Skip to main content

​
Overview

kimi-k2.5 is the best first pick when your workload looks like an agent instead of a single prompt. It handles tool calls, long sessions, and image-aware workflows more naturally than the rest of the catalog.

​
Specs

FieldValue
Model IDkimi-k2.5
Best forAgentic coding, tool use, multimodal workflows
Context window262K
Max output tokens32K
Input modalitiesText, image
Output modalitiesText
Tool callingYes
Structured outputsYes
Prompt cachingNo
SpeedMedium
Cost bandPremium
Release stageStable

​
Use this when

  • Your coding agent uses lots of tool calls.
  • You need long context for large repos or multi-step tasks.
  • You want one model for text plus screenshots or diagrams.
  • You care more about reliable agent behavior than lowest latency.

​
Pick something else when

  • You want the best general-purpose default: use qwen-3.6-plus.
  • You only need deep reasoning, not agent behavior: use deepseek-r1.
  • You need a cheaper long-context option: use gemini-2.5-flash.

​
Example

from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="ky-...")

response = client.chat.completions.create(
    model="kimi-k2.5",
    messages=[
        {"role": "user", "content": "Plan the refactor, then call tools to inspect the relevant files."}
    ],
    tools=[
        {
            "type": "function",
            "function": {
                "name": "read_file",
                "description": "Read a file from the repo",
                "parameters": {
                    "type": "object",
                    "properties": {"path": {"type": "string"}},
                    "required": ["path"]
                }
            }
        }
    ]
)

​
Agent query example

curl "https://kymaapi.com/v1/models?recommended_for=agent&tools=true&input_modalities=text,image"
AliasResolves to
agentkimi-k2.5