CodeGemma 2B
CodeGemma 2B on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.
—
Input / 1M tokens
—
Output / 1M tokens
—
Cache read
8K
Context window
At a glance.
| Provider | Fireworks AI |
| Family | gemma |
| Released | — |
| License | Open weights |
| Context window | 8K tokens |
| Max output | — |
| Parameters | 3B |
| Modalities | text |
| Tool calling | No |
| Reasoning mode | No |
| Caching | none |
| Batch discount | No batch tier |
What reuse looks like here.
Not yet profiled
Pricing, context, and capabilities for CodeGemma 2B 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.
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="codegemma-2b",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseCodeGemma 2B, answered.
How much does CodeGemma 2B cost?
CodeGemma 2B is an open-weights model routed through Fireworks AI. It is priced on the host's serverless size tier rather than a single published per-token list price, so it shows "—" here until profiled.
What is CodeGemma 2B's context window?
CodeGemma 2B supports a 8K-token context window.
Run CodeGemma 2B with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.