deepseek-v4.1VIDEO

Roteo hosts DeepSeek V4.1 Flash 1017 at $0.23 input / $0.69 output per 1M tokens

Third-party platform Roteo lists DeepSeek V4.1 Flash 1017 with 1M context at $0.23 input, $0.69 output and $0.0069 cached input per 1M tokens, claiming 23%/43%/8% below Venice's public API.

Roteo

@roteo_aiArchived 10 days agoOriginally posted 2026.10.22

Roteo @roteo_aiOriginally posted 2026.10.22

Open original on X

DeepSeek V4.1 Flash 1017 is live on Roteo. Built for coding and agent work: • $0.23 input / $0.69 output / $0.0069 cached input per 1M tokens • 1M context • Available in chat and through `POST /v1/chat/completions` Compared with Venice’s public API pricing, that is: • 23% less on input • 43% less on output • 8% less on cached input We also cut DeepSeek V4 Flash 0731 to $0.069 / $0.207 / $0.01725 per 1M input / output / cached tokens. Same endpoint. Lower rates. https://roteo.ai

x.com/roteo_ai/status/2113024934004039749Archived 2026.10.22 11:59