DeepSeek
DeepSeek V4 Flash
DeepSeek V4 Flash — efficiency-optimized 284B-parameter MoE model with 13B active parameters, 1M context, and strong reasoning/coding performance.
deepseek-v4-flashCatalog preview. Paid requests for this model are not enabled yet.
Pricing
~90%USD. No uRouter markup. Live prices can change.
- Input
- $0.009091 / 1,000,000 tokens
- Output
- $0.018182 / 1,000,000 tokens
- Cache read
- $0.001818 / 1,000,000 tokens
- Cache write
- $0.009091 / 1,000,000 tokens
Model details
- Input
- text
- Output
- text
- Context window
- 1,000,000 tokens
- Maximum output
- 128,000 tokens
- Availability
- $3.9KUncapped capacity
- Updated
- 11/8/2026, 1:49:20 AM UTC
Capacity is reserved when your request is accepted.
Price history
Observed best prices · Last 24 hours · UTC
$0.009091/ 1,000,000 tokens
Capabilities
chatstreamingtoolsreasoning
Supported parameters
max_tokenstemperaturetop_pfrequency_penaltypresence_penaltyrepetition_penaltymin_plogit_biaslogprobstop_logprobsstoptoolstool_choiceresponse_formatseedstructured_outputsinclude_reasoningreasoningListed capabilities describe the model. uRouter execution support is verified separately.