kimi-k3.1-pro

Kimi K3.1 Pro 支持百万 token 上下文和原生视觉理解，可用于代码开发、3D 创作、研究分析及复杂 Agent 任务。

text → image → text

Modalities

In / Out Price

$2/ 1M

$2 Official price

$10/ 1M

$10 Official price

1.048576M

Context

Oct 23, 2026

Released

Providers

This model is hosted by one provider. Requests are forwarded to it directly, with no routing decisions to make.

Provider	Input /M	Output /M	Context	Latency	Throughput	Uptime
Moonshot	$2 $2 Official price	$10 $10 Official price	1.048576M	—	—	—

Call this model in three steps.

Get your API key

Create a key and set your API key and base URL as environment variables.

Create API Key

Environment

export UNIROUTER_API_KEY="<YOUR_API_KEY>"
export UNIROUTER_BASE_URL="https://api.tokatlas.com/v1"

Choose a request format

Choose the format supported by your selected route.

Make your first request

Model ID: kimi-k3.1-pro

from openai import OpenAI

client = OpenAI(
    base_url="https://api.tokatlas.com/v1",
    api_key="<YOUR_API_KEY>",
)
response = client.chat.completions.create(**{
    "model": "kimi-k3.1-pro",
    "messages": [
        {
            "role": "user",
            "content": "Explain quantum entanglement."
        }
    ],
    "temperature": 0.7
})

print(response)

Endpoint

Creates a model response for the given chat conversation.

POST: https://api.tokatlas.com/v1/chat/completions
Authorization: Bearer $UNIROUTER_API_KEY
Content-Type: application/json