DeepSeek launched V4 Pro and V4 Flash with thinking mode controls
DeepSeek added deepseek-v4-pro and deepseek-v4-flash to its API model catalog on April 24, 2026. Both models support thinking and non-thinking modes, 1M token context, 384K max output, JSON output, tool calls, and FIM in non-thinking mode. Official pricing lists V4 Flash at $0.14 cache-miss input / $0.028 cache-hit input / $0.28 output per 1M tokens, and V4 Pro at $1.74 cache-miss input / $0.145 cache-hit input / $3.48 output per 1M tokens.
Impact Assessment
Alternative models
Directional candidates based on stored listed rates and editorial scenario tags; validate quality and current terms before switching
Significant cost savings • Similar use cases
Slightly cheaper option • Similar use cases
Significant cost savings • Similar use cases
Good value alternative • Similar use cases
Significant cost savings
Sources
Official DeepSeek social announcement URL for the V4 Pro and V4 Flash launch.
DeepSeek lists deepseek-v4-flash and deepseek-v4-pro with 1M context, 384K max output, cache-hit input, cache-miss input, and output token pricing.
DeepSeek documents thinking mode toggles, reasoning effort controls, reasoning_content behavior, and tool-call handling for deepseek-v4-pro.
DeepSeek describes V4 Pro and V4 Flash as MoE models with 1M token context and configurable non-think, high, and max reasoning modes.
Comments
Does this change your best option?
Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.