4 26B A4B (free)!"}
],
)
print(response.choices[0].message.content)Recommendation
Google: Gemma 4 26B A4B (free) is a reasonable starting point for developers and researchers who want to evaluate this model's multimodal capabilities — including text, image, and video inputs — at zero cost before deciding whether to integrate the paid variant into production. The free tier is appropriate for prototyping, testing, and low-volume exploration. For any production use case that requires consistent throughput, guaranteed response times, or higher rate limits, the paid Gemma 4 26B A4B ($0.35/M output) is the appropriate path. Teams comparing free models should also consider that free tier availability can change without notice.
How We Test
We test every model against our 12-benchmark suite covering tool calling, agentic planning, creative problem solving, safety calibration, and more. Each test is scored 1–5 by an LLM judge. Read our full methodology.