Cline

Cline is a VS Code extension that runs an autonomous coding agent. It supports custom OpenAI-compatible providers, so you can route its requests through MirAPI with your own key.

What you need

Element	Value
API provider	`OpenAI Compatible`
Base URL	`https://api.mirapi.ai/v1`
API key	Your MirAPI key (`sk-...`)
Model ID	`deepseek-chat`
Context window	The model’s catalog value

Create the key in the Platform (https://platform.mirapi.ai) and check the model’s context length on the Models & pricing page.

Configure

Open Cline → Settings → API Provider.
Select OpenAI Compatible.
Fill in:

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

Set the context window from the catalog value for deepseek-chat. Cline uses this number to plan truncation, so an overstated value makes it overfill the request.
Save. If Cline offers to send a small test request, allow it.

Verify with a message

Create a Cline task and send:

Reply with exactly: connected to MirAPI

The assistant’s reply should contain connected to MirAPI. If it does not, see Errors and troubleshooting below.

You can also confirm the model is listed before starting:

curl https://api.mirapi.ai/v1/models -H "Authorization: Bearer sk-..."

Look for deepseek-chat among the returned id values.

Protocol variants

MirAPI serves three protocols under one key. The OpenAI Compatible provider above is the recommended path; if you use Cline’s Anthropic or Gemini provider instead, point it at the matching surface:

Protocol	Base URL	Auth
OpenAI-compatible	`https://api.mirapi.ai/v1`	`Authorization: Bearer sk-...`
Anthropic	`https://api.mirapi.ai`	`x-api-key` or `Authorization: Bearer`
Gemini	`https://api.mirapi.ai` or `https://api.mirapi.ai/v1beta`	`x-goog-api-key` or `?key=`

Whichever protocol you pick, copy the model ID verbatim from GET /v1/models. Requests use the exact id, not the display name.

Errors and troubleshooting

Symptom	Cause and fix
`401`	Key missing, invalid, or unknown. Check that it is copied in full and matches the Platform.
`403`	Key is valid but rejected: the model is not on the key’s whitelist, the key hit a quota, the caller’s IP is not on the allowlist, or the balance is empty. Top up or adjust the key’s limits, then retry.
`413`	Payload too large. Trim the context or the attached files.
`429`	Rate limited. Retry with jittered exponential backoff (1s → 2s → 4s, capping around 30s). MirAPI sends no `Retry-After` header and does not retry for you.
`500`	Gateway or upstream failure. Idempotent requests are safe to retry.

Every error message ends with a request ID; include it in a support ticket. OpenAI-style errors use the envelope {"error": {"message", "type", "param", "code"}}, where type is new_api_error (gateway side) or upstream_error (upstream failure).

Billing

Cline usage is charged to your MirAPI prepaid balance. There is no subscription or monthly fee, and the balance never expires. Chat turns are billed per token in three tiers (input, output, and cache read), priced in USD per 1M tokens, and reasoning tokens count as output. When the balance runs out, MirAPI returns 403; after you top up, the same key works again immediately.