LiteLLMLiteLLM/ MODELS

Kimi K3.1 API Pricing

By Moonshot AI · 1 providermoonshotai.kimi-k3.1Compare
Input / output
$4.40 / $22.00 per 1M tokens
Cache read
$0.22 / 1M
Context
869K tokens
Max output
128K tokens

As of November 7, 2026, Kimi K3.1 costs $4.40 per 1M input tokens and $22.00 per 1M output tokens on Amazon Bedrock, with cache reads at $0.22 and cache writes at $5.50 per 1M tokens. It has an 868,928-token context window and returns up to 131,072 tokens per response.

Prices updated Checked

Kimi K3.1 pricing by provider

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

Kimi K3.1 prices by provider in US dollars, token prices per 1M tokens, as of November 7, 2026. Source: LiteLLM model price file.
ProviderModel name in LiteLLMInputOutputCache readCache writeContext
Amazon Bedrockmoonshotai.kimi-k3.1$4.40$22.00$0.22$5.50869K
Amazon BedrockGlobal cross-regionglobal.moonshotai.kimi-k3.1$4.00$20.00$0.20$5.00869K
Amazon BedrockIndia cross-regionin.moonshotai.kimi-k3.1$4.40$22.00$0.22$5.50869K
Amazon BedrockUS cross-regionus.moonshotai.kimi-k3.1$4.40$22.00$0.22$5.50869K

Other Kimi K3.1 prices on Amazon Bedrock

Priority input$7.70 per 1M tokens
Priority output$38.50 per 1M tokens
Flex input$2.20 per 1M tokens
Flex output$11.00 per 1M tokens

What Kimi K3.1 costs in practice

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

Amazon Bedrock$19.80

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

Amazon Bedrock$48.40

Kimi K3.1 cost calculator

At Amazon Bedrock's price ($4.40 input, $22.00 output per 1M tokens), 10,000 requests a day with 1,000 input and 500 output tokens each cost $154 a day, about $4,620 a month. Change the numbers for your workload, or compare it with other models.

Per request
$0.0154
Per day
$154
Per month (30 days)
$4,620

Kimi K3.1 features

Input: text, image. Output: text.

Use Kimi K3.1 with LiteLLM

Call Kimi K3.1 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="moonshotai.kimi-k3.1",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: kimi-k3.1
    litellm_params:
      model: moonshotai.kimi-k3.1
      aws_region_name: os.environ/AWS_REGION_NAME
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LITELLM_API_KEY" \
  -d '{
    "model": "kimi-k3.1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Kimi K3.1 FAQ

How much does Kimi K3.1 cost?

Kimi K3.1 costs $4.40 per 1M input tokens and $22.00 per 1M output tokens on Amazon Bedrock, with cache reads at $0.22 and cache writes at $5.50 per 1M tokens.

What is the context window of Kimi K3.1?

Kimi K3.1 has an 868,928-token context window and returns up to 131,072 tokens per response.

Which providers offer Kimi K3.1?

Kimi K3.1 is available from Amazon Bedrock through LiteLLM, using the model name moonshotai.kimi-k3.1.

How do I call Kimi K3.1 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="moonshotai.kimi-k3.1", 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 K3.1 support?

Kimi K3.1 supports function calling, structured output, image input, reasoning and prompt caching. It does not support audio input.

When did LiteLLM add Kimi K3.1?

Kimi K3.1 was added to LiteLLM's model price file on November 7, 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. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change. Provider pricing pages:

LiteLLM docs: Amazon Bedrock.

Provider pages: Amazon Bedrock.