DeepSeek Flash 1017
Default · native vision · 1×deepseek-flashUse the new native multimodal model for everyday coding, screenshots, charts, and mixed text-image Agent work. Send image URLs or Base64 input through the supported API protocol.
Configuration guide
DeepSeek Coding Plan setup
Connect your plan to DSH Desktop on macOS or Windows, or follow the CLI instructions for Codex, Claude Code, DSH, Pi, OpenCode, OpenClaw, and Hermes.
Need DeepSeek Coding Plan access?
These instructions use this site’s managed DeepSeek gateway and its delivered key. Official DeepSeek API credentials and Multi-Model Coding Plan credentials use separate configurations. Compare the current DeepSeek cards for price, shared 5-hour and 7-day token quotas, service period and stock. Choose pay once or explicitly enable renewal on the card; the renewal schedule and price are shown before checkout. Zero stock blocks purchase.
View DeepSeek plans and current stockPreview configuration · These examples start with deepseek-flash. Replace YOUR-TOKEN-PLAN-KEY with your delivered key, oropen Dashboard for your personal configuration.
SetupChoose a tool
Connect your coding tool
Choose your tool. We’ll guide you through the rest.
Already configured?
Model reference & compatibility
1 · How to choose
Use deepseek-flash by default for both text and images
The new Flash 1017 route has a 1M context window, supports native multimodal input, and produces up to 384K output tokens. All routes share one token pool and route to deepseek-flash. Every route, including the legacy Pro Model ID, uses one plan token per raw input/output token reported by the provider (1×). Send images by URL or Base64; this plan does not include Files API uploads.
DeepSeek V4 Flash
Compatibility · 1×deepseek-v4-flashKeep this existing text route for compatibility with configurations that have not yet moved to deepseek-flash.
DeepSeek V4 Pro
Compatibility · 1×deepseek-v4-proKeep this legacy Model ID for existing configurations. It routes to deepseek-flash and uses the same 1× plan-token accounting.
DeepSeek V4 Flash Vision Exp
Compatibility · image input · 1×deepseek-v4-flash-vision-expKeep this experimental Vision route for compatibility with existing image configurations. New configurations should use the native multimodal deepseek-flash model.
2 · Switch models
Keep the Key and Base URL; change only model
Start with deepseek-flash. For a new image task, keep the same model and add a URL or Base64 image to the request. The older deepseek-v4-flash, deepseek-v4-pro, and deepseek-v4-flash-vision-exp IDs remain compatibility routes, so existing configurations continue to work while users move to the new ID.
// New default
model: "deepseek-flash"// Native image input
model: "deepseek-flash"// Existing configs
model: "deepseek-v4-flash"Plan details & purchase
Available while stock lasts
One access Key for Flash 1017 and the existing V4 routes
Pay once for 31 days of API access. New configurations should use deepseek-flash for both text and image input. Existing configurations continue to work with the same encrypted Key and Base URL while you migrate. Ready-to-copy Agent configurations appear in Dashboard.
Delivery
One access key for the new and compatibility routes
5-hour limit
50M Flash-equivalent tokens
Long-window limit
400M tokens / 7 days
Access term
31 days · one-time