DeepSeek
deepseek-v4-flash-vision-exp API Pricing
DeepSeek charges $0.22 per 1M input tokens and $0.66 per 1M output tokens across a 1M context window. Verified 2026-08-26 against the official DeepSeek pricing page.
Vision model; images are converted into tokens based on dimensions and billed as input tokens; cache-miss off-peak rate shown; cache-hit input $0.007 per MTok; peak hours 01:00-04:00 and 06:00-10:00 UTC double pricing
Input / 1M tokens
$0.22
Output / 1M tokens
$0.66
Context window
1M
What it costs to run
| Workload | Tokens | Cost |
|---|---|---|
| Single short call | 2K in, 500 out | $0.00077 |
| Typical chat turn | 10K in, 1K out | $0.00286 |
| Long document pass | 100K in, 2K out | $0.023 |
| 1,000 chat turns | 10M in, 1M out | $2.86 |
Price history
No price move recorded for deepseek-v4-flash-vision-exp since tracking began on 2026-08-26. Every future change lands here with the before and after.
How it compares
Ranked on the blended cost of a typical chat turn (10K in, 1K out), not the input rate alone.
| OpenAI | gpt-5-nano | $0.00090 per turn |
| gemini-2.0-flash-lite | $0.00105 per turn | |
| gemini-2.5-flash-lite | $0.00140 per turn | |
| OpenAI | gpt-4.1-nano | $0.00140 per turn |
| OpenAI | gpt-4o-mini | $0.00210 per turn |
| DeepSeek | deepseek-v4-flash-vision-exp | $0.00286 per turn |
| OpenAI | gpt-5.6-luna | $0.00320 per turn |
| OpenAI | gpt-5.4-nano | $0.00325 per turn |
| gemini-3.1-flash-lite | $0.00400 per turn | |
| OpenAI | babbage-002 | $0.00440 per turn |
| OpenAI | gpt-5-mini | $0.00450 per turn |
Free JSON API
Every tracked model, including this one, is available as JSON. Free to use with attribution and a link back.
curl https://techfastforward.com/api/data/llm-pricingMaintained by Jordan Hale, TechFastForward. Prices are read daily from the official provider page and recorded only when they move. See every tracked model on the LLM API Pricing Tracker.