Use DeepSeek V4.1 Flash in OpenCode

Steps

1. Edit opencode.json. Add a provider block using the config below.
2. Add the key. Run /connect in OpenCode and add the key for the provider, or set it in your environment.
3. Select the model. Pick the deepseek-v4.1-flash-1017 model in the model picker.

Config

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "fikra": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Fikra API",
      "options": { "baseURL": "https://api.fikraapi.co.ke/v1" },
      "models": { "deepseek-v4.1-flash-1017": { "name": "DeepSeek V4.1 Flash 1017" } }
    }
  }
}

Test it

Ask OpenCode to explain the repo structure.

What it costs

Default model: deepseek-v4.1-flash-1017. Prices come from the live catalog.

Input	$0.05 / 1M
Cached input	$0.0075 / 1M
Output	$0.15 / 1M

Repeated prompt prefixes are billed at the cached rate. Cached input can never cost more than fresh input.

Get your key

Free model

While the window is open, model deepseek-v4-1-flash-economy-free is free. Check live availability.

Troubleshooting

Common errors.

401 Unauthorized

The key is missing, revoked, or has a leading space. Paste it again from the dashboard and use the fk_live_ value.

404 Not Found

The base URL usually has an extra /chat/completions. Use exactly https://api.fikraapi.co.ke/v1.

Model not found

The model ID is case sensitive. Copy it from /models or the snippet on the dashboard.

429 Too Many Requests

You hit the account rate limit. Free accounts allow 30 requests per minute and 300 per day. Any top-up raises the limits.