the model

deepseek-chat

Served by DeepSeek. Point a task at it and the audit prices the ceiling before a token is spent.

Vendored from the released binary · supernovae-st/nika@5d61b7e13f1f (v0.107.0) · digest-verified, re-derived at build, gated in CI

Point a task at it

tasks:
  ask:
    infer:
      model: "deepseek/chat"
      prompt: "…"

The seats · 1

deepseek/chat64k context · 8k out
DeepSeek · the provider room

The price

deepseek$0.14 in · $0.28 out · $0.0028 cache · open weights
per million tokens · 1m window

{"id":"deepseek-chat","served_by":[{"provider":"deepseek","provider_name":"DeepSeek","alias":"chat","context_window_tokens":64000,"max_output_tokens":8192}],"pricing":[{"provider":"deepseek","input_per_million":0.14,"output_per_million":0.28,"cache_read_per_million":0.0028,"cache_write_per_million":null,"context_window_tokens":1000000,"max_output_tokens":384000,"open_weights":true}],"slug":"deepseek-chat","energy":[]}