View on models.dev 
View on OpenRouter X
How to Save Millions by Self-Hosting LLMs
At @cline we're on track to spend about $3M a year on inference for Kimi models. Everyone told us the same thing: it's open-weights, so just self-host and save.
Ara@arafatkatze
Kimi K2.6
Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.
Specs
Model
- Family
- Kimi
- Variant
- K2.6
- Parameters
- 1T
- Weights
- Open
- License
- Modified MIT
Limits
- Context
- 262,144 tokens
- Max output
- 262,144 tokens
Modalities
- Input
- Text Image Video
- Output
- Text
Pricing
- Input
- $0.95 / 1M
- Output
- $4 / 1M
- Cache read
- $0.16 / 1M
Capabilities
- Reasoning
- Yes
- Reasoning control
- On / off
- Tool calling
- Yes
- Attachments
- Yes
Dates
- Released
- 21 Apr 2026
- Knowledge cutoff
- Jan 2025
Articles
All articlesx.com
The Cloudflare Blog
How we built a software factory to drive Astro’s GitHub issue count to zero
By replacing manual issue verification with isolated AI subagents running in GitHub Actions, the Astro maintainers reduced open issue count by 85%. This post explores the architecture behind automated bug reproduction, patch verification, and preview releases.
Matthew Phillips
