Model
DeepSeek Flash
DeepSeek · Active · Text
At a glance
A quick read on fit, access, and published limits.
ActiveDeepSeek · Direct API
DeepSeek Flash from DeepSeek's official model directory.
Model ID
deepseek-flash- Pricing
- $0.15 input · $0.003 cached input · $0.60 output / 1M tokens
- Modalities
- Text
- Context window
- 1,000,000 tokens
- Max output
- 384,000 tokens
- Released
- Not published
- Last checked
- 2026-09-22
Pricing
Rates are grouped by usage type and available tier.
Per 1M tokens
Input
$0.15
Cached input
$0.003
Output
$0.60
Rate tiers
Peak
Input
$0.30
Cached input
$0.006
Output
$1.20
Pricing notes
- Off-peak rates are shown by default; peak rates are listed in the rate tiers.
Batch pricing
Not published
Capabilities and limits
What the API supports and where limits apply.
- Provider
- DeepSeek
- Model type
- Text tokens
- Family
- deepseek
- Access
- Direct API
- Modalities
- Text
- Context window
- 1,000,000 tokens
- Max output
- 384,000 tokens
- Released
- Not published
- Deprecation date
- Not announced
Sources
Official pages and the date this information was checked.
- Last checked
- 2026-09-22
- Source links
- 2
Next step
Estimate costs with this model.
Recommended for
- Customer support bot cost calculatorEstimate support automation volume and see how quickly a high-usage inbox can move margin.
- Meeting summarizer cost calculatorEstimate summary and recap workflows built on long meeting transcripts.
- Batch classification cost calculatorEstimate large asynchronous labeling jobs where throughput matters more than latency.
Recent updates
Added to the model directory.
View source