Fireworks AI · none caching
Pythia 12B
Pythia 12B on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.
Specifications
At a glance.
| Provider | Fireworks AI |
| Family | pythia |
| Released | — |
| License | Open weights |
| Context window | 2K tokens |
| Max output | — |
| Parameters | 12B |
| Modalities | text |
| Tool calling | No |
| Reasoning mode | No |
| Caching | none |
| Batch discount | No batch tier |
Measured by Zumik
What reuse looks like here.
Pricing, context, and capabilities for Pythia 12B 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.
Call it
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="pythia-12b",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseFrequently asked
Pythia 12B, answered.
How much does Pythia 12B cost?
Pythia 12B 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 Pythia 12B's context window?
Pythia 12B supports a 2K-token context window.
Does Pythia 12B support prompt caching?
Yes. Fireworks AI uses Automatic prompt caching (serverless and dedicated) caching. In the Zumik corpus, Pythia 12B shows a median cache capture of 77% on agent workloads.
Run Pythia 12B with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.