Sulat.com
AI models
$10 off the fastest DeepSeek V4.1 Flash, Kimi K3 and GLM 5.3 from Synthetic
Requesty logo

Model details

Kimi K2.6 (EU)

Kimi K2.6 is a multimodal workhorse from the kimi-k2 family, developed by Moonshot AI and positioned for agent loops, coding tasks, and visual context handling. The model supports reasoning, tool calling, structured output, and temperature control, making it suitable for orchestrated pipelines that require chain-of-thought reasoning and external function use. Its open-weights availability, published on Hugging Face, allows teams to inspect, fine-tune, or self-host the model alongside managed deployments.

The EU-routed variant through Requesty emphasizes European data sovereignty, with Frankfurt-based inference and a GDPR-compliant posture that includes ISO and SOC2 certifications and a zero data-training policy for inference traffic. This routing makes the model a practical fit for European enterprises that need frontier-scale capabilities while keeping data residency within EU data centers. The large context window supports long-document analysis and multi-turn agent workflows, while multimodal input combined with text-only output streamlines code generation and tool-augmented task automation for regulated environments.

Requestykimi-k2.6@eukimi-k2

Quick Info

Powered by
Provider
Requesty
Model key
kimi-k2.6@eu
Release date
Apr 21, 2026
Last updated
Apr 21, 2026
Knowledge cutoff
2025-01
Input modalities
Output modalities
Capabilities

Cost

Input token cost
$0.95
Output token cost
$4.00

Limits

Output tokens
128,000 tokens
Context window
256,000 tokens

Latest news about Kimi K2.6 (EU)

Requesty

Coverage

The DIT model profile for Kimi K2.6 (published 23 August 2026) characterizes the model as Moonshot AI's prior-generation open-weight flagship, specifying a mixture-of-experts architecture with 1 trillion total parameters and 32 billion active parameters per token, released under a modified MIT-style license. The piece According to the profile, independent capability indexes dropped K2.6's overall ranking after K3 shipped but continued to list it as a clarified coding and long-context performer within its offering class, citing BenchLM and Artificial Analysis. The author argues that K2.6's lighter 32B-active footprint keeps per-token

Videos about Kimi K2.6 (EU)

More models around Kimi K2.6 (EU)