Costs less than most peers
Market median price: $2.625 blended / 1M, cheaper than 6 of 6 priced peers.
DeepSeek · Chat
DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.
Evidence and sources
Market median price: $2.625 blended / 1M, cheaper than 6 of 6 priced peers.
The weights are public. 4 of the 10 peers that say either way have open weights.
Also known as: accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast, deepseek v4.1 flash 1017 ultrafast, deepseek-v4-1-flash-1017-ultrafast, deepseek/deepseek-v4.1-flash-1017-ultrafast, fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works