DeepSeek V4 Flash Latest pricing
Compare stored list-price records, context window, and recent API changes. Source links are shown where available; verify current provider terms before deciding.
View model specs, context window, and lifecycle →Record updated 2026-10-05 · openrouter
Pricing per platform
Same model, different platforms. Cached input prices apply when supported.
| Platform | Region | Input / 1M | Output / 1M | Cached input | Context |
|---|---|---|---|---|---|
openrouter View source | global | $0.02 | $1.28 | $0.02 | 1,048,576 |
How much are you overpaying?
Enter your monthly spend on this model to see what the same workload could cost on cheaper alternatives.
Price history
Stored record history where available. Timestamps reflect database updates, not independent source verification.
AI Budget Calculator
Estimate monthly spend using your current token volume and cache ratio.
Save this listed-rate estimate for free
Create a free account to keep a watchlist and weekly digest. Results use stored listed rates and do not represent an actual bill.
Estimate boundary
Excludes taxes, tier discounts, extra fees, availability, latency, and quality; verify the source.
Percentage of input tokens that match cached context.
DeepSeekFrequently asked questions
- How much does DeepSeek V4 Flash Latest cost per 1M tokens?
- DeepSeek V4 Flash Latest is priced at $0.02 per 1M input tokens and $1.28 per 1M output tokens on openrouter. This is a stored listed price and may differ from current provider terms; verify the displayed source link before making a decision.
- Who provides DeepSeek V4 Flash Latest?
- DeepSeek V4 Flash Latest is provided by DeepSeek. ModelPriceLab also tracks third-party platforms that resell or proxy this model.
- What does the price record timestamp mean?
- It shows when ModelPriceLab's stored record changed. It is not an independent source-verification timestamp; confirm current pricing with the provider or platform.
- What is the context window for DeepSeek V4 Flash Latest?
- DeepSeek V4 Flash Latest supports up to 1,048,576 tokens per request, with a max output of 943,718 tokens.
Does this change your best option?
Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.