the model

gpt-5-mini

Served by OpenAI. 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: "openai/gpt-5-mini"
      prompt: "…"

The seats · 1

openai/gpt-5-mini272k context · 128k out
OpenAI · the provider room

The price

openai$0.25 in · $2 out · $0.025 cache
per million tokens · 400k window

{"id":"gpt-5-mini","served_by":[{"provider":"openai","provider_name":"OpenAI","alias":"gpt-5-mini","context_window_tokens":272000,"max_output_tokens":128000}],"pricing":[{"provider":"openai","input_per_million":0.25,"output_per_million":2,"cache_read_per_million":0.025,"cache_write_per_million":null,"context_window_tokens":400000,"max_output_tokens":128000,"open_weights":false}],"slug":"gpt-5-mini","energy":[]}