Which DeepSeek models does Terminus carry?

The catalog tracks DeepSeek's current chat and reasoning models; the /v1/models endpoint lists exactly what your account can use right now, each model by its address.

Does Terminus use DeepSeek's off-peak pricing?

Yes — the gateway's pricing model knows DeepSeek's discounted off-peak windows, and usage is metered per request either way.

Can a scheduled agent run on DeepSeek?

Yes. An agent's model is part of its configuration; a DeepSeek-powered agent runs its schedule like any other, with usage visible in Billing.

DeepSeek

Run DeepSeek on Terminus

DeepSeek's models made frontier-adjacent reasoning dramatically cheaper, and its API prices drop further in off-peak windows. That combination — strong models, aggressive pricing — is exactly what you want behind agents that run all day.

On Terminus, DeepSeek is a first-class provider: pick a DeepSeek model for the desktop chat, or give it to an agent that runs on a schedule. The gateway tracks DeepSeek's discounted off-peak windows, and every request is metered so you can see what each agent actually costs.

From the gateway

# The models your account can use
curl -s "$TERMINUS_API/v1/models?modality=chat" \
  -H "authorization: Bearer $TOKEN"

# Route a chat completion to one
curl -s "$TERMINUS_API/v1/terminus/chat/completions" \
  -H "content-type: application/json" \
  -H "authorization: Bearer $TOKEN" \
  -d '{
    "model": "@terminus/<address from the list above>",
    "messages": [{"role": "user", "content": "hello"}]
  }'

The gateway speaks the OpenAI chat-completions protocol.

One gateway, one bill

The Terminus gateway is OpenAI-compatible and meters every request. Switch providers by changing the model string — no new keys, SDKs, or invoices per vendor.

Agents, not just chat

Any model the gateway carries can power a Terminus agent: an autonomous worker with its own address, schedule or trigger, and scoped tool grants, running on Terminus infrastructure around the clock.

A desktop over your files

Conversations and agent runs happen in a workspace with a real file system — what the model produces lands in directories you browse, sync, and export, not in a chat log.

Questions

Which DeepSeek models does Terminus carry?: The catalog tracks DeepSeek's current chat and reasoning models; the /v1/models endpoint lists exactly what your account can use right now, each model by its address.
Does Terminus use DeepSeek's off-peak pricing?: Yes — the gateway's pricing model knows DeepSeek's discounted off-peak windows, and usage is metered per request either way.
Can a scheduled agent run on DeepSeek?: Yes. An agent's model is part of its configuration; a DeepSeek-powered agent runs its schedule like any other, with usage visible in Billing.

Terminus is in beta. Join the waitlist, or write to early-access@terminus.build to become a founding user.