Skip to main content
The Kimi K2 series models are available through Upmore via the standard Chat Completions API (/v1/chat/completions). All of them are reasoning models — they think before answering and return the chain-of-thought in reasoning_content. Context window: 256k tokens.

​
Available models

ModelNotes
kimi-k2.7-codeStrongest coding model — reliable instruction-following in long contexts
kimi-k2.7-code-highspeedSame model, ~180 tokens/s output (up to 260 on short contexts), higher price
kimi-k2.6Strongest general model — agentic coding, long-context reasoning, front-end design; vision input
kimi-k2.5Agent / coding / vision all-rounder, thinking and non-thinking modes
Reasoning tokens are billed as completion tokens — budget max_tokens generously. Prompt-cache hits are billed at a reduced input rate automatically.

​
Quick example

curl https://api.upmore.net/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.6",
    "messages": [
      { "role": "user", "content": "Explain quantum entanglement in one paragraph." }
    ]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.upmore.net/v1"
)

response = client.chat.completions.create(
    model="kimi-k2.7-code",
    messages=[
        {"role": "user", "content": "Write a Python function that merges two sorted lists."}
    ]
)

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

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.upmore.net/v1"
)

response = client.chat.completions.create(
    model="kimi-k2.5",
    messages=[
        {"role": "user", "content": [
            {"type": "image_url", "image_url": {"url": "https://example.com/chart.png"}},
            {"type": "text", "text": "Summarize this chart."}
        ]}
    ]
)

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

​
Parameters

ParameterTypeRequiredDescription
modelstringYesOne of the model IDs from the table above
messagesarrayYesList of { role, content } objects; kimi-k2.5 / kimi-k2.6 accept image_url content items
streambooleanNoEnable SSE streaming. Default: false
temperaturefloatNoControls randomness. Default: 1
max_tokensintegerNoMax output tokens including reasoning tokens
stopstring / arrayNoSequences that stop generation
toolsarrayNoList of tools the model may call

​
Response notes

FieldDescription
choices[].message.reasoning_contentThe model’s chain-of-thought (streamed as delta.reasoning_content)
usage.completion_tokens_details.reasoning_tokensReasoning tokens spent — part of completion_tokens
usage.prompt_tokens_details.cached_tokensPrompt cache hits — billed at the discounted cache rate

API Reference

View the interactive API playground.