Kimi k3

kimi-k3

Use the Kimi K3 API for chat, coding, and reasoning. Send conversation messages and include tool definitions on supported routes. Build developer assistants for code review, debugging, and implementation. Compare the available provider routes, request examples, and usage prices on OpenAny.

Published price
From $2.607 / 1M tokens
Billing unit
/ 1M tokens
Context / Max output
1000K / 1000K
Listed routes
2

Provider

Published price $2.607 / 1M tokens

Request parameters

POST /v1/chat/completions
Other parameters (7)

Result preview

Neolink · 1848ms

Response example. Run to see the actual response.

{
  "id": "cc0e9f7a7bbe0ead34787584381dd1d4",
  "model": "kimi-k2.5",
  "usage": {
    "total_tokens": 102,
    "prompt_tokens": 8,
    "completion_tokens": 94,
    "prompt_tokens_details": {
      "cached_tokens": 8
    },
    "completion_tokens_details": {
      "reasoning_tokens": 83
    }
  },
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?",
        "reasoning_content": "The user said \"hello\". This is a simple greeting. I should respond in a friendly, helpful manner. Since there's no specific question or task yet, I'll keep it open-ended to invite further conversation.\n\nI should:\n1. Greet them back\n2. Ask how I can help them today\n3. Keep it concise and warm\n\nNo complex reasoning needed here - just a standard polite greeting response."
      },
      "finish_reason": "stop"
    }
  ],
  "created": 1793805552,
  "openmodels_cost": 277
}

Model API questions

How do I call Kimi k3 through OpenAny?

Use model ID kimi-k3 with an OpenAny key and the operation published in this model's API tab. The model API base is https://api.openany.si/v1. Confirm the protocol and request schema; model availability does not imply every OpenAI API operation is supported.

How is Kimi k3 billed?

Compare the published rate and billing unit of the selected provider route. Input, output and cache token rates may differ. Image, audio and video models can use other units. Recorded usage determines the charge under that route's billing contract.

Are Community and Verified routes the same as an official publisher API?

No. Inspect the provider name and supply classification for the specific route. A marketplace listing or a supply label is not a claim of publisher endorsement, identical service or measured uptime. Different route prices may reflect different supply and conditions.

Where do these prices come from, and when were they updated?

Rates come from the provider routes in OpenAny's public model catalog, not an independent quote from the model publisher. The catalog does not supply a price update timestamp. A page or catalog snapshot date is not a price revision date. Compare supply, billing units, tiers and conditions; a lower listed rate alone does not establish equivalent service or explain the price difference.

Use Kimi k3 with your agent

Inspect endpoint contracts and confirm availability and pricing before a paid call.