Which Kimi models does Terminus carry?

The catalog tracks Moonshot AI's current Kimi models; call /v1/models to see exactly what your account can use, each model by its address.

What is Kimi good at inside Terminus?

Long-context and tool-heavy agent work: large documents in your file space, multi-step research, agents that make many connector calls in one run.

Can I mix Kimi with other models?

Yes — model choice is per conversation and per agent, so one workspace can run Kimi, Claude, GPT, and DeepSeek side by side under one bill.

Moonshot AI

Run Kimi on Terminus

Kimi, from Moonshot AI, earned its reputation on long context and strong agentic performance — models that hold a large working set and follow multi-step tool use without losing the plot.

On Terminus that profile fits naturally: point an agent with a big job — long documents, sprawling research, many tool calls — at a Kimi model, or use it in the desktop chat, all through the same gateway and the same per-request metering as every other provider.

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 Kimi models does Terminus carry?: The catalog tracks Moonshot AI's current Kimi models; call /v1/models to see exactly what your account can use, each model by its address.
What is Kimi good at inside Terminus?: Long-context and tool-heavy agent work: large documents in your file space, multi-step research, agents that make many connector calls in one run.
Can I mix Kimi with other models?: Yes — model choice is per conversation and per agent, so one workspace can run Kimi, Claude, GPT, and DeepSeek side by side under one bill.

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