🎁 New Sign up free, 10 calls on us. Up to $1, no card needed.

Kimi K2.7 Code Released 2026-06

Moonshot chat code reasoning tools
Input$0.95/M
Output$4/M
Cache read$0.19/M
Context256K
vs GPT-4o~81% cheaper

Provider list prices: no platform markup, pay-as-you-go. These are official list prices. Logged-in customers may see effective prices including workspace discounts on /console/pricing. Effective input at a 70% cache-hit rate:$0.418/M. Automatic caching with hit/miss pricing: cached input tokens bill at the discounted cache-hit rate, no cache management required.

Use Kimi K2.7 Code in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="kimi-k2.7-code",
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

About Kimi K2.7 Code

About 30% fewer thinking tokens
Reasoning preserved across multi-turn conversations
Tuned for real-world software engineering

Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built upon Kimi K2.6, tuned for real-world software engineering.

  • It keeps the 1T-parameter Mixture-of-Experts architecture with 32B activated per token and a 256K context, accepts image input alongside text, and always runs in thinking mode with reasoning content preserved across multi-turn conversations.
  • Officially, it strengthens end-to-end task completion across complex software engineering workflows while using about 30% fewer thinking tokens than K2.6, and supports agentic tool use through the MCP ecosystem.
  • Weights are open under a Modified MIT license.
  • Access Kimi K2.7 Code on Synthorai through the OpenAI-compatible endpoint.

Specs & limits

Max output (vendor spec)32,768
Modalitiestext + image + video → text
Parameters1T total · 32B active (MoE)
Featurestools · streaming · vision · reasoning
LicenseModified-MIT ↗
NotableCoding-focused agentic model built on K2.6: 1T/32B active MoE, 256K context; thinking always on with preserved reasoning across turns; ~30% fewer thinking tokens vs K2.6.
Prompt cachingautomatic

per Moonshot official docs ↗

FAQ

Is the Kimi K2.7 Code API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $0.95/M input tokens, that credit alone covers roughly 131 requests of ~8K tokens against Kimi K2.7 Code.

What is Kimi K2.7 Code best at?

About 30% fewer thinking tokens, plus reasoning preserved across multi-turn conversations and tuned for real-world software engineering. See the About section for the full picture from the vendor's own release notes.

How much does Kimi K2.7 Code cost?

Kimi K2.7 Code costs $0.95 per million input tokens and $4 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.19/M.

Does Kimi K2.7 Code support prompt caching?

Yes, automatically: Moonshot-served prompts cache with no code changes. Cached input tokens bill at $0.19/M vs $0.95/M uncached. Prompt caching guide →

How do I get access to Kimi K2.7 Code?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="kimi-k2.7-code", and you're done. One API key covers every model on the gateway.

Is Kimi K2.7 Code open source?

Yes: the weights are published under the Modified-MIT license. Or skip the GPUs: the hosted version here is pay-as-you-go with no infrastructure to run. Running open-weight models →

Related models

Get your free API key Compare your cost →