Models
What Eterial serves today, and which model to reach for.
Three models are available now, and a fourth is close. All of them are open-weight, and all of them speak the same API — switching is a change of one string.
| Model | Reach for it when |
|---|---|
minimax-m2.7 | Conversation: support agents, assistants, anything user-facing. |
kimi-k2.6 | Straightforward coding — small functions, edits, scripts, refactors. |
deepseek-v4-flash | Volume: simple work, a lot of it, where the bill is the constraint. |
glm-5.2 Coming soon | Serious coding. Frontier-class, and the strongest model here when it lands. |
Choosing between them
minimax-m2.7 is the default for anything that talks to a person. It holds a
conversation, follows a system prompt and calls tools, which is most of what an
AI support system does.
kimi-k2.6 is the one to point at code when the task is well defined —
implement this function, fix this bug, convert this file. For architectural work
or a large unfamiliar codebase, wait for GLM.
deepseek-v4-flash is the cheap one, and cheap by a wide margin rather than a
sliver — see Pricing for what the three currently cost. Reach for
it when the job is simple and there is a great deal of it: classification,
extraction, routing, tagging, summarising a queue. It reasons and calls tools, so
it can carry an agent loop; it is also the smallest of the three, so it rewards
work that does not need the extra capacity rather than work it will do badly and
cheaply.
glm-5.2 Coming soon is the heavyweight: frontier-class coding ability at
open-weight prices, which is the whole argument for running inference this way.
One difference the ids do not show: kimi-k2.6 is the only one of the three
that takes images and PDFs. The other two advertise reasoning and tools and
nothing more, so a request carrying an image_url or a file content part routes
to Kimi or to nothing at all. GET /v1/models is where to check that before
sending one.
The live list
GET /v1/models is authoritative — it returns exactly what you can send to right
now, along with the capabilities each model advertises. See
Models endpoint.
Model ids are short and stable. What changes underneath is which backend serves one, which is why the same id keeps working when the network is busy — see Routing.