Cursor: model API costs and setup

Cursor supports provider API keys for chat. A custom endpoint must match the API format Cursor expects; this is not a promise that every Cursor feature uses your gateway.

Custom endpoint requires validation. Documentation checked 2026-11-02.

Protocol and setup checks

Steps below are per vendor documentation. Read the official Cursor documentation.

1. Open Cursor Settings > Models and locate the OpenAI API key controls.
2. For versions exposing Override OpenAI Base URL, set https://api.meldport.com/v1 and use a dedicated Meldport key. If that control is absent, use the vendor documentation for your version rather than changing unrelated settings.
3. Select an exact published model ID. Validate chat, streaming, and a tool round trip before using Agent mode. Custom API keys do not cover Tab completion.

See also the official custom-endpoint guidance. Endpoint compatibility must be checked for the selected model and feature.

Calculate cost before comparing savings

For DeepSeek V4.1 Flash, verified on 2026-11-06, the listed uncached rates are $0.045 input and $0.18 output per million tokens. An illustrative 100,000 input plus 10,000 output tokens costs $0.006300, before minimum charges, caching, retries, and any other fees. This does not establish that the model works with Cursor.

Repeat the calculation using the same token counts and model at another provider. Savings exist only when that comparable total is higher. A lower rate does not establish equal quality, latency, or fewer retries.

Compare current token prices, review Meldport's API contract, and plan a task budget.

Confirm protocol compatibility before buying credit for this client. Compare the other agent connection options.