Model card

Kimi K3

sdn-kimi-k3FrontierLive in the catalog

The top of the Kimi line: a 2.8-trillion-parameter flagship with vision and a million-token window. It's priced like the frontier it sits in, so spend it where depth decides the outcome — hard multi-step problems, long agent runs, and work that mixes screenshots with very large codebases.

Context window1M tokens

Input · per Mtok$3

Output · per Mtok$15

Served bySideren engine

Where it earns its keep[01/03]

01Frontier-class reasoning from the strongest Kimi yet
02Vision plus a 1M-token window
03Stays coherent across very long agent runs

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.

VisionYes

Reads images — screenshots, diagrams, and UI states — inline in the conversation.

Behind the endpoint[02/03]

One endpoint. Served by our engine.

Kimi K3 is served through the Sideren 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.sideren.io/v1/messages \
  -H "x-api-key: sdn_your_key" \
  -H "content-type: application/json" \
  -d '{
    "model": "sdn-kimi-k3",
    "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.sideren.io

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.