Moonshot (Kimi)
Kimi K2
model
kimi-k2MidStableStreamingToolsLong contextGlobal
Context
200K
Input / 1M tokens
$1.00
Output / 1M tokens
$3.00
Weighted tokens formula
1× provider × 4× tier
About this model
Kimi K2
Moonshot's Kimi K2 — strong Chinese-English bilingual model with native long-context support. Particularly good at long-document tasks and Chinese-language reasoning.
Training cutoff
2024-09
Parameters
Not disclosed
Best for
Use cases
- ✓Chinese-language chat + writing
- ✓Bilingual Chinese-English workloads
- ✓Long-document analysis
Strengths
What it does well
- ●200K context window
- ●Strong Chinese benchmarks
- ●Bilingual balanced quality
Limitations
Know the trade-offs
- !English benchmarks trail GPT-4o / Claude class
- !Smaller community tooling than Western models
Code example
Chat completion with Kimi K2
from openai import OpenAI
client = OpenAI(
base_url="https://api.anoman.io/v1",
api_key="anm-sk-..."
)
response = client.chat.completions.create(
model="kimi-k2",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Weighted tokens
weighted_tokens = raw_tokens × 1 (provider) × 4 (tier)
Pro plan: 20M weighted tokens/month. Combined multiplier 4×: 5,000,000 raw tokens available.
Alternatives
Similar models in our catalog
Workloads that fit Kimi K2 often fit these too. Compare benchmarks and pricing before locking in a default.