Gemma 3 12B Instruct
Gemma 3 12B Instruct on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.
At a glance.
| Provider | Fireworks AI |
| Family | gemma3_text |
| Released | 2025-03 |
| License | Open weights |
| Context window | 131K tokens |
| Max output | 8K tokens |
| Parameters | 13B |
| Modalities | text, image |
| Tool calling | No |
| Reasoning mode | No |
| Caching | none |
| Batch discount | No batch tier |
What reuse looks like here.
Pricing, context, and capabilities for Gemma 3 12B Instruct are live, but it is outside the flagship set Zumik benchmarks in depth, so measured reuse, capture, and warm TTFT are not shown yet. Run a workload estimate or route it by id to start collecting traces.
What you actually pay once caching works.
At a typical 55% prefix reuse, a million input tokens on Gemma 3 12B Instruct effectively costs $0.05 instead of $0.05 - blending to roughly $0.06 with a 25% output share. There is no batch tier, so cost control here leans on caching and routing.
Estimate it for your workloadRoute it directly by id, or let an alias pick it when it wins under policy.
Same OpenAI client, this model.
from openai import OpenAI
client = OpenAI(base_url="https://api.zumik.ai/v1", api_key="zk_live_...")
r = client.responses.create(
model="gemma-3-12b-it",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseGemma 3 12B Instruct, answered.
How much does Gemma 3 12B Instruct cost?
Gemma 3 12B Instruct is $0.05 per million input tokens and $0.10 per million output tokens through Zumik. Cache reads are $0.05 per million, a 0% discount on input.
What is Gemma 3 12B Instruct's context window?
Gemma 3 12B Instruct supports a 131K-token context window with up to 8K output tokens.
Run Gemma 3 12B Instruct with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.