DeepSeek / deepseek/deepseek-v4-flash-vision-exp
DeepSeek V4 Flash Vision Exp - access through LLMTR
Experimental DeepSeek V4 Flash Vision model with a 1M-token context window and up to 384K maximum output. Supports tool calling and prompt caching. Image inputs are accepted both as base64 data URLs and as remote https links, and are tokenized by image dimensions into the input token count.
Technical specifications
| Canonical ID | deepseek/deepseek-v4-flash-vision-exp |
|---|---|
| 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 | $0.220000 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.007000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $0.660000 |
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-v4-flash-vision-exp","messages":[{"role":"user","content":"Hello"}]}'Related models
- DeepSeek V4 Flash deepseek/deepseek-v4-flash
- DeepSeek V4 Pro deepseek/deepseek-v4-pro
- DeepSeek Chat deepseek/deepseek-chat
- DeepSeek R1 deepseek/deepseek-reasoner
- 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