LongCat provides a hosted API for LongCat-2.0, a reasoning model built for coding and agentic workloads. Apus provides the official LongCat plugin for LongCat's OpenAI-compatible endpoint.

Install plugin

Install the official package:

apus plugins install @openclaw/longcat-provider

Installation applies to a running Gateway automatically; otherwise it takes effect on the next startup. See Apply changes and inspect.

Getting started

Sign in to the [LongCat API Platform](https://longcat.chat/platform/) and
create a key on the [API Keys](https://longcat.chat/platform/api_keys)
page.

```bash
apus onboard --auth-choice longcat-api-key
```

```bash
apus models list --provider longcat
```

Onboarding adds the hosted catalog and selects longcat/LongCat-2.0 when no primary model is already configured.

Non-interactive setup

apus onboard --non-interactive --accept-risk --skip-health \
  --mode local \
  --auth-choice longcat-api-key \
  --longcat-api-key "$LONGCAT_API_KEY"

Reasoning behavior

LongCat exposes binary thinking control. Apus maps enabled thinking levels to thinking: { type: "enabled" } and /think off to thinking: { type: "disabled" }. Apus removes reasoning_effort from LongCat requests.

LongCat returns reasoning in reasoning_content. Apus preserves that field when replaying assistant tool-call turns so multi-turn agent sessions retain the provider's expected message shape.

Pricing

The built-in catalog uses LongCat's pay-as-you-go list prices in USD per million tokens: $0.75 uncached input, $0.015 cached input, and $2.95 output. LongCat may offer temporary discounts; the pricing page and your billing records are authoritative.

Self-hosted LongCat-2.0

The longcat provider targets LongCat's hosted API. For the open weights on Hugging Face, serve the model through an OpenAI-compatible runtime and use Apus's existing vLLM or SGLang provider instead.

Keep the runtime's exact model identifier in the self-hosted provider catalog; do not route a local deployment through longcat/LongCat-2.0.

Troubleshooting

Daemon-managed Gateway processes do not inherit every interactive shell
variable. Put `LONGCAT_API_KEY` in `~/.apus/.env`, configure it through
onboarding, or use an approved secret reference.

`402` means the account has insufficient token quota. `429` means the API
key hit a rate limit. Check [LongCat usage](https://longcat.chat/platform/usage)
and retry rate-limited requests after the provider's backoff window.

Run `apus plugins list` and confirm the `longcat` plugin is
enabled, then run `apus models list --provider longcat`.

Related

Provider configuration, model refs, and failover behavior.

Hosted API endpoints, authentication, limits, and examples.

Architecture, deployment guidance, and model details.

Store provider credentials without embedding plaintext in config.