Model card

Kimi K2 Thinking

lx1-kimi-k2-thinkingReasoningLive in the catalog

An extended-reasoning specialist: it burns real tokens thinking before it answers, and the answers show it. Budget output generously — the hidden chain-of-thought counts against max_tokens — and give it the problems where a long, careful think beats a fast reply.

Context window262K tokens

Input · per Mtok$0.6

Output · per Mtok$2.5

Served byLayer X1 engine

Where it earns its keep[01/03]

01Extended deliberation on genuinely hard problems
02262K context keeps everything in view while it thinks
03Strong on math, logic, and multi-step plans

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.

Kimi K2 Thinking 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.in/v1/messages \
  -H "x-api-key: lx1_your_key" \
  -H "content-type: application/json" \
  -d '{
    "model": "lx1-kimi-k2-thinking",
    "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 doesn't change.
Everything underneath does.

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

Get a key Read the docs

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

One endpoint. Served by our engine.

Your agent doesn't change.Everything underneath does.

Your agent doesn't change.
Everything underneath does.