Molmo2-4B
Molmo2-4B 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
37K
Context window
At a glance.
| Provider | Fireworks AI |
| Family | molmo2 |
| Released | — |
| License | Open weights |
| Context window | 37K tokens |
| Max output | — |
| Parameters | 4B |
| Modalities | text, image |
| 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 Molmo2-4B 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="molmo2-4b",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseMolmo2-4B, answered.
How much does Molmo2-4B cost?
Molmo2-4B 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 Molmo2-4B's context window?
Molmo2-4B supports a 37K-token context window.
Run Molmo2-4B with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.