DeepSeek V4.1 Flash-1017 now available as a serverless model on Together AI
Together AI added a serverless DeepSeek model with a 1,000,000 context length and priced input and output per 1M tokens.
Models:deepseek-ai/DeepSeek-V4.1-Flash-1017
What changed
Together AI added a new serverless model, deepseek-ai/DeepSeek-V4.1-Flash-1017. It supports a 1,000,000 context length, FP8 quantization, function calling, and structured outputs. Pricing is $0.30 input, $1.20 output, and $0.006 cached input per 1M tokens.
Source
deepseek-ai/DeepSeek-V4.1-Flash-1017: 1,000,000 context length, FP8 quantization, function calling, and structured outputs. Pricing: $0.30 input / $1.20 output / $0.006 cached input (per 1M tokens).
Original announcement: Together AI changelog
Source: Together AI changelog (2026-10-18)