Kimi K2.5
Kimi K2.5 is part of Moonshot AI's Kimi K2 family, an open-weight trillion-parameter mixture-of-experts series tuned for long-context reasoning and agentic workloads. The K2 line is known for strong tool-use, coding, and Chinese-English bilingual quality, with native support for very long inputs. A solid choice for document-heavy agents, code assistants, and bilingual production traffic.
Pricing
Input
$0.600 / 1M
Output
$3.00 / 1M
Pay only for what you use. No subscriptions, no minimums.
Specs
- Context
- 200K
- Max output
- 256K
- Latency
- Medium
- Category
- Text
- Arabic
- Partial
Quick start
Use any OpenAI-compatible client. Just change base_url and your key.
from openai import OpenAI
client = OpenAI(
api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
base_url="https://api.thalam.ai/v1",
)
response = client.chat.completions.create(
model="moonshotai/kimi-k2.5",
messages=[
{"role": "user", "content": "Hello from Thalam!"}
],
)
print(response.choices[0].message.content)Similar models
GPT-5.6 Sol
The top tier of OpenAI's GPT-5.6 generation. Frontier reasoning, coding, and agentic work with a 1M-token context and image input.
GPT-5.6 Terra
The balanced tier of OpenAI's GPT-5.6 generation. Same 1M-token context and image input, tuned for everyday production work.