Kimi K2.8 Preview
Kimi K2.8 Preview is a Moonshot AI model with a 1M-token context window. It lets you choose how hard it thinks.
Moonshot AI
4 models
Kimi K2.8 Preview in the Moonshot AI constellation, with Kimi K3.1 Pro, Kimi K3.1 Pro Soft-Derisked and Kimi K3.
A star's size and colour follow its API output price. Moonshot AI in the model list
Facts
- Context window
- 1M tokens
- Input
- Text
- Thinking effort
- Adjustable, up to High
- Speed
- Standard
- Available on
- All plans
- Intelligence rank at Vani
- Not ranked
Kimi K2.8 Preview API price
Use this model on the Vani API with the OpenAI- or Anthropic-compatible endpoints. Prepaid API prices per 1M tokens.
| Per 1M tokens | On Vani |
|---|---|
| Input | $0.665 |
| Output | $2.80 |
| Cached input | $0.133 |
In Vani Chat it uses your plan's allowance: tokens per plan.
Kimi K2.8 Preview API quickstart
OpenAI-compatible: point any OpenAI SDK at https://api.vani.ai/v1 and send moonshotai/kimi-k2.8-preview as the model. The Anthropic-compatible /v1/messages endpoint works too.
curl https://api.vani.ai/v1/chat/completions \
-H "Authorization: Bearer $VANI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"moonshotai/kimi-k2.8-preview","messages":[{"role":"user","content":"Hello"}]}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.vani.ai/v1",
api_key=os.environ["VANI_API_KEY"], # a vani_ key
)
reply = client.chat.completions.create(
model="moonshotai/kimi-k2.8-preview",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)import os
from anthropic import Anthropic
client = Anthropic(
base_url="https://api.vani.ai",
api_key=os.environ["VANI_API_KEY"], # a vani_ key
)
message = client.messages.create(
model="moonshotai/kimi-k2.8-preview",
max_tokens=1024,
messages=[{"role": "user", "content": "Hello"}],
)
print(message.content)Compare with
Moonshot AI
Kimi K3
Kimi K3 is a Moonshot AI model with a 1M-token context window. It lets you choose how hard it thinks.
1M context$10.50 output per 1M
Compare side by side with Kimi K3OpenAI
GPT-6.1 Terra
GPT-6.1 Terra is a balanced, cost-efficient model in OpenAI’s GPT-6.1 family, positioned below GPT-6.1 Sol. Designed for everyday agentic workflows, coding, and content creation, it excels at interpreting screenshots and visual interfaces while delivering reliable performance and efficiency for high-volume workloads.
1M context$3.50 output per 1M
Compare side by side with GPT-6.1 TerraZ.AI
GLM-5.3
GLM-5.3 is a Z.AI model with a 1M-token context window. It reads images and lets you choose how hard it thinks.
1M context$3.08 output per 1M
Compare side by side with GLM-5.3
Kimi K2.8 Preview: questions
- What is Kimi K2.8 Preview?
- Kimi K2.8 Preview is a Moonshot AI model with a 1M-token context window. It lets you choose how hard it thinks.
- How large is Kimi K2.8 Preview's context window?
- Kimi K2.8 Preview has a context window of 1M tokens: that is how much it can read at once. It reads text.
- How much does the Kimi K2.8 Preview API cost?
- On the prepaid Vani API, Kimi K2.8 Preview costs $0.665 per 1M input tokens and $2.80 per 1M output tokens ($0.133 per 1M cached input tokens). In Vani Chat it uses your plan's allowance.
- Which Vani plan includes Kimi K2.8 Preview?
- Kimi K2.8 Preview is on every Vani Chat plan, the Free plan included.
Put a question to Kimi K2.8 Preview.
Kimi K2.8 Preview is on every Vani Chat plan, the Free plan included.