DeepSeek V4 Pro 0813(openrouter.ai)

1004 points by explosion-s 2 months ago | 431 comments

OpenRouter model page for DeepSeek V4 Pro 0813, a mixture-of-experts LLM GA release, listing pricing ($0.435/$0.87 per 1M tokens), 1M context, and providers.

DeepSeek: DeepSeek v4.1 Flash 1017(openrouter.ai)

499 points by theanonymousone 9 days ago | 264 comments

OpenRouter model page for DeepSeek V4.1 Flash 1017, a sparse mixture-of-experts LLM snapshot with pricing, 1M context, and API access details.

Show HN: WebGPU + TypeScript Slime Mold(github.com)

58 points by SuboptimalEng 1 year ago | 11 comments

Five Qwen3.8-27B models match Fable 5 Using GVS5H Harness(github.com)

160 points by rzk 1 day ago | 56 comments

GitHub repo with code and paper for GVS5H, a training-free self-orchestration harness letting Qwen3.8-27B instances match Claude Fable 5 on hard LiveCodeBench problems.

DeepSeek makes the V4 Pro price discount permanent(api-docs.deepseek.com)

574 points by Tiberium 5 months ago | 514 comments

DeepSeek API documentation page listing models and per-million-token pricing for deepseek-v4-flash and deepseek-v4-pro, including the permanent V4 Pro price cut.

DeepSeek V4 Pro at 75% off until 31 May(api-docs.deepseek.com)

53 points by nateb2022 5 months ago | 23 comments