Kimi K2.5 API Pricing
As of October 10, 2026, Kimi K2.5 costs $0.60 per 1M input tokens and $3.00 per 1M output tokens on Moonshot AI, with cache reads at $0.10 per 1M tokens. Across 8 providers on LiteLLM, the input price ranges from $0.45 to $0.60. It has a 262,144-token context window and returns up to 262,144 tokens per response.
- Input
- $0.60 / 1M tokens
- Output
- $3.00 / 1M tokens
- Cache read
- $0.10 / 1M tokens
- Context window
- 262,144 tokens
- Max output
- 262,144 tokens
- Providers
- 8
- Added to LiteLLM
- February 2026
Kimi K2.5 pricing by provider
18 listings across 8 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 | Context |
|---|---|---|---|---|---|
| Moonshot AI | moonshot/kimi-k2.5 | $0.60 | $3.00 | $0.10 | 256K |
| Amazon Bedrock | bedrock/moonshotai.kimi-k2.5 | $0.60 | $3.03 | – | 256K |
| Amazon Bedrock | moonshotai.kimi-k2.5 | $0.60 | $3.00 | – | 256K |
| Azure AI Foundry | azure_ai/kimi-k2.5 | $0.60 | $3.00 | $0.10 | 256K |
| Baseten | baseten/moonshotai/Kimi-K2.5 | $0.60 | $3.00 | – | – |
| DeepInfra | deepinfra/moonshotai/Kimi-K2.5 | $0.45 | $2.25 | $0.07 | 256K |
| Fireworks AI | fireworks_ai/accounts/fireworks/models/kimi-k2p5 | $0.60 | $3.00 | $0.10 | 256K |
| Fireworks AI | fireworks_ai/kimi-k2p5 | $0.60 | $3.00 | $0.10 | 256K |
| Novita AI | novita/moonshotai/kimi-k2.5 | $0.60 | $3.00 | $0.10 | 256K |
| Weights & Biases | wandb/moonshotai/Kimi-K2.5 | $0.60 | $3.00 | $0.10 | 256K |
| Amazon Bedrockap-northeast-1 | bedrock/ap-northeast-1/moonshotai.kimi-k2.5 | $0.72 | $3.60 | – | 256K |
| Amazon Bedrockap-south-1 | bedrock/ap-south-1/moonshotai.kimi-k2.5 | $0.72 | $3.60 | – | 256K |
| Amazon Bedrockap-southeast-3 | bedrock/ap-southeast-3/moonshotai.kimi-k2.5 | $0.72 | $3.60 | – | 256K |
| Amazon Bedrockeu-north-1 | bedrock/eu-north-1/moonshotai.kimi-k2.5 | $0.72 | $3.60 | – | 256K |
| Amazon Bedrocksa-east-1 | bedrock/sa-east-1/moonshotai.kimi-k2.5 | $0.72 | $3.60 | – | 256K |
| Amazon Bedrockus-east-1 | bedrock/us-east-1/moonshotai.kimi-k2.5 | $0.60 | $3.00 | – | 256K |
| Amazon Bedrockus-east-2 | bedrock/us-east-2/moonshotai.kimi-k2.5 | $0.60 | $3.00 | – | 256K |
| Amazon Bedrockus-west-2 | bedrock/us-west-2/moonshotai.kimi-k2.5 | $0.60 | $3.00 | – | 256K |
What Kimi K2.5 costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Moonshot AI | $2.70 |
| DeepInfra | $2.025 |
| Amazon Bedrock | $2.715 |
| Azure AI Foundry | $2.70 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Moonshot AI | $6.60 |
| DeepInfra | $4.95 |
| Amazon Bedrock | $6.606 |
| Azure AI Foundry | $6.60 |
Kimi K2.5 features
- Function calling
- Structured output
- Image input
- Video input
- Reasoning
- Prompt caching
Use Kimi K2.5 with LiteLLM
Call Kimi K2.5 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.
from litellm import completion
response = completion(
model="moonshot/kimi-k2.5",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: kimi-k2.5
litellm_params:
model: moonshot/kimi-k2.5
api_key: os.environ/MOONSHOT_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "kimi-k2.5",
"messages": [{"role": "user", "content": "Hello!"}]
}'Kimi K2.5 FAQ
How much does Kimi K2.5 cost?
Kimi K2.5 costs $0.60 per 1M input tokens and $3.00 per 1M output tokens on Moonshot AI, with cache reads at $0.10 per 1M tokens. Across 8 providers on LiteLLM, the input price ranges from $0.45 to $0.60.
What is the context window of Kimi K2.5?
Kimi K2.5 has a 262,144-token context window and returns up to 262,144 tokens per response.
Which providers offer Kimi K2.5?
Kimi K2.5 is available from 8 providers through LiteLLM: Moonshot AI, Amazon Bedrock, Azure AI Foundry, Baseten, DeepInfra, Fireworks AI, Novita AI and Weights & Biases. The lowest price is on DeepInfra.
How do I call Kimi K2.5 with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="moonshot/kimi-k2.5", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does Kimi K2.5 support?
Kimi K2.5 supports function calling, structured output, image input, video input, reasoning and prompt caching.
When did LiteLLM add Kimi K2.5?
Kimi K2.5 was added to LiteLLM's model price file in February 2026.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
- platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart
- docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html
- aws.amazon.com/bedrock/pricing/
- prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'
LiteLLM docs: Moonshot AI, Amazon Bedrock, Azure AI Foundry, Baseten, DeepInfra, Fireworks AI.
Provider pages: Moonshot AI, Amazon Bedrock, Azure AI Foundry, Baseten, DeepInfra, Fireworks AI, Novita AI, Weights & Biases.