SPRO adds DeepSeek V4.1 Flash 1017: specs and pricing
Third-party gateway SPRO lists V4.1-Flash-1017 with 1M context, 393K output tokens, four reasoning levels, and $0.15/$0.60 per million input/output tokens.
DeepSeek V4.1 Flash on SPRO now has @deepseek_ai's latest weights: V4.1-Flash-1017. Same model, updated checkpoint. DeepSeek says it scores higher on benchmarks, finishes tasks faster and writes shorter answers than the previous weights. > 1M context, up to 393K output tokens > Text and image input, with reasoning on or off (none, low, high or max) > Tool calling and JSON mode Pricing: > Input: $0.15 / 1M tokens > Output: $0.60 / 1M tokens > Cache read: $0.003 / 1M tokens Model ID: deepseek-v4.1-flash-1017 Guardrails, caching, spend limits and request logs on every call. https://spro.hridaai.com/explore/models/deepseek/deepseek-v4.1-flash-1017 #DeepSeek #LLM #AIGateway