fireworks/deepseek-v4-pro

Common Name: DeepSeek V4 Pro

Fireworks
SupportedTool InvocationSupportedReasoning
CompareTry in Chat

DeepSeek's higher-capability hybrid-thinking model in the V4 family.

Specifications

Context
1000K
Maximum Output
384K
Inputtext
Outputtext

Performance (7-day Average)

Collecting…
Collecting…
Collecting…

Pricing

Input$1.74/MTokens
Cached Input$0.145/MTokens
Output$3.48/MTokens

Availability Trend (24h)

Performance Metrics (24h)

Similar Models

$3.00/$15.00/M
ctx1.0Mmax131Kavailtps
InOutCap

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

$1.40/$4.40/M
ctx1.0Mmax131Kavailtps
InOutCap

Zhipu AI's flagship reasoning model for long-context engineering and agentic tasks.

$1.00/$4.05/M
ctx1.0Mmaxavailtps
InOutCap

Thinking Machines Lab's general-purpose multimodal model with controllable reasoning effort.

$2.10/$6.60/M
ctx1.0Mmax131Kavailtps
InOutCap

Zhipu AI's accelerated flagship reasoning model for long-context engineering and agentic tasks.