Kimi K2.7 Code by Deep Infra | AI model information

The fastest GLM 5.2, Kimi K2.7 and MiniMax M3The fastest GLM 5.2, Kimi K2.7 and MiniMax M3 Discuss

Model details

Kimi K2.7 Code

Deep Inframoonshotai/Kimi-K2.7-Codekimi-k2

Open provider page Provider docs

Quick Info

Provider: Deep Infra
Model key: moonshotai/Kimi-K2.7-Code
Release date: Jun 12, 2026

Cost

Input token cost: $0.74
Output token cost: $3.50

Limits

Output tokens: 262,144 tokens
Context window

Latest news about Kimi K2.7 Code

Videos about Kimi K2.7 Code

Recent tweets and retweets from Deep Infra

Jun 30, 2026, 7:19 PMUTC

We're proud to serve our models on @nvidia inference stack 🚀

Jun 30, 2026, 6:59 PMUTC

We wrote about why we made that bet 👇 deepinfra.com/blog/deepinfra… Link How DeepInfra Built on NVIDIA's Inference Stack and Why It Paid Off Low pay-as-you-go pricing. No long-term contracts. Simple APIs. Scale to trillions of tokens. 100+ AI models. deepinfra.com

Jun 30, 2026, 6:59 PMUTC

We’ve been building on @nvidia's inference stack from day one — TensorRT-LLM, Dynamo, NVFP4 on Blackwell. When DeepSeek V4 dropped, we served it on day 0. Then we moved to B300 after measuring a 4x perf increase. A workload that needed 4×H200 now runs on a single…

Jun 25, 2026, 7:28 PMUTC

Pay attention to the prompt details: "A woman in her twenties dressed as a friendly party clown — light, natural face makeup, a round red nose, bright red curly clown wig, and a colorful costume — performs a magic trick on the green lawn of a cozy backyard birthday party: with…

Jun 25, 2026, 7:28 PMUTC

We keep thinking "How did she do it?" 🎬 Just shipped: LTX-2.3-Distilled-Diffusers is live on Deep Infra. 1080p. 5 seconds of video. ~24 seconds on @nvidia Blackwell. The model is live now at $0.035/second. Stay tuned for speed improvements. Video