Build advanced reasoning agents with DeepSeek V4 Pro, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $1.74/1M input and $3.48/1M output tokens, native tool calling support, open weights architecture. Access DeepSeek V4 Pro via the Deep Infra API with up to 66K output tokens.
Tokens
Tokens
Tokens
DeepSeek V4 Pro by Deep Infra costs $1.74 per 1M input tokens and $3.48 per 1M output tokens. Cached reads cost $0.14 per 1M tokens.