the model

gpt-4o-mini

Served by Azure OpenAI · 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@f3a31a6ee007 (v0.118.7) · digest-verified, re-derived at build, gated in CI

Point a task at it

tasks:
  ask:
    infer:
      model: "azure/cheap"
      prompt: "…"

The seats · 2

azure/cheap128k context · 16k out
Azure OpenAI · the provider room
openai/gpt-4o-mini128k context · 16k out
OpenAI · the provider room

The price

openai$0.15 in · $0.6 out · $0.075 cache
per million tokens · 128k window

{"id":"gpt-4o-mini","served_by":[{"provider":"azure","provider_name":"Azure OpenAI","alias":"cheap","context_window_tokens":128000,"max_output_tokens":16384},{"provider":"openai","provider_name":"OpenAI","alias":"gpt-4o-mini","context_window_tokens":128000,"max_output_tokens":16384}],"pricing":[{"provider":"openai","input_per_million":0.15,"output_per_million":0.6,"cache_read_per_million":0.075,"cache_write_per_million":null,"context_window_tokens":128000,"max_output_tokens":16384,"open_weights":false,"status":null}],"slug":"gpt-4o-mini","energy":[]}