Moonshot

Kimi K2.5

Kimi K2.5 is Moonshot's general-purpose model. It reads images and reasons step by step before it answers. It takes up to 256K tokens of context and writes up to 262.14K per response.

Vision inputReasoningStreaming
Get an API keyCompare models

Output price

$1.92

USD / 1M tokens

36% below list price

Add $5, get $5 more on your first top-up.

Same Kimi K2.5. 36% less.

Price
USD / 1M tokens, next to Moonshot's list price.
TokensList pricePromptsForLess
Input$0.60$0.384
Output$3.00$1.92
Your monthly bill
Enter your monthly usage to see the difference.
At list price$12
With PromptsForLess$7.68

That's $4.32 saved every month.

USD, before tax and prompt caching.

Specs.

Model ID
kimi-k2.5
Made by
Moonshot
Context window
256K tokens
Max output
262.14K tokens
Endpoint
/v1/chat/completions
Billing
Per token, from one balance
Built for
  • Text and code. Drafting, summarising, extraction, chat and code, with the output streamed back as it is generated.
  • Reasoning. Works through multi-step problems before answering, for planning, analysis and agent workflows.
  • Vision. Send screenshots, photos, charts and documents alongside your prompt.

Edge gateways

Requests enter at the gateway nearest your app and go straight to the model, so routing adds very little to each call.

One key, every model

Switch models by changing a string. One prepaid balance covers all of them, billed per token.

Nothing stored

We keep token counts for billing, never your prompts or responses.

Call Kimi K2.5 in a minute.

Point any OpenAI-compatible client at our base URL, keep your key in an environment variable, and use the model ID kimi-k2.5.

Copy
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.promptsforless.com/v1",
    api_key=os.environ["PFL_API_KEY"],
)

response = client.chat.completions.create(
    model="kimi-k2.5",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
Cursor guideOpenCode guideOpenAI SDK guide

More from Moonshot.

1M context

Kimi K3

$9.00 / 1M tokens output

40% below list

256K context

Kimi K2 Thinking

$1.26 / 1M tokens output

37% below list

Similar price, other makers

Google

Gemini 3 Flash

$1.92 / 1M tokens output

36% below list

DeepSeek

DeepSeek V4 Pro 0813

$1.9404 / 1M tokens output

51% below list

Alibaba

Qwen3.8 27B

$1.83 / 1M tokens output

39% below list

Z.ai

GLM-5

$1.664 / 1M tokens output

48% below list

Questions.

How much does Kimi K2.5 cost?

$1.92 / 1M tokens output and $0.384 / 1M tokens input, 36% below Moonshot's list price. You pay per token from a prepaid balance, with no subscription or minimum. We match your first $5 top-up, so you start with $10 of credit.

Is it the real Kimi K2.5?

Yes. Your requests run on Moonshot's Kimi K2.5, not a distilled copy or a substitute. The discount comes from how we buy capacity, not from changing the model.

Which tools can use Kimi K2.5?

Anything that speaks the OpenAI API: set the base URL to our endpoint and use the model ID kimi-k2.5. We have setup guides for Cursor, Codex, OpenCode, the OpenAI and Vercel AI SDKs, LangChain and more.

How fast is it?

Requests go through our edge gateways, so the network hop adds very little on top of Kimi K2.5's own generation time. Responses stream back token by token.