Zumik
Sign inSign up

ERNIE-4.5-21B-A3B-PT

ERNIE-4.5-21B-A3B-PT on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.

Call it through ZumikAbout Fireworks AI
—
Input / 1M tokens
—
Output / 1M tokens
—
Cache read
131K
Context window

At a glance.

ProviderFireworks AI
Familyernie4_5_moe
Released—
LicenseOpen weights
Context window131K tokens
Max output—
Parameters21B
Modalitiestext
Tool callingNo
Reasoning modeNo
Cachingnone
Batch discountNo batch tier

What reuse looks like here.

Not yet profiled

Pricing, context, and capabilities for ERNIE-4.5-21B-A3B-PT 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.

python
from openai import OpenAI

client = OpenAI(base_url="https://api.zumik.ai/v1", api_key="zk_live_...")

r = client.responses.create(
    model="ernie-4p5-21b-a3b-pt",
    input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached)   # confirm reuse

ERNIE-4.5-21B-A3B-PT, answered.

How much does ERNIE-4.5-21B-A3B-PT cost?

ERNIE-4.5-21B-A3B-PT 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 ERNIE-4.5-21B-A3B-PT's context window?

ERNIE-4.5-21B-A3B-PT supports a 131K-token context window.

Run ERNIE-4.5-21B-A3B-PT with reuse measured.

Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.

Migration quickstartBack to catalog