DeepSeek / deepseek/deepseek-flash

DeepSeek V4.1 Flash - access through LLMTR

DeepSeek V4.1 Flash is the successor to the V4 Flash line, with a 1M-token context window and up to 384K output. Image input, tool calls and JSON output are supported; images are accepted both as base64 data URIs and as remote https links. Thinking mode is on by default. Repeated prefix input bills at the lower cache-hit rate. DeepSeek applies peak-hour pricing to this model: every token item costs double on weekdays (Monday-Friday, Beijing time) between 01:00-04:00 and 06:00-10:00 UTC. Weekends bill at the off-peak rate all day.

Technical specifications

Canonical IDdeepseek/deepseek-flash
ProviderDeepSeek
Context window1,000,000 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext, image

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENS$0.150000
CHAT_COMPLETIONSCACHE_READPER_1M_TOKENS$0.003000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$0.600000

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions   -H "Authorization: Bearer llmtr-your_key"   -H "Content-Type: application/json"   -d '{"model":"deepseek/deepseek-flash","messages":[{"role":"user","content":"Hello"}]}'

Related models