Kimi-K2.5

Kimi-K2.5 multimodal chat model by MoonShot via AnyFast OpenAI-compatible API. Vision understanding and thinking mode.

Kimi-K2.5 is a multimodal chat model by MoonShot (月之暗面), available through AnyFast via an OpenAI-compatible interface. It achieves open-source SoTA across agent, coding, and vision-understanding tasks, and supports vision and text input, thinking and non-thinking modes, and both conversational and agent workloads.

Key capabilities

• OpenAI-compatible — Works as a drop-in replacement with the OpenAI SDK
• 256K context — 262,144 tokens for large documents and multi-turn conversations
• Vision understanding — Accepts image and text input; reads text, colors, and shapes in images
• Thinking mode — Toggle via the thinking parameter; returns reasoning_content
• Agent & coding — Open-source SoTA on agent and code tasks
• Rich features — Tool Calls (function calling), JSON Mode, Partial Mode, web search, and automatic context caching

Quick example

cURL

curl https://www.anyfast.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.5",
    "messages": [
      { "role": "user", "content": "Explain quantum entanglement in simple terms." }
    ]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

response = client.chat.completions.create(
    model="kimi-k2.5",
    messages=[
        {"role": "user", "content": "Explain quantum entanglement in simple terms."}
    ]
)

print(response.choices[0].message.content)

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

stream = client.chat.completions.create(
    model="kimi-k2.5",
    messages=[
        {"role": "user", "content": "Write a short poem about the sea."}
    ],
    stream=True
)

for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

# Thinking is enabled by default; pass {"type": "disabled"} to turn it off
completion = client.chat.completions.create(
    model="kimi-k2.5",
    messages=[
        {"role": "user", "content": "Solve x² + 5x + 6 = 0 for x."}
    ],
    extra_body={"thinking": {"type": "enabled"}},
    stream=True
)

for chunk in completion:
    if chunk.choices and chunk.choices[0].delta:
        delta = chunk.choices[0].delta
        if hasattr(delta, "reasoning_content") and delta.reasoning_content:
            print(delta.reasoning_content, end="", flush=True)
        if delta.content:
            print(delta.content, end="", flush=True)

import base64
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

with open("your_image.jpg", "rb") as f:
    img_base = base64.b64encode(f.read()).decode("utf-8")

response = client.chat.completions.create(
    model="kimi-k2.5",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe this image."},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": f"data:image/jpeg;base64,{img_base}"
                        # or a file reference: "url": "ms://<file_id>"
                    }
                }
            ]
        }
    ]
)

print(response.choices[0].message.content)

curl https://www.anyfast.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.5",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "Describe this image."},
          {"type": "image_url", "image_url": {"url": "data:image/png;base64,iVBORw0KGgo..."}}
        ]
      }
    ]
  }'

Note: For vision, message.content must be an array of objects (not a string), and do not serialize the array into a string. image_url accepts a base64 data URI (data:image/png;base64,...) or a file reference (ms://<file_id>). Tokens served from the context cache are reported in usage.prompt_tokens_details.cached_tokens.

Parameters

Parameter	Type	Required	Description
model	string	Yes	Must be kimi-k2.5
messages	array	Yes	List of { role, content } objects. content may be a string or a multimodal array of text/image_url
thinking	object	No	Controls thinking mode, e.g. {"type": "enabled"} (default) or {"type": "disabled"}
max_completion_tokens	integer	No	Maximum tokens to generate. (max_tokens is deprecated and not honored)
temperature	float	No	0–2. Controls randomness. Default: 1
stream	boolean	No	Enable SSE streaming. Default: false
top_p	float	No	Nucleus sampling threshold. Default: 1
response_format	object	No	Set to {"type": "json_object"} to enable JSON Mode
tools	array	No	A list of tools the model may call (function calling)
stop	string / array	No	Sequences that stop generation (up to 5, max 32 bytes each)

API Reference

View the interactive API playground for Kimi-K2.5.