LiteLLMModels

Kimi K2 Instruct API Pricing

As of October 10, 2026, Kimi K2 Instruct costs $0.50 per 1M input tokens and $2.00 per 1M output tokens from DeepInfra, the lowest of 6 providers. It has a 131,072-token context window and returns up to 131,072 tokens per response.

By Moonshot AIModel ID deepinfra/moonshotai/Kimi-K2-InstructPrices updated Checked
Input
$0.50 / 1M tokens
Output
$2.00 / 1M tokens
Context window
131,072 tokens
Max output
131,072 tokens
Providers
6
Added to LiteLLM
July 2025

Kimi K2 Instruct pricing by provider

8 listings across 6 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readContext
DeepInfradeepinfra/moonshotai/Kimi-K2-Instruct$0.50$2.00–128K
Basetensnapshot 0905baseten/moonshotai/Kimi-K2-Instruct-0905$0.60$2.50––
DeepInfrasnapshot 0905deepinfra/moonshotai/Kimi-K2-Instruct-0905$0.50$2.00$0.40256K
Fireworks AIfireworks_ai/accounts/fireworks/models/kimi-k2-instruct$0.60$2.50–128K
Fireworks AIsnapshot 0905fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905$0.60$2.50–256K
Hyperbolichyperbolic/moonshotai/Kimi-K2-Instruct$2.00$2.00–128K
Novita AInovita/moonshotai/kimi-k2-instruct$0.57$2.30–128K
Together AItogether_ai/moonshotai/Kimi-K2-Instruct$1.00$3.00––

What Kimi K2 Instruct costs in practice

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

DeepInfra$2.00
Novita AI$2.29
Baseten$2.45
Fireworks AI$2.45

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

DeepInfra$5.40
Novita AI$6.16
Baseten$6.50
Fireworks AI$6.50

Kimi K2 Instruct features

Use Kimi K2 Instruct with LiteLLM

Call Kimi K2 Instruct 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="deepinfra/moonshotai/Kimi-K2-Instruct",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: kimi-k2-instruct
    litellm_params:
      model: deepinfra/moonshotai/Kimi-K2-Instruct
      api_key: os.environ/DEEPINFRA_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-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Kimi K2 Instruct FAQ

How much does Kimi K2 Instruct cost?

Kimi K2 Instruct costs $0.50 per 1M input tokens and $2.00 per 1M output tokens from DeepInfra, the lowest of 6 providers.

What is the context window of Kimi K2 Instruct?

Kimi K2 Instruct has a 131,072-token context window and returns up to 131,072 tokens per response.

Which providers offer Kimi K2 Instruct?

Kimi K2 Instruct is available from 6 providers through LiteLLM: DeepInfra, Baseten, Fireworks AI, Hyperbolic, Novita AI and Together AI. The lowest price is on DeepInfra.

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

Use the LiteLLM Python SDK with model="deepinfra/moonshotai/Kimi-K2-Instruct", 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 Instruct support?

Kimi K2 Instruct supports function calling, parallel tool calls and structured output.

When did LiteLLM add Kimi K2 Instruct?

Kimi K2 Instruct was added to LiteLLM's model price file in July 2025.

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: DeepInfra, Baseten, Fireworks AI, Hyperbolic, Together AI.

Provider pages: DeepInfra, Baseten, Fireworks AI, Hyperbolic, Novita AI, Together AI.