Get it for macOS

Compare what every AI model costs per million tokens, across Anthropic, OpenAI, Fireworks AI, Ollama Cloud and OpenRouter, in one table. A Relative column ranks each model against the cheapest one on screen, weighted by an input/output blend you choose. Each row also gives the context window, the longest reply, and whether the model can reason, call tools or return structured output. Sort by any column, search by name, hide a provider with its legend dot, and open any model's own page from its row. Prices come from the public models.dev catalog and OpenRouter's model list and are kept for twelve hours; no account or key is needed, but the machine running the bb server must reach both sites.


Overview

View source

Choosing which model to point an agent at usually means opening five vendor pricing pages and doing arithmetic. The Model pricing page puts every model from the providers you follow in one table, with the numbers that decide the choice side by side.

What you get

  • A Model pricing page in the sidebar listing each model's price per million tokens in and out, its context window, its longest reply, and whether it can reason, call tools, return structured output and take a temperature.
  • A Relative column that ranks every model against the cheapest one on screen, so the cheapest reads 1.0× and the rest say how many times more they cost. How much of that blend is input is your choice: 80/20 suits an agent reading a repository, 25/75 a chat drafting prose.
  • Sorting by any column, search by name, and coloured provider dots that hide a provider's models for a moment without fetching anything.
  • Every row opens that model's own page on the provider's site.
  • A card per model in a narrow window, and palette commands for the page and its settings.

Where the prices come from

Anthropic, OpenAI and Fireworks AI publish no pricing API, so those three and Ollama Cloud are read from the community catalog at https://models.dev, and OpenRouter from its own public list. The bb server fetches them, keeps them for twelve hours, and refreshes on request; an unchanged catalog costs one round trip. If a source cannot be reached, its last prices stay on screen with a note saying how old they are.

Settings

  • One switch per provider: a provider switched off is neither fetched nor shown.
  • The input/output blend used by the Relative column.
  • Whether to list only models that can call tools (on by default). Models whose provider does not say are always shown.

What it needs

  • No account, key or login: only public price lists are read.
  • Network access from the machine running the bb server to models.dev and openrouter.ai.

Limits

  • Prices are as current as their source; the vendor's own pricing page remains the authority.
  • Only per-token prices are shown: no cached-input, batch, image or audio pricing.
  • With OpenRouter on, a model sold both directly and through the gateway appears twice, once per price.

More from Gustavo Ambrozio

ChatGPT Realtime ConnectionRun Voice Mode's voice chats on your ChatGPT subscription instead of a separately billed OpenAI API key. It hands Voice Mode the ChatGPT sign-in that the Codex CLI already keeps on the machine running the bb server, reads it again for every chat, and never renews or rewrites it. Only the plugins you allow, Voice Mode to begin with, receive the token; the bb app, the command line and agents in threads never do. This is an undocumented use of the subscription that OpenAI could stop accepting at any time, nobody has checked whether OpenAI's terms allow it, and voice chats count against your ChatGPT plan. Requires bb 0.46 or later, Voice Mode 0.1.9 or later, and the Codex CLI signed in with Sign in with ChatGPT on a plan that includes Codex.26Diff ReviewComment on a thread's changes line by line, then send the comments to its agent, which fixes the code and answers each one. A Review tab beside the thread shows the diff of its uncommitted, staged or unstaged changes, its branch, one commit or a range, and each comment follows its code as the code moves. The same tab reviews a GitHub pull request: answer its threads, mark files viewed in step with GitHub, and submit your comments as one review, posted as the GitHub CLI's signed-in account. An AI review leaves comments of its own, @reviewer answers a question inside a comment thread, and Fix in a new thread hands the comments to another agent; these runs start as threads under the one being reviewed, in the permission mode set in the settings (bb's Approve for me by default, or Accept edits), and in full permission mode with a provider that lacks that mode, such as opencode. Follows the review loop of the open-source diffity, credited in the plugin's third-party notices. Needs bb 0.48 or later with bb's Git plugin on, and the signed-in GitHub CLI (gh) for pull request review only; it is built on experimental bb plugin APIs that may change between bb releases.NewDreamKeep every Claude Code project's memory consolidated overnight, as Claude Code's own auto-dream would if it ran in bb. Each dream is a hidden thread that can read anything but write only that project's memory files, and a project's first dream is a dry run you review as a diff, then apply or discard. The memory is backed up before every change, and the Dream page shows each project's memory, why it is or is not due, the dry runs waiting for you and the history of dreams. The schedule is off until you turn it on. Each dream is one model run on your Claude Code account; requires bb 0.49 or later, macOS or Linux, and Claude Code signed in on the machine dreams run on.NewFirstMate CrewHand one agent your to-do list and it runs a crew of worker threads, each in its own git worktree, until the work lands. The first mate is a pinned thread in bb's own chat that writes each worker's instructions, supervises it, and brings back branches, pull requests, findings and only the decisions that are yours. A FirstMate tab shows the crew as a board of Queued, Working, Blocked, Parked, Done, Failed and Idle, with Steer, Interrupt, Relaunch and End on every card. A built-in watch tells the first mate within about five minutes when a pull request is merged, reviewed or changes check status. Requires bb 0.47 or later, git, and the logged-in gh CLI for the pull request watch; a capable model such as Claude Sonnet is recommended for the first mate.14

More in Token Usage & Limits 44

Understand or control token, context-window, and provider-quota use.

View all