Model card

DeepSeek V4 Flash

lx1-deepseek-v4-flashGeneral purposeLive in the catalog

The catalog default: a 284-billion-parameter mixture-of-experts with only 13 billion active per token, which is why it answers about twice as quickly as its Pro sibling while carrying the same million-token window. If you don't name a model, this is the one serving you. A first token in well under a second, throughput that holds steady, and reasoning you can surface whenever you want to see the working.

Context window1M tokens

Input · per Mtok$0.44

Output · per Mtok$1.32

Served byLayer X1 engine

Where it earns its keep[01/03]

01Around twice the throughput of the V4 Pro
02A 1M-token window at general-purpose pricing
03Tight, predictable latency for all-day agent traffic

Capabilities

Tool callingYes

Strict, schema-faithful tool calls, enforced by the engine on every request — safe to build an agent loop on.

ReasoningYes

Thinks before it answers. Budget max_tokens generously — hidden reasoning counts against it.

VisionNo

Text-only.

Behind the endpoint[02/03]

One endpoint. Served by our engine.

DeepSeek V4 Flash is served through the Layer X1 engine — zero-downtime serving is the design target, not a status-page apology. You request it by name; everything else is our problem.

Call it by name

curl https://api.layerx1.com/v1/messages \
  -H "x-api-key: lx1_your_key" \
  -H "content-type: application/json" \
  -d '{
    "model": "lx1-deepseek-v4-flash",
    "max_tokens": 1024,
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

OpenAI-style clients work too — send the same model name to /v1/chat/completions with a Bearer key. See the docs for both dialects.

Your agent stays the same.
Its inference gets better.

$export ANTHROPIC_BASE_URL=https://api.layerx1.com

Get a key Read the docs

Start free · no card · Starter from $5/mo

One endpoint. Served by our engine.

Your agent stays the same.Its inference gets better.

Your agent stays the same.
Its inference gets better.