fireworks:deepseek/deepseek-flash

Common Name: DeepSeek V4.1 Flash

-50%On SaleReleased on Sep 10 12:00 AMSupportedTool InvocationSupportedReasoning

DeepSeek V4.1 Flash with native multimodal understanding and efficient reasoning for agentic workloads.

Context

1000K

Maximum Output

384K

Inputtext, image

Outputtext

Collecting…

Availability Trend (24h)

Input$0.11/MTokens

Cached Input$0.0035/MTokens

Output$0.33/MTokens

$0.075/$0.25/M-50%

ctx1.0Mmax131Kavail—tps—

InOutCap

Z.ai's multimodal GLM-5.3 model for fast reasoning and visual coding workloads.

$0.15/$0.60/M-50%

ctx512Kmax512Kavail—tps—

InOutCap

MiniMax's reasoning model for long-context coding and agentic tasks.

$0.075/$0.30/M-50%

ctx131Kmax33Kavail—tps—

InOutCap

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

$1.50/$7.50/M-50%

ctx1.0Mmax131Kavail—tps—

InOutCap

Fireworks' specialized model built on Kimi K3 with shorter reasoning traces for efficient agentic workloads.