LLM Reference

Kimi K2 Thinking Turbo on Vercel AI Gateway

Kimi K2 · Moonshot AI

Serverless

Last refreshed 2026-05-22. Next refresh: weekly.

Why use Kimi K2 Thinking Turbo on Vercel AI Gateway?

Vercel AI Gateway offers Kimi K2 Thinking Turbo with pay-as-you-go pricing at $1.15/1M input tokens. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.

Input / 1M
$1.15
Output / 1M
$8.00
Cache
read $0.15
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install openai
Auth
export AI_GATEWAY_API_KEY=...
Call
import os
from openai import OpenAI
client = OpenAI(
    api_key=os.environ["AI_GATEWAY_API_KEY"],
Model ID
moonshotai/kimi-k2-thinking-turbo

Request example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AI_GATEWAY_API_KEY"],
    base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
    model="moonshotai/kimi-k2-thinking-turbo",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Gotchas

  • Use provider model ID "moonshotai/kimi-k2-thinking-turbo", not the LLMReference slug "kimi-k2-thinking-turbo".
  • creator/model-name e.g. kwaipilot/kat-coder-pro-v2
  • The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.

Pricing

TypePrice (per 1M)
Input tokens$1.15
Output tokens$8.00

Capabilities

No model capability flags are currently sourced.

About Kimi K2 Thinking Turbo

Kimi K2 Thinking Turbo is Moonshot AI's Kimi K2 model. It offers a 256K-token context window.

FAQ

What does Kimi K2 Thinking Turbo cost on Vercel AI Gateway?

On Vercel AI Gateway, Kimi K2 Thinking Turbo costs $1.15 per 1M input tokens and $8 per 1M output tokens.

What is the context window for Kimi K2 Thinking Turbo on Vercel AI Gateway?

Kimi K2 Thinking Turbo supports a 262,114 token context window on Vercel AI Gateway.

What API model ID do I use for Kimi K2 Thinking Turbo on Vercel AI Gateway?

Use the model ID moonshotai/kimi-k2-thinking-turbo when calling Vercel AI Gateway's API.

Who created Kimi K2 Thinking Turbo?

Kimi K2 Thinking Turbo was created by Moonshot AI as part of the Kimi K2 model family.

Is Kimi K2 Thinking Turbo open source?

Kimi K2 Thinking Turbo is not open source; the seed data lists it as proprietary.

Get Started

Model Specs

Released2025-11-06
Parameters1T (32B active)
Context262K

Related Models on Vercel AI Gateway