ZyyandCodex ed3e23887b fix(openai): calculate standalone image generation costs ...

Estimate gpt-image-2 generation and edit costs from the official standard
API rates for text input, image input, cached input and image output.
Emit calculated costs before image delivery while preserving raw responses.
Leave unsupported models, invalid usage and ambiguous mixed cache totals
unpriced. Mark calculated total-only amounts with an approximation sign.

Validation: 1,107 related backend tests, workspace rustfmt and strict
OpenAI/gateway-api Clippy. Replaying the previously verified live usage
of 18 text input and 229 image output tokens yields exactly USD 0.00696.

Co-authored-by: Codex <noreply@openai.com>

2026-09-08 02:41:14 +08:00

..

gateway-admin

fix(openai): recover exhausted quota windows independently

2026-09-07 00:59:48 +08:00

gateway-api

fix(openai): calculate standalone image generation costs

2026-09-08 02:41:14 +08:00

gateway-core

fix(openai): record image usage and endpoint request models

2026-09-08 02:23:00 +08:00

gateway-host

feat(logging): add opt-in request dumps

2026-09-04 19:15:28 +08:00

gateway-protocol

fix(openai): prioritize session affinity and isolate child failover

2026-09-07 03:16:45 +08:00

gateway-store

fix(openai): preserve WebSocket continuation and surface streaming errors

2026-09-07 12:24:28 +08:00

providers

fix(openai): calculate standalone image generation costs

2026-09-08 02:41:14 +08:00