Fireworks AI · none caching
Firesearch OCR V6
Firesearch OCR V6 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 | phi3_v |
| Released | — |
| License | Open weights |
| Context window | 8K tokens |
| Max output | — |
| Parameters | 5B |
| Modalities | text, image |
| 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 Firesearch OCR V6 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="firesearch-ocr-v6",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseFrequently asked
Firesearch OCR V6, answered.
How much does Firesearch OCR V6 cost?
Firesearch OCR V6 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 Firesearch OCR V6's context window?
Firesearch OCR V6 supports a 8K-token context window.
Does Firesearch OCR V6 support prompt caching?
Yes. Fireworks AI uses Automatic prompt caching (serverless and dedicated) caching. In the Zumik corpus, Firesearch OCR V6 shows a median cache capture of 75% on agent workloads.
Run Firesearch OCR V6 with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.