Kourier uses Google Analytics to understand aggregate website usage. Analytics is optional and is not used for targeted advertising. Read our Privacy Policy.

Kourier
sign up

The DeepSeek coding plan with no token caps.

DeepSeek's own API bills per token. Kourier runs DeepSeek V4 Flash on our own GPUs and sells it as a flat monthly plan for coding agents: Pro at $50/month, Max at $100/month.

Pro

Hands-on coding

$50/month
  • No request-volume or token-usage quotas
  • Up to 3 concurrent requests
  • DeepSeek V4 Flash access; new models added as available
  • OpenAI-compatible API endpoint
  • Community support via Discord
  • Usage dashboard and request logs
Recommended

Max

Long sessions, heavy use

$100/month
  • No request-volume or token-usage quotas
  • Up to 7 concurrent sessions
  • DeepSeek V4 Flash access; new models added as available
  • Priority routing and prefix caching
  • Priority email support
  • Advanced usage analytics and export

Flat pricing, not a token meter.

Agent sessions are long and bursty. Kourier limits how many requests run at once, never how many tokens you use.

Per-token APIToken-quota planKourier
How you payPer million input and output tokensMonthly fee for a token allowance$50 or $100 per month, flat
What limits youYour budgetToken windows, often every 5 hours and every weekConcurrent requests only: 3 on Pro, 7 on Max
Long agent sessionsEvery retry and tool call adds to the billCan stop mid-session when a window runs outNo 5-hour, weekly, or monthly cap
Monthly costVaries with usageFixed, plus top-ups when you run outFixed

Works with your coding agent.

One OpenAI-compatible and Anthropic-compatible endpoint. Set a base URL, an API key, and the model DSV4-Flash-0731.

DeepSeek coding plan questions.

DeepSeek's own API bills per token. Kourier is a separate service: we run DeepSeek V4 Flash on our own GPUs and sell it as a flat monthly plan built for coding agents.
DeepSeek V4 Flash, API model string DSV4-Flash-0731. The maximum context length is 278,528 tokens (272K), with up to 262,144 input tokens for requests that generate up to 16,384 tokens.
Concurrency. Pro accepts up to 3 simultaneous requests and Max accepts up to 7. When a request finishes, that slot is immediately available again; neither plan has a 5-hour, weekly, or monthly request or token cap.
Any tool that accepts a custom OpenAI-compatible or Anthropic-compatible endpoint, including Oh My Pi, Claude Code, Codex CLI, Cursor, Cline, OpenCode, Zed, Continue, and Aider. The docs have setup steps for each.
No. Sign up, choose Pro or Max in Billing, and create an API key. Omega is a separate, invite-only early-access membership.
No. Prompts and completions are processed in memory and discarded after the response returns. We retain only request metadata (timestamp, token counts, model id) needed for billing. We never train on your data.

Start coding on DeepSeek.

No invite needed. Sign up, pick Pro or Max, and create an API key.

Read the docs