Last refreshed 2026-06-20. Next refresh: weekly.
Why use Kimi K2.7-Code HighSpeed on Moonshot AI Kimi?
Moonshot AI Kimi offers Kimi K2.7-Code HighSpeed with competitive pricing. Moonshot AI's platform offers a comprehensive suite of AI-driven solutions, focusing on e-commerce optimization and advanced language processing.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: kimi-k2.7-code-highspeedkimi-k2.7-code-highspeedRequest example
kimi-k2.7-code-highspeed.Gotchas
- Use provider model ID "kimi-k2.7-code-highspeed", not the LLMReference slug "kimi-k2-7-code-highspeed".
Pricing
| Type | Price (per 1M) |
|---|---|
| Image input | $1.00 |
Capabilities
About Kimi K2.7-Code HighSpeed
HighSpeed serving variant of Kimi K2.7-Code optimized for throughput at the cost of latency flexibility. Announced June 15, 2026 — three days after the standard K2.7-Code release. Delivers approximately 180 output tokens per second (up to 260 tokens/s on short-context tasks), around 6× faster than standard K2.7-Code. Same underlying 1T-parameter MoE architecture (32B active, 384 experts, 8 selected per token) with MoonViT vision encoder, 262K context window, and thinking mode always on. Best suited for interactive or latency-bound workflows; the standard variant is preferred for correctness-sensitive long-horizon agentic work.
FAQ
What is the context window for Kimi K2.7-Code HighSpeed on Moonshot AI Kimi?
Kimi K2.7-Code HighSpeed supports a 262k token context window on Moonshot AI Kimi.
What API model ID do I use for Kimi K2.7-Code HighSpeed on Moonshot AI Kimi?
Use the model ID kimi-k2.7-code-highspeed when calling Moonshot AI Kimi's API.
Who created Kimi K2.7-Code HighSpeed?
Kimi K2.7-Code HighSpeed was created by Moonshot AI as part of the Kimi K2 model family.
Is Kimi K2.7-Code HighSpeed open source?
Kimi K2.7-Code HighSpeed is open source under MIT according to the seed data.