DeepSeek V4.1 Flash API access
Your selected API rates, access details, and next steps.
Activate on Discord
Open Palepale Discord ↗ and send: I would like DeepSeek V4.1 Flash API access. Include the app you want to connect. Confirm allowance, model access, payment terms, and limits before activation.
Your selected API model
DeepSeek V4.1 Flash: $0.045 input, $0.0009 cached input, and $0.18 output per 1 million tokens.
Save at least 85% across these rates compared with the reference prices recorded on 2026-10-08. Status: Planned. These are draft rates. This model is not available for paid use yet.
API pricing by usage
API tokens are priced by the input, cached input, and output your requests use. Compare API prices to choose a model. This is separate from the monthly and 30-day plans, which have an agreed token allowance.
Activate API access
Open Palepale Discord and tell the team you want DeepSeek V4.1 Flash. They confirm the model, usage rates, payment arrangements, and account limits, then supply your API address and device credential. This website does not take payment or fund an account automatically.
Connect your client
Configure your client with the supplied API address and device credential. The gateway exposes GET /v1/models for the model catalog and POST /v1/chat/completions for streaming chat requests. Select an available model ID from your catalog. Copy a connection example or set up OpenCode.
Keep track of usage
Input and output usage are recorded against your account. A shared token budget, concurrency limits, and request-rate limits apply across its devices. Understand billing.
Manage device access
Keep credentials private. Ask the team to revoke a lost device or replace an expiring credential. Read the account-access guide.