9 chat models to pin behind the Versely agent in 2026
The brain plans; the catalog renders. Pin GLM 5.3, Grok 4.6, Kimi, Claude, Gemini — then name Kling or Seedance separately.
The brain plans; the catalog renders. Pin GLM 5.3, Grok 4.6, Kimi, Claude, Gemini — then name Kling or Seedance separately.
Claude ids via OpenRouter take image parts and win on scripts. They still do not burn captions or pick Kling unless you name Kling.
Same attachment rule as GLM: no stills on the wire. Cost-efficient when the brief is already words. Not a video model.
Pick Gemini when the image is the brief. Video and audio attachments are pre-processed through Gemini for non-Gemini brains so you do not have to pick it just to describe a clip.
Pin z-ai/glm-5.3 behind the Versely agent. Text-only, 1M context, reasoning always on. Name Kling or Seedance in the same brief. Do not attach a still.
x-ai/grok-4.6 accepts images and PDFs. z-ai/glm-5.3 is text-only. Pin Grok when the pack shot is the brief; pin GLM when the brief is already words.
Imagine Image, Imagine Video, Extend, TTS are catalog rows. x-ai/grok-4.6 is chat_model. Pin the brain and the renderer separately or the look will drift.
runpod/kimi-k2.7-code is the documented default on /chat-models. Text-only. Changing it changes the plan, not the MP4, unless you also let generate routing wander.
Vision chat id versus /models/qwen-image-3-text-to-image. Two catalogs. Pin both or the slide will be a different model than the planner.
The chat model plans; the generate model renders. Change chat_model to pick the brain, and pin generate models separately when the clip has to match.