Home › VastLLM Catalog › DeepSeek V4 Flash Vision Exp
DeepSeek V4 Flash Vision Exp
by DeepSeek · Language Models
Context 1049K tokensVisionReasoning / thinkingFunction calling
by DeepSeek · Language Models
DeepSeek-V4-Flash-Vision-Exp is an experimental multimodal model for visual understanding. Its text-only capabilities, including agent tasks, reasoning and world knowledge, match the official DeepSeek-V4-Flash, while stronger visual understanding brings its multimodal agent capabilities close to Opus-4.8.
$0.1943 in · $0.777 out / 1M
| Usage | Rate (USD) | Unit |
|---|---|---|
| Input tokens | $0.19 | per 1M tokens |
| Cached input (cache hit) | $0 | per 1M tokens |
| Output tokens | $0.78 | per 1M tokens |
TuneRouter live platform pricing · currency: USD · pre-deduction settled by actual usage
OpenAI-compatible · base URL https://api.tunerouter.com/v1/
curl https://api.tunerouter.com/v1/chat/completions \
-H "Authorization: Bearer $TUNEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "deepseek-v4-flash-vision-exp", "messages": [{"role": "user", "content": "Hello!"}]}'Model ID: deepseek-v4-flash-vision-exp · works with OpenAI SDKs — just point base_url at api.tunerouter.com