Skip to content
llms.party

Models

Clients ask for a model group, a stable name like deepseek-flash. The gateway maps the group to a provider, applies fallbacks, and meters the call. A provider change does not change client code.

Model groups

GroupContextOutputRPMNotes
deepseek-flashdeepseek/deepseek-flash1.0M384K600DeepSeek Flash, text and image input, thinking enabledAlias deepseek-chat
deepseek-v4-prodeepseek/deepseek-v4-pro1.0M384K600DeepSeek Pro, reasoning tuned, thinking enabledAlias deepseek-reasoner
minimax-h3minimax/MiniMax-H3n/an/a60MiniMax H3 video, 768P or 2K, 4–15 sAsynchronous /v1/videos task
minimax-h3-maxminimax/MiniMax-H3-Maxn/an/a60MiniMax H3-Max video, 480P or 768P, 5–15 sAsynchronous /v1/videos task
seedancevolcengine/dreamina-seedance-2-5-260628n/an/an/aBytePlus Seedance 2.5, 480p to 1080p, 4–30 sText or first-frame image input

deepseek-v4-pro falls back to deepseek-flash when the reasoning model is unavailable. DeepSeek thinking is on by default for both groups; see Chat completions for the reasoning controls. Video groups are asynchronous task APIs described in Video generation.

Check what your key can call

What can this key call?

GET /v1/models
deepseek-flashdeepseek-v4-prominimax-h3minimax-h3-maxseedance

Check your own key to confirm the groups it is scoped to.

A key only sees the groups it was issued for. If a group is missing, ask your administrator for a key that includes it.

Choosing a group

  • Use deepseek-flash for fast text and image input.
  • Use deepseek-v4-pro for multi-step reasoning, planning and code review.
  • Use minimax-h3 or minimax-h3-max for clips of 4–15 s.
  • Use seedance for clips up to 30 s, including image-to-video.