DeepSeek V4.1 Flash
DeepSeek · text, image → text
DeepSeek's latest model, DeepSeek V4.1 Flash, is in a mid-release internal beta and open for trial. It uses a new model architecture with native multimodal support, greater capability, faster speed, and lower cost. Because the model is still in internal testing, it will be rate-limited and is available only for testing—not recommended for production use.
Input$0.142 /M
Output$0.284 /M
Cache read$0.0284 /M