DeepSeek Coder V2 Lite Instruct

DeepSeek Coder V2 Lite Instruct 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
164K
Context window

At a glance.

ProviderFireworks AI
Familydeepseek_v2
Released
LicenseOpen weights
Context window164K tokens
Max output
Parameters16B
Modalitiestext
Tool callingNo
Reasoning modeYes
Cachingnone
Batch discountNo batch tier

What reuse looks like here.

Not yet profiled

Pricing, context, and capabilities for DeepSeek Coder V2 Lite Instruct 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="deepseek-coder-v2-lite-instruct",
    input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached)   # confirm reuse

DeepSeek Coder V2 Lite Instruct, answered.

How much does DeepSeek Coder V2 Lite Instruct cost?

DeepSeek Coder V2 Lite Instruct 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 DeepSeek Coder V2 Lite Instruct's context window?

DeepSeek Coder V2 Lite Instruct supports a 164K-token context window.

Run DeepSeek Coder V2 Lite Instruct with reuse measured.

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