gpt-5.2

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-5.2"
      prompt: "…"

The seats · 1

openai/gpt-5.2272k context · 128k out
OpenAI · the provider room

The price

openai$1.75 in · $14 out · $0.175 cache
per million tokens · 400k window

{"id":"gpt-5.2","served_by":[{"provider":"openai","provider_name":"OpenAI","alias":"gpt-5.2","context_window_tokens":272000,"max_output_tokens":128000}],"pricing":[{"provider":"openai","input_per_million":1.75,"output_per_million":14,"cache_read_per_million":0.175,"cache_write_per_million":null,"context_window_tokens":400000,"max_output_tokens":128000,"open_weights":false}],"slug":"gpt-5-2","energy":[]}