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 ID | deepseek/deepseek-flash |
|---|---|
| Provider | DeepSeek |
| Context window | 1,000,000 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text, image |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| CHAT_COMPLETIONS | INPUT_TEXT | PER_1M_TOKENS | $0.150000 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.003000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_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
- DeepSeek V4 Pro deepseek/deepseek-v4-pro
- DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813
- Gemma 4 llmtr/gemma-4
- Qwen 3.6 35B-A3B llmtr/qwen3-6-35b
- Trendyol Asure 12B llmtr/trendyol-asure-12b
- Magibu 11B v8 llmtr/magibu-11b-v8
- Muse Glimmer 30B (Turkey) llmtr/muse-glimmer-30b-tr
- EmbeddingGemma 300M llmtr/embeddinggemma-300m