DeepSeek
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.
deepseek-v4-flash-0731Catalog preview. Paid requests for this model are not enabled yet.
Pricing
~99.3%USD. No uRouter markup. Live prices can change.
- Input
- $0.000901 / 1,000,000 tokens
- Output
- $0.001802 / 1,000,000 tokens
- Cache read
- $0.000097 / 1,000,000 tokens
- Cache write
- $0.000901 / 1,000,000 tokens
Model details
- Input
- text
- Output
- text
- Context window
- 1,048,576 tokens
- Maximum output
- 65,536 tokens
- Availability
- $2KUncapped capacity
- Updated
- 11/8/2026, 2:16:16 AM UTC
Capacity is reserved when your request is accepted.
Price history
Observed best prices · Last 24 hours · UTC
$0.000901/ 1,000,000 tokens
Capabilities
chatstreamingtoolsreasoningjson mode
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_pListed capabilities describe the model. uRouter execution support is verified separately.