DeepSeek V4.1 Flash 1017 Now Available on Telnyx Inference

Telnyx Inference has made DeepSeek V4.1 Flash 1017, the post-training checkpoint of DeepSeek's open-weight DeepSeek-V4.1-Flash model, available on Telnyx-owned GPUs under the model ID deepseek-ai/DeepSeek-V4.1-Flash-1017. The checkpoint targets agentic workloads such as coding agents, terminal automation and long-context document pipelines, and ships with open weights under the MIT license, a 1M-token context, a KV cache a quarter the size of the prior generation, and zero data retention on prompts and responses. Telnyx said running the model on its own in-region GPUs avoids cloud provider markup, with per-token rates listed on its Inference pricing page.

Contact sales https://telnyx.com/contact-us Log in https://portal.telnyx.com DeepSeek V4.1 Flash 1017, the post-training checkpoint of DeepSeek's open-weight DeepSeek-V4.1-Flash model, is now live on Telnyx Inference https://telnyx.com/products/inference , hosted on Telnyx-owned GPUs. model=deepseek-ai/DeepSeek-V4.1-Flash-1017 in the deepseek-ai/DeepSeek-V4.1-Flash . The gains in this checkpoint land exactly where agentic workloads live: coding agents, terminal automation, and long-context document pipelines. Open weights under the MIT license, a 1M-token context, a KV cache a quarter the size of the prior generation, and cached input rates that reward reuse all point the same way: more agent work per dollar. On Telnyx it runs on GPUs we own, in-region, with no cloud provider markup and zero data retention on prompts and responses. For current per-token rates, see Telnyx Inference pricing https://telnyx.com/pricing/inference-api . curl -X POST https://api.telnyx.com/v2/ai/openai/chat/completions \ -H "Authorization: Bearer $TELNYX API KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "deepseek-ai/DeepSeek-V4.1-Flash-1017", "messages": {"role": "user", "content": "Write a SQL query that computes month-over-month growth from an orders table."} }' Learn more in the model documentation https://developers.telnyx.com/docs/inference/models and in DeepSeek's 1017 model card https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017 .