Kimi K2.7 Code - Kyma API

Overview

Kimi K2.7 Code is Moonshot AI’s June 2026 coding-focused release in the Kimi K2 family, a 1T-parameter mixture-of-experts model released under a modified MIT license. Where the general K2.6 spreads across agentic, vision, and reasoning work, K2.7 Code is built to complete programming tasks reliably over long contexts, and it always operates in a thinking mode that preserves full reasoning across multi-turn conversations. Against K2.6 it posts +21.8% on Kimi Code Bench v2 and +31.5% on MLS Bench Lite while using roughly 30% fewer reasoning tokens — so it tends to reach a correct answer with less generated text, which lowers the effective cost on output-heavy coding loops. It accepts both text and image input and supports function calling and structured outputs, so it slots into existing agent frameworks. On Kyma it routes with automatic failover across multiple serving paths, bills exact per-request cost in usage.cost, and is reachable with the same OpenAI-compatible key as every other model. The 262K-token context window holds a substantial codebase plus the agent’s working state, and the always-thinking design suits multi-step tasks over one-shot replies.

Specs

Field	Value
Model ID	`kimi-k2.7-code`
Best for	End-to-end coding, long-horizon programming, agentic tool use
Context window	262,144
Max output tokens	16K
Input modalities	Text, Image
Output modalities	Text
Tool calling	Yes
Structured outputs	Yes
Prompt caching	No
Speed	Medium
Cost band	Premium
Release stage	Stable

Pricing

	Per 1M tokens
Input	$1.28
Output	$5.40

Use this when

End-to-end coding tasks — Its core design target — completing programming work reliably across long contexts rather than answering isolated snippets.
Agentic programming loops — Function calling plus structured outputs keep read-edit-test-iterate agent cycles parseable and on schema.
Cost-sensitive coding — Roughly 30% fewer reasoning tokens than K2.6 means lower output spend on long, output-heavy sessions.
Multimodal code context — Text-plus-image input lets you pass screenshots, diagrams, or UI mockups alongside the code prompt.

Not ideal for

Quick interactive chat where its always-on thinking mode adds latency, or general non-coding agentic work — for that, Kimi K2.6 is the better fit.

Example

from openai import OpenAI

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

response = client.chat.completions.create(
    model="kimi-k2.7-code",
    messages=[{"role": "user", "content": "..."}],
    tools=[...],  # function calling supported
)

FAQ

How is Kimi K2.7 Code different from K2.6? K2.7 Code is the coding-specialist build: it posts +21.8% on Kimi Code Bench v2 versus K2.6 and uses about 30% fewer reasoning tokens, but it’s tuned for programming rather than the broad agentic and vision work K2.6 covers. It always runs in thinking mode and has a 262K context window. Does Kimi K2.7 Code support tool calling and images? Yes — it supports function calling and structured outputs, and accepts both text and image input, so it works in agent frameworks and can take screenshots or diagrams alongside a code prompt. Why run Kimi K2.7 Code through Kyma? One OpenAI-compatible key and endpoint cover this and every other model on the platform, with automatic failover when a serving path degrades, exact per-request cost in usage.cost, and $0.50 free credit to try it with no card.

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Example

​FAQ