fireworks/deepseek-v4-flash-0731

Common Name: DeepSeek V4 Flash 0731

Released on Jul 31 12:00 AMSupportedTool InvocationSupportedReasoning

DeepSeek's official V4 Flash release for cost-efficient reasoning and agentic workloads.

Context

1000K

Maximum Output

131.1K

Inputtext

Outputtext

Collecting…

Input$0.14/MTokens

Cached Input$0.028/MTokens

Output$0.28/MTokens

Performance Metrics (24h)

$0.14/$0.28/M

ctx1.0Mmax384Kavail—tps—

InOutCap

DeepSeek's cost-efficient hybrid-thinking model in the V4 family.

$0.15/$0.60/M

ctx131Kmax33Kavail—tps—

InOutCap

OpenAI's open-weight 120B model for production, agentic tasks, and high-reasoning use cases.

$0.07/$0.30/M

ctx131Kmax33Kavail—tps—

InOutCap

OpenAI's open-weight 20B model for lower-latency reasoning and specialized use cases.

$3.00/$15.00/M

ctx1.0Mmax131Kavail—tps—

InOutCap

Kimi's flagship multimodal reasoning model for long-context knowledge work and agentic workflows.