Kimi K2 series - Upmore

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

Model	Notes
`kimi-k2.7-code`	Strongest coding model — reliable instruction-following in long contexts
`kimi-k2.7-code-highspeed`	Same model, ~180 tokens/s output (up to 260 on short contexts), higher price
`kimi-k2.6`	Strongest general model — agentic coding, long-context reasoning, front-end design; vision input
`kimi-k2.5`	Agent / 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

Parameter	Type	Required	Description
`model`	string	Yes	One of the model IDs from the table above
`messages`	array	Yes	List of `{ role, content }` objects; `kimi-k2.5` / `kimi-k2.6` accept `image_url` content items
`stream`	boolean	No	Enable SSE streaming. Default: `false`
`temperature`	float	No	Controls randomness. Default: `1`
`max_tokens`	integer	No	Max output tokens including reasoning tokens
`stop`	string / array	No	Sequences that stop generation
`tools`	array	No	List of tools the model may call

Response notes

Field	Description
`choices[].message.reasoning_content`	The model’s chain-of-thought (streamed as `delta.reasoning_content`)
`usage.completion_tokens_details.reasoning_tokens`	Reasoning tokens spent — part of `completion_tokens`
`usage.prompt_tokens_details.cached_tokens`	Prompt cache hits — billed at the discounted cache rate

API Reference

View the interactive API playground.