Available now
Moonshot

kimi-k2.5

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

TextReasoningToolsOpen WeightsVision262.1KVideo
Input$0.72/ 1M
Output$3.78/ 1M
Context262.1K
Endpointsopenai

Capabilities

ReasoningToolsVisionVideoStructured

Modalities

Input
textimage
Output
text

Quick stats

Context window262.1K
Max output262.1K
Modechat
TokenizerOther

Performance

Loading performance data...

Supported parameters

ParameterAlwaysDefault
frequency_penalty-(do not send)
include_reasoning-
logit_bias--
logprobs--
max_tokens--
min_p--
presence_penalty-(do not send)
reasoning-
repetition_penalty-(do not send)
response_format--
seed--
stop--
structured_outputs--
temperature-(do not send)
tool_choice-
tools-
top_k-(do not send)
top_logprobs--
top_p-(do not send)
§ 01

Pricing

Input price$0.72 · 1M tokens
Output price$3.78 · 1M tokens
Context window262.1K tokens
Compatible endpointsopenai
VendorMoonshot
§ 02

Call kimi-k2.5 from your code

Point any OpenAI-compatible SDK at UnoRouter and request the model by name. Replace YOUR_API_KEY with a real key from your dashboard.

bash
curl https://api.unorouter.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Sign in to auto-fill your API key

§ 03

Frequently asked questions

How much does kimi-k2.5 cost per 1M tokens?

Input is priced at $0.72 per 1M tokens, output at $3.78 per 1M tokens. Billing is per token, no rounding to batch sizes.

How do I access kimi-k2.5 via API?

Send requests to the UnoRouter /v1/chat/completions endpoint with model=kimi-k2.5. Any OpenAI-compatible client library works. Authentication uses a standard Bearer token.

What is the context window of kimi-k2.5?

kimi-k2.5 supports a context window of 262.1K tokens, shared between your prompt and the model's response.

§ 04

Similar models

Try kimi-k2.5 now

Create an API key and start making requests in under a minute.

View all models