LiteLLMModels

Kimi K2.6 API Pricing

As of October 10, 2026, Kimi K2.6 costs $0.95 per 1M input tokens and $4.00 per 1M output tokens on Moonshot AI, with cache reads at $0.16 per 1M tokens. Across 13 providers on LiteLLM, the input price ranges from $0.65 to $1.20. It has a 262,144-token context window and returns up to 262,144 tokens per response.

By Moonshot AIModel ID moonshot/kimi-k2.6Prices updated Checked
Input
$0.95 / 1M tokens
Output
$4.00 / 1M tokens
Cache read
$0.16 / 1M tokens
Context window
262,144 tokens
Max output
262,144 tokens
Providers
13
Added to LiteLLM
April 2026

Kimi K2.6 pricing by provider

14 listings across 13 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readContext
Moonshot AImoonshot/kimi-k2.6$0.95$4.00$0.16256K
AIHubMixaihubmix/kimi-k2.6$0.95$4.00$0.1608256K
Azure AI Foundryazure_ai/kimi-k2.6$0.95$4.00$0.16256K
Basetenbaseten/moonshotai/Kimi-K2.6$0.95$4.00$0.16262K
Cloudflare Workers AIcloudflare/@cf/moonshotai/kimi-k2.6$0.95$4.00$0.16256K
DeepInfradeepinfra/moonshotai/Kimi-K2.6$0.75$3.50$0.15256K
Fireworks AIfireworks_ai/accounts/fireworks/models/kimi-k2p6$0.95$4.00$0.16256K
Fireworks AIfireworks_ai/kimi-k2p6$0.95$4.00$0.16256K
Nebius AI Studionebius/moonshotai/Kimi-K2.6$0.95$4.00–256K
Novita AInovita/moonshotai/kimi-k2.6$0.80$3.40$0.16256K
Sailsail/moonshotai/Kimi-K2.6$1.00$4.00$0.20256K
Tensormeshtensormesh/moonshotai/Kimi-K2.6$0.96$4.00$032K
Together AItogether_ai/moonshotai/Kimi-K2.6$1.20$4.50$0.20256K
Weights & Biaseswandb/moonshotai/Kimi-K2.6$0.65$3.41$0.15262K

What Kimi K2.6 costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Moonshot AI$3.90
Weights & Biases$3.005
DeepInfra$3.25
Novita AI$3.30

100 long-document requests with 100,000 input and 2,000 output tokens each

Moonshot AI$10.30
Weights & Biases$7.182
DeepInfra$8.20
Novita AI$8.68

Kimi K2.6 features

Use Kimi K2.6 with LiteLLM

Call Kimi K2.6 through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="moonshot/kimi-k2.6",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: kimi-k2.6
    litellm_params:
      model: moonshot/kimi-k2.6
      api_key: os.environ/MOONSHOT_API_KEY
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "kimi-k2.6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Kimi K2.6 FAQ

How much does Kimi K2.6 cost?

Kimi K2.6 costs $0.95 per 1M input tokens and $4.00 per 1M output tokens on Moonshot AI, with cache reads at $0.16 per 1M tokens. Across 13 providers on LiteLLM, the input price ranges from $0.65 to $1.20.

What is the context window of Kimi K2.6?

Kimi K2.6 has a 262,144-token context window and returns up to 262,144 tokens per response.

Which providers offer Kimi K2.6?

Kimi K2.6 is available from 13 providers through LiteLLM: Moonshot AI, AIHubMix, Azure AI Foundry, Baseten, Cloudflare Workers AI, DeepInfra, Fireworks AI, Nebius AI Studio, Novita AI, Sail, Tensormesh and Together AI and 1 more. The lowest price is on Weights & Biases.

How do I call Kimi K2.6 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="moonshot/kimi-k2.6", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does Kimi K2.6 support?

Kimi K2.6 supports function calling, structured output, image input, video input, reasoning and prompt caching.

When did LiteLLM add Kimi K2.6?

Kimi K2.6 was added to LiteLLM's model price file in April 2026.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Moonshot AI, AIHubMix, Azure AI Foundry, Baseten, Cloudflare Workers AI, DeepInfra.

Provider pages: Moonshot AI, AIHubMix, Azure AI Foundry, Baseten, Cloudflare Workers AI, DeepInfra, Fireworks AI, Nebius AI Studio, Novita AI, Sail, Tensormesh, Together AI.