Kimi K3 API Pricing

As of October 10, 2026, Kimi K3 costs $3.00 per 1M input tokens and $15.00 per 1M output tokens on Moonshot AI, with cache reads at $0.30 per 1M tokens. Across 13 providers on LiteLLM, the input price ranges from $2.50 to $3.30. It has a 1,048,576-token context window and returns up to 1,048,576 tokens per response.

By Moonshot AIModel ID moonshot/kimi-k3Prices updated October 10, 2026Checked October 10, 2026

Input: $3.00 / 1M tokens
Output: $15.00 / 1M tokens
Cache read: $0.30 / 1M tokens
Context window: 1,048,576 tokens
Max output: 1,048,576 tokens
Providers: 13
Added to LiteLLM: August 16, 2026

Kimi K3 pricing by provider

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

Provider	Model name in LiteLLM	Input	Output	Cache read	Cache write	Context
Moonshot AI	`moonshot/kimi-k3`	$3.00	$15.00	$0.30	–	1M
AIHubMix	`aihubmix/kimi-k3`	$3.00	$15.00	$0.30	–	1M
Amazon Bedrock	`moonshotai.kimi-k3`	$3.30	$16.50	$0.33	$4.125	1M
Baseten	`baseten/moonshotai/Kimi-K3`	$3.00	$15.00	$0.30	–	1M
Databricks	`databricks/databricks-kimi-k3`	$3.00	$15.00	$0.30	$3.00	1M
DeepInfra	`deepinfra/moonshotai/Kimi-K3`	$2.85	$14.25	$0.285	–	1M
Fireworks AI	`fireworks_ai/accounts/fireworks/models/kimi-k3`	$3.00	$15.00	$0.30	–	1M
Fireworks AI	`fireworks_ai/kimi-k3`	$3.00	$15.00	$0.30	–	1M
GitHub Copilot	`github_copilot/kimi-k3`	–	–	–	–	896K
Nebius AI Studio	`nebius/moonshotai/Kimi-K3`	$3.00	$15.00	–	–	1M
Novita AI	`novita/moonshotai/kimi-k3`	$3.00	$15.00	$0.30	–	1M
Perplexity	`perplexity/perplexity/kimi-k3`	$3.00	$15.00	$0.30	–	–
Sail	`sail/moonshotai/Kimi-K3`	$2.50	$12.50	$0.25	–	1M
Together AI	`together_ai/moonshotai/Kimi-K3`	$2.70	$13.50	$0.27	–	1M
Amazon BedrockGlobal cross-region	`global.moonshotai.kimi-k3`	$3.00	$15.00	$0.30	$3.75	1M
Amazon BedrockIndia cross-region	`in.moonshotai.kimi-k3`	$3.30	$16.50	$0.33	$4.125	1M
Amazon BedrockUS cross-region	`us.moonshotai.kimi-k3`	$3.30	$16.50	$0.33	$4.125	1M

What Kimi K3 costs in practice

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

Moonshot AI	$13.50
Sail	$11.25
Together AI	$12.15
DeepInfra	$12.82

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

Moonshot AI	$33.00
Sail	$27.50
Together AI	$29.70
DeepInfra	$31.35

Kimi K3 features

Function calling
Parallel tool calls
Structured output
Image input
Video input
Reasoning
Prompt caching
Web search

Use Kimi K3 with LiteLLM

Call Kimi K3 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-k3",
    messages=[{"role": "user", "content": "Hello!"}],
)

Proxy config.yaml

model_list:
  - model_name: kimi-k3
    litellm_params:
      model: moonshot/kimi-k3
      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-k3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Kimi K3 FAQ

How much does Kimi K3 cost?

Kimi K3 costs $3.00 per 1M input tokens and $15.00 per 1M output tokens on Moonshot AI, with cache reads at $0.30 per 1M tokens. Across 13 providers on LiteLLM, the input price ranges from $2.50 to $3.30.

What is the context window of Kimi K3?

Kimi K3 has a 1,048,576-token context window and returns up to 1,048,576 tokens per response.

Which providers offer Kimi K3?

Kimi K3 is available from 13 providers through LiteLLM: Moonshot AI, AIHubMix, Amazon Bedrock, Baseten, Databricks, DeepInfra, Fireworks AI, GitHub Copilot, Nebius AI Studio, Novita AI, Perplexity and Sail and 1 more. The lowest price is on Sail.

How do I call Kimi K3 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="moonshot/kimi-k3", 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 K3 support?

Kimi K3 supports function calling, parallel tool calls, structured output, image input, video input, reasoning, prompt caching and web search.

When did LiteLLM add Kimi K3?

Kimi K3 was added to LiteLLM's model price file on August 16, 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, Amazon Bedrock, Baseten, Databricks, DeepInfra.

Provider pages: Moonshot AI, AIHubMix, Amazon Bedrock, Baseten, Databricks, DeepInfra, Fireworks AI, GitHub Copilot, Nebius AI Studio, Novita AI, Perplexity, Sail.