Fireworks AI · none caching
PaddleOCR VL 1.6
PaddleOCR VL 1.6 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 | paddleocr_vl |
| Released | — |
| License | Open weights |
| Context window | 131K tokens |
| Max output | — |
| Parameters | 1B |
| 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 PaddleOCR VL 1.6 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="paddleocr-vl-1-6",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseFrequently asked
PaddleOCR VL 1.6, answered.
How much does PaddleOCR VL 1.6 cost?
PaddleOCR VL 1.6 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 PaddleOCR VL 1.6's context window?
PaddleOCR VL 1.6 supports a 131K-token context window.
Does PaddleOCR VL 1.6 support prompt caching?
Yes. Fireworks AI uses Automatic prompt caching (serverless and dedicated) caching. In the Zumik corpus, PaddleOCR VL 1.6 shows a median cache capture of 73% on agent workloads.
Run PaddleOCR VL 1.6 with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.