DeepSeek V4 Flash Free returns FreeUsageLimitError on OpenCode Zen

Description

The deepseek-v4-flash-free model on OpenCode Zen consistently returns a FreeUsageLimitError when making requests through the OpenAI-compatible API.

Authentication works correctly, but the request is rejected by the provider with:

FreeUsageLimitError: Error from provider (Console): Rate limit exceeded. Please try again later.

I'm trying to use the free DeepSeek V4 Flash model through OpenCode Zen as a coding agent.

Plugins

none

OpenCode version

1.18.18

Steps to reproduce

1. Create/use an OpenCode Zen API key.
2. Send a request to:
   https://opencode.ai/zen/v1/chat/completions
3. Use the model:
   deepseek-v4-flash-free
4. Send a normal chat completion request.

Example:

curl -X POST "https://opencode.ai/zen/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4-flash-free","messages":[{"role":"user","content":"Say hello in one sentence."}]}'

### Screenshot and/or share link

_No response_

### Operating System

windows 11

### Terminal

windows terminal