The Orchestrator › Models › DeepSeek
DeepSeek: DeepSeek V4 Flash Vision Exp
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...
Specifications
| Provider | DeepSeek |
| Model ID | deepseek/deepseek-v4-flash-vision-exp |
| Context window | 1.0M tokens (1,048,576) |
| Modalities | text + image → text |
| Tokenizer | DeepSeek |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway |
| Released | 2026-08-21 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | On by default |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | deepseek/deepseek-v4-flash-vision-exp | $0.44 | $1.32 | 1.0M |
| standard | TrustedRouter | deepseek/deepseek-v4-flash-vision-exp | $0.464 | $1.39 | 1.0M |
| standard | Vercel AI Gateway | deepseek/deepseek-v4-flash-vision-exp | $0.216 | $0.647 | 1.0M |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.216 | $0.647 | 1.0M |
| 2026-11-14 | $0.464 | $1.39 | 1.0M |
| 2026-11-14 | $0.44 | $1.32 | 1.0M |
Capabilities
Vision (image input)Agentic tool useStructured outputsReasoning mode1M+ context windowControllable reasoningNo content storage (attested)No training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p