kimi-k3 API
Call kimi-k3 through a single OpenAI-compatible endpoint — one key, no separate vendor account, no multi-provider wiring.
Moonshot AIChatReasoningCodingVision43.6
Intelligence index
76.2
Coding index
50.0
Agentic index
Pricing
Input$3.08 / 1M tokens (¥20.00)
Output$15.38 / 1M tokens (¥100.00)
Output multiplier×5.00
Context window1M tokens
Max output131K tokens
Prices are per 1M tokens in USD · ¥6.5 = $1 · Billed in CNY
Moonshot AI
Kimi models target long-context reading and code generation, with dedicated coding variants tuned for repository-scale tasks.
When to use it
At $3.08 per 1M input tokens it sits well above the catalogue median of $0.69 — a capability-first choice. Best for coding agents and repository-scale edits. Every model here is reachable with the same API key, so trialling it against a stronger sibling costs one line of code.
Code
from openai import OpenAI
client = OpenAI(
base_url="https://starseaapi.com/v1",
api_key="sk-your-key"
)
r = client.chat.completions.create(
model="kimi-k3",
messages=[{"role": "user", "content": "Explain prefix caching in one paragraph"}]
)
print(r.choices[0].message.content)Other models from this provider
| Models | Input $/M | Output $/M | Intelligence index | Coding index |
|---|---|---|---|---|
| kimi-k2.6 | $1.00 | $4.15 | 27.0 | 61.8 |
| kimi-k2.7-code | $1.00 | $4.15 | 25.8 | 60.8 |
| kimi-k2.8-preview | $1.00 | $4.15 | — | — |