Home › Models › Kimi K3

Kimi K3 API

Moonshot's long-context specialist: 256K tokens for whole-repo review, contract analysis and agentic loops — 20% below official pricing.

FlagshipBest for: Maximum 256K context for heavy agentic workloads.

Why developers pick it

• The largest context window in the Bridge catalog — 256K tokens.
• Built for agentic loops: long histories stay in context, cached-input billing keeps repeats cheap.
• Predictable per-token accounting on every request — critical at 200K-token prompt sizes.

Code example

from openai import OpenAI

client = OpenAI(base_url="https://bridge.computeindex.net/v1", api_key="sk-bridge-YOUR_KEY")

completion = client.chat.completions.create(
    model="kimi-k3",
    messages=[
        {"role": "system", "content": "You summarize long legal documents."},
        {"role": "user", "content": open("contract.txt").read()},
    ],
)
print(completion.choices[0].message.content)

FAQ

Is this the same Kimi K3 as Moonshot's official? Yes — the same model, served through the Bridge OpenAI-compatible gateway.

Can I stream responses? Yes — standard SSE streaming with stream_options.include_usage supported.

Related