Coding Plans

Starter includes 1 concurrent request; Pro includes up to 3 concurrent requests. Both include DeepSeek V4.1 Flash and new models as they become available.

DeepSeek V4.1 Flash is available today. We are exploring smaller models to behave as a small fast context gatherer.

No. Starter and Pro are flat monthly plans governed by simultaneous concurrency, not token credits or rolling request quotas. There are no per-token charges, seat fees, or surprise usage bills.

Concurrency. Starter accepts 1 simultaneous request and Pro accepts up to 3. When a request finishes, that slot is immediately available again; neither plan has a 5-hour, weekly, or monthly request or token cap.

We do not use your API prompts or outputs to train or fine-tune models. Prompt and response content is excluded from inference gateway request logs. Requests are processed in memory with temporary caching. We retain operational metadata for usage, billing, security, and service reliability. Read our Data use & retention policy.

Performance varies with request shape, context length, and fleet load. We publish measured median time to first token and output speed when sufficient production traffic is available.

Kourier offers flat monthly concurrency plans instead of per-token metering, so you never pay extra for retries, tool calls, or long agent sessions. See our DeepSeek coding plan comparison for a side-by-side breakdown.