Processing or generating 1,000,000 words (approximately 1,333,000 tokens) with DeepSeek V4 Flash Vision Exp ranges from $0.0187 (cached input) to $1.76 (full generation).
Quick answer
For 1,000,000 words, DeepSeek V4 Flash Vision Exp processes approximately 1,333,000 tokens. That costs $0.5865 as uncached input, $0.0187 with the modeled cache discount, or $1.76 when generated as output.
Method & trust
The estimate converts the selected English word count with the model tokenizer family, then applies the published input/output price per million tokens. Real prompts vary with code, formatting, language, and system instructions.
You send 1,000,000 words as prompt context, documentation, or background knowledge.
DeepSeek V4 Flash Vision Exp drafts a complete 1,000,000 words article, chapter, or code module.
800,000 words input prompt + 200,000 words output reply.
| Model | Provider | Input Cost (1,000,000 words) | Cached Input Cost | Output Cost (1,000,000 words) | Context Limit |
|---|---|---|---|---|---|
| DeepSeek V4 Flash Vision Exp (Current) | deepseek | $0.5865 | $0.0187 | $1.76 | 1,050,000 |
| GPT-5.6 Luna | openai | $0.256 | $0.0256 | $1.536 | 1,050,000 |
| GPT-5.4 mini | openai | $0.96 | $0.096 | $5.76 | 256,000 |
| GPT-5.4 nano | openai | $0.256 | $0.0256 | $1.60 | 128,000 |
| GPT-4o mini | openai | $0.192 | $0.096 | $0.768 | 128,000 |
| Claude Haiku 4.5 | anthropic | $1.32 | $0.132 | $6.60 | 1,000,000 |
For DeepSeek V4 Flash Vision Exp (deepseek_v4 tokenizer), 1,000,000 words is approximately 1,333,000 tokens (an average ratio of 1.33 tokens per word in English). Code, technical vocabulary, and non-English scripts will have higher token densities.
Sending 1,000,000 words as input costs $0.5865 (or $0.0187 with prompt caching). Generating 1,000,000 words as output costs $1.76. Output tokens are more expensive because autoregressive token generation requires significantly more computation per token.
Yes! If your input text is part of a repeated context, prompt caching saves 50% to 90% (costing $0.0187). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.2933 for input, $0.8798 for output).
At an average human reading speed of 250 words per minute, 1,000,000 words takes approximately 4000 minutes to read. In contrast, DeepSeek V4 Flash Vision Exp can process or generate this text in seconds.