XiaoZhan AIhubXiaoZhan AIhub
HomeAI ChatAgentsCreateDigital HumansCreative AgentModel catalogueMarketTopicsPriceDocs
XiaoZhan AIhubXiaoZhan AIhub
HomeAI ChatAgentsCreateDigital HumansCreative AgentModel catalogueMarketTopicsPriceDocs
Model catalogueKimi K2.5

Kimi K2.5

Online

Model ID

Put this value in the request body's `model` field — not the display name above.

Text generationReasoningToolsJSON256kOpen source

by Moonshot · Moonshot Kimi K2.5. 256K context, with prompt caching.

Try it now

Quick start

EndpointPOST /v1/chat/completions
AuthenticationAuthorization: Bearer sk-gpushare-…Get API key
Call styleSynchronous: one request returns the result
Base URLhttps://api.dflop.top/v1
cURL
curl https://api.dflop.top/v1/chat/completions \
  -H "Authorization: Bearer sk-gpushare-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.5",
    "messages": [
      {"role": "user", "content": "你可以帮我做什么"}
    ]
  }'

Pricing

Billed per token: input and output are priced separately and settled on the upstream's reported usage.

Rates
Input 0.2426Credits/K·Output 1.011Credits/K
  • Input tokens that hit the prompt cache are billed at 40.44 Credits / 1M — cheaper than full-price input.
  • Failed requests (upstream 4xx / 5xx) are not billed.
  • All your API keys share one balance; when it runs out the API returns HTTP 402 `quota_exceeded`.

Sign in and any personal discount on your account will show up here. Sign in

Capabilities & specs

Category
Text generation
Context window
256k tokens
Default max output
256k tokens
Endpoint family
Chat Completions
Protocols
OpenAI Chat
Released
2025-11-01
License
Open source
Health
30 min ago

Try it

Pick a key under "API access" and fire one real request to see the response — the estimated cost is shown before you send.

Try it in chat

Common errors

404 model_not_found

You passed the display name instead of the model ID.✗ Kimi K2.5→✓ kimi-k2.5

→ Copy the Model ID at the top of this page

402 quota_exceeded

Insufficient account balance. All your API keys share one balance.

→ Add funds in your account

401 / 403

The API key is invalid, or it has a model allowlist that doesn't include this ID.

→ Check the key's status and allowed models

400 invalid_request

A request body field is invalid, or this model doesn't support the protocol endpoint you called.

→ Check your request body against the sample code above

More models from this vendor

Kimi K2.6kimi-k2.6Kimi K2.7 Codekimi-k2.7-codeKimi K3kimi-k3Kimi K3 1013kimi-k3-1013
Try it

Kimi K2.5 FAQ

How do I call Kimi K2.5?
Set the model field of the request body to kimi-k2.5, send it to https://api.dflop.top/v1/chat/completions, and put your key (it starts with sk-gpushare-) in the Authorization: Bearer header. The official OpenAI, Anthropic and Google Gemini SDKs all work directly; just point base_url at this gateway.
How much does the Kimi K2.5 API cost?
  • ·Input: 242.64 credits (≈ ¥4.04 / ≈ $0.6) per 1M tokens
  • ·Output: 1,011 credits (≈ ¥16.85 / ≈ $2.5) per 1M tokens
  • ·Cached input: 40.44 credits (≈ ¥0.674 / ≈ $0.1) per 1M tokens
  • ·Prices are in credits: 60 credits = ¥1. Each call first holds the most it could cost, then settles on actual usage and refunds the difference.
How large is Kimi K2.5's context window?
256,000 tokens, with a default output limit of 256,000 tokens per request.
What can Kimi K2.5 do?
Tool calling, Thinking mode, JSON mode, Open weights. Compatible protocols: OpenAI Chat Completions.

Input price is about $0.6 per 1M tokens. Markdown version of this page (Chinese): /models/kimi-k2.5.md

Related

  • All Moonshot AI models