
A Claude Code and Codex plugin that converts image inputs, screenshots, and image-tool outputs into structured text descriptions using gpt-5.4-mini via the Codex CLI, enabling text-only models to reason about images.
Prices and medians update for the tier you select. Caution: thin market — treat statistics as indicative.
No providers in this market have a Pro-tier plan — try another tier.
Ranked by how closely each one matches Deepseek Vision Bridge's job. Prices show each provider's Pro state; entry prices are labelled as such. Unpriced products still belong to the market.
Thin market — few comparable priced products; treat statistics as indicative.