Brief failures: let it recover on its own
AI models are occasionally busy or rate-limited. When a single reply fails, the app retries automatically, and you can also tap the failed message to resend. Waiting a few minutes usually brings it back.
Persistent failures: troubleshoot in order
1. Confirm your network is fine (see the "connection lost" article). 2. Check the status page for anomalies. 3. Confirm your account's AI capabilities are available (some advanced ones need a membership or wallet balance). 4. Self-hosters: check that the model API key in .env is valid and its quota isn't exhausted.
Self-hosting: switch models to isolate the cause
Self-hosting supports multiple models (BYOK cloud models or local Ollama / vLLM). If one model keeps failing, switch to another in the configuration first — that tells you whether it's a single provider's problem or the deployment itself.
Related questions
Is Enclave free? How does pricing work?
Enclave is free to start: open it in your browser, no credit card needed. Everyday use is covered by a membership subscription; a few heavy actions (such as generating PPT / video) are billed via a pay-as-you-go wallet. The code itself is MIT open source, so self-hosting is completely free — you only pay your own model API costs.Which large language models does Enclave support?
Enclave's model layer is fully swappable: OpenAI, Anthropic, Google, DeepSeek, and local Ollama / vLLM can all be configured. Different characters can even use different models, freely allocated by scenario and cost.