@modal: You can now run Kimi K3 in Codex on Modal. K3 leads open models on agentic coding benchmarks, with native vision and a …
Summary
Kimi K3, an open model that leads agentic coding benchmarks with native vision and a 1M-token context window, is now available to run in Codex on Modal via its Shared Endpoint.
View Cached Full Text
Cached at: 07/31/26, 08:54 PM
You can now run Kimi K3 in Codex on Modal. K3 leads open models on agentic coding benchmarks, with native vision and a 1M-token context window. Try it on our Shared Endpoint. https://t.co/VrBFkiKNW1
Similar Articles
Kimi K3 is now live
Kimi AI has launched K3, a new model built for agentic coding and knowledge work, now live on their platform.
Kimi K3: Open Frontier Intelligence
Kimi introduces Kimi K3, a 2.8 trillion parameter open model with native vision and 1M context, built on Kimi Delta Attention and Attention Residuals. It achieves frontier-level performance in coding and reasoning, with full weights to be released by July 2026.
Kimi K3 Now Available via Telnyx Inference API
Kimi K3, a 2.8-trillion-parameter open-source model from Moonshot AI with 1M token context and native vision, is now available on the Telnyx Inference API for tasks like coding, reasoning, and multimodality.
unsloth/Kimi-K3
Kimi K3 is an open-weight 2.8T-parameter native multimodal agentic model with a novel architecture (KDA, AttnRes), 1M token context, and open-source MoE framework.
Kimi K3’s open weights drop today — is anyone actually using Chinese AI models instead of Claude or Codex?
Moonshot AI releases open weights for Kimi K3, a 3T-parameter frontier model focused on long-horizon coding, repository-scale context, and tool use, allowing self-hosting and fine-tuning.