DeepSeek V4.1 Flash in Claude Code: 13x cheaper via Anthropic-compatible endpoint
Three env vars point Claude Code at DeepSeek's Anthropic-compatible endpoint: $0.30/$1.20 per 1M tokens (half off weekends), beating Opus 5 on DeepSWE 77 vs 74 but losing Terminal Bench 42 vs 52.
DEEPSEEK JUST MADE CLAUDE CODE 13X CHEAPER. 26X ON WEEKENDS. same terminal. same workflow. you just swap opus for v4.1 flash 1017. the part the launch posts skip: deepseek runs an anthropic compatible endpoint. 3 lines: export ANTHROPIC_BASE_URL=https://api.deepseek.com/anthropic export ANTHROPIC_AUTH_TOKEN=your_deepseek_key export ANTHROPIC_MODEL="deepseek-flash[1m]" then run claude like always. the math per 1M tokens, input / output: > opus 5.5: $4 / $20 > deepseek flash: $0.30 / $1.20 > off peak and weekends: $0.15 / $0.60 why it's that cheap: every layer has 384 experts. only 6 wake up per token. the other 378 sleep. that's the whale in the video. the catch, straight from deepseek's own table: > beats opus 5 on DeepSWE, 77 vs 74 > loses to opus 5 on Terminal Bench, 42 vs 52 so keep opus for the hard calls. let the whale do the grind. your claude code bill is a setting, not a law.
This post quotes another post: x.com/juliangoldieseo/status/2111525607763034116