LiteLLMModels

Kimi K3 Fast API Pricing

As of October 10, 2026, Kimi K3 Fast costs $4.50 per 1M input tokens and $22.50 per 1M output tokens on Fireworks AI, with cache reads at $0.45 per 1M tokens. It has a 1,048,576-token context window and returns up to 131,072 tokens per response.

By Moonshot AIModel ID fireworks_ai/kimi-k3-fastPrices updated Checked
Input
$4.50 / 1M tokens
Output
$22.50 / 1M tokens
Cache read
$0.45 / 1M tokens
Context window
1,048,576 tokens
Max output
131,072 tokens
Providers
1
Added to LiteLLM
August 20, 2026

Kimi K3 Fast pricing by provider

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

ProviderModel name in LiteLLMInputOutputCache readContext
Fireworks AIfireworks_ai/kimi-k3-fast$4.50$22.50$0.451M
Fireworks AIfireworks_ai/accounts/fireworks/routers/kimi-k3-fast$4.50$22.50$0.451M

What Kimi K3 Fast costs in practice

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

Fireworks AI$20.25

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

Fireworks AI$49.50

Kimi K3 Fast features

Use Kimi K3 Fast with LiteLLM

Call Kimi K3 Fast 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="fireworks_ai/kimi-k3-fast",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: kimi-k3-fast
    litellm_params:
      model: fireworks_ai/kimi-k3-fast
      api_key: os.environ/FIREWORKS_AI_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-fast",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Kimi K3 Fast FAQ

How much does Kimi K3 Fast cost?

Kimi K3 Fast costs $4.50 per 1M input tokens and $22.50 per 1M output tokens on Fireworks AI, with cache reads at $0.45 per 1M tokens.

What is the context window of Kimi K3 Fast?

Kimi K3 Fast has a 1,048,576-token context window and returns up to 131,072 tokens per response.

Which providers offer Kimi K3 Fast?

Kimi K3 Fast is available from Fireworks AI through LiteLLM, using the model name fireworks_ai/kimi-k3-fast.

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

Use the LiteLLM Python SDK with model="fireworks_ai/kimi-k3-fast", 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 Fast support?

Kimi K3 Fast supports function calling, structured output, image input and reasoning.

When did LiteLLM add Kimi K3 Fast?

Kimi K3 Fast was added to LiteLLM's model price file on August 20, 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: Fireworks AI.

Provider pages: Fireworks AI.