Roo Code

Roo Code shares Cline’s provider architecture, so the setup is nearly identical to Cline’s: one OpenAI-compatible provider, one key, and one model. MirAPI’s OpenAI-compatible endpoint accepts Roo Code’s standard requests without any changes.

What you need

Element	Value
Base URL	`https://api.mirapi.ai/v1`
API key	`MIRAPI_API_KEY`
Model	`deepseek-chat`

Create the key in the Platform at https://platform.mirapi.ai. Roo Code sends it as Authorization: Bearer, which MirAPI accepts (the scheme is case-insensitive).

Configure

Open Roo Code → Settings → API Provider.
Choose OpenAI Compatible.
Fill in the three fields:

Base URL: https://api.mirapi.ai/v1
API Key: $MIRAPI_API_KEY
Model ID: deepseek-chat

Set the context window to the model’s context_length from the catalog (see Models & pricing).
Save. If the provider settings offer a connection test, run it once.

Keep /v1 in the base URL: Roo Code appends /chat/completions itself, so the full path becomes https://api.mirapi.ai/v1/chat/completions.

Verify with a message

Start a task and type:

Reply with exactly: connected to MirAPI

The assistant reply should contain connected to MirAPI. If it does not, check the status codes table below.

Model, context window, and profiles

Send the exact id that GET /v1/models returns (here, deepseek-chat). Model names pass through verbatim.
The vendor/ prefix in the catalog (for example deepseek/deepseek-chat) is only for browsing and filtering in the Platform; never put it in the Model ID field.
Set the context window from the model’s context_length in the catalog. An overstated value makes Roo Code assume the model accepts more context than it does, which can truncate a task midway.
Roo Code profiles (Architect, Code, Ask) each remember their own model, so switch every profile you use to deepseek-chat.
MirAPI sends each request to the primary channel you chose and fails over to your backup channel if the primary errors. If both are down, the request fails with a 5xx rather than silently substituting another model.

Errors and troubleshooting

Status codes

Status	Meaning	What to do
401	Key missing, invalid, or unknown	Check the key in Roo Code settings
403	Key valid but rejected: empty balance, model whitelist, quota, or IP	Fix the cause; top up if the balance is empty
413	Request too large	Reduce the context or payload
429	Rate limited (no `Retry-After` header)	Retry with jittered exponential backoff (1s → 2s → 4s, capped ~30s)
5xx	Upstream or channel failure	Retry idempotent requests

Every error message ends with a request ID. Include it in any support ticket. See Errors for the full reference.

Billing

MirAPI bills against a prepaid USD balance that never expires. There is no subscription and no minimum spend.
Chat requests are billed per token (input, output, cache read), priced per 1M tokens; reasoning tokens are billed as output.
When the balance runs out, requests return 403. Top up at https://platform.mirapi.ai and the same key works again immediately.
Reconcile usage in the Platform billing log or via GET /api/log/token. The usage object in a non-streaming response reports token counts only, never a dollar amount.

Tool-specific pitfalls

Enter the model ID verbatim: deepseek-chat must match GET /v1/models exactly.
A 403 with a valid key usually means the model is not whitelisted for the key or the balance is empty. Top up and retry; the same key works again immediately.
Keep /v1 in the base URL; Roo Code appends /chat/completions.
After changing the key or model, re-save each profile you use, because Architect, Code, and Ask store settings separately.