> ## Documentation Index
> Fetch the complete documentation index at: https://docs.percify.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Percify changelog: what shipped and when

> Dated releases for Percify: the Composer API, server-driven batches, new MCP tools, new models, and the credit price of each. Newest first.

What shipped, newest first, with the date it reached production. Dates come from the release itself rather than from when it was written up here.

<Update label="2026-09-27" description="Composer rounds for agents">
  **Ten MCP tools for Composer.** An agent can now run a brand's daily rounds the way the app deals them: `todays_round`, `reveal_round`, `shuffle_round`, `approve_play`, `undo_approve`, `pass_play`, plus the Library shelf with `save_to_library`, `list_library`, `remove_from_library` and `download_library`. Round actions are logged as an agent's, not a person's.

  The MCP server now exposes **55 tools**. See [the Percify MCP server](/mcp-server).
</Update>

<Update label="2026-09-23" description="Batches, personas and spend alerts">
  **Server-driven batches.** `POST /v1/batches` runs one model over up to 50 prompts, and because the server drives it you can start a batch and hang up. `budgetCredits` is a hard ceiling checked **before each submission**, and polling a batch that lost its driver resumes the prompts it had not reached. See [the batches API](/api-reference/batches).

  **Avatar personas hold a character**, and any model can use one. Persona images can be screened as a batch before any of them are written.

  A **choice of lip-sync model**, and **spend alerts** on API keys.
</Update>

<Update label="2026-09-19" description="Composer deals rounds instead of a wall">
  **Plays are now dealt in rounds of three, face down.** Reveal turns the three over, Approve locks a card, and Shuffle rerolls only the cards still open. Any single approved card can be scheduled on its own.

  This replaced the sixteen-card wall. Measured over the ten days before the change, eleven brand owners reached the wall, eight hovered, and three ever kept a card: sixteen at once reads as a catalogue to browse rather than a decision to make. See [Composer](/brand-os/composer).
</Update>

<Update label="2026-09-17" description="What the API needs to be true">
  A **webhook signing secret** you can read from the API, a **complete OpenAPI document**, and full tool definitions for MCP clients. See [Webhooks](/guides/webhooks) and [errors and limits](/api-reference/errors-and-limits).
</Update>

<Update label="2026-09-16" description="Brand OS for agents">
  **Brand OS over MCP**: read a brand from its website, write its words into a proven short video format, render it, and publish to connected social accounts, with an autopilot that learns from each post. Agents can also wait on any job server-side and list past generations.
</Update>

<Update label="2026-09-15" description="MCP gets its own origin">
  The MCP server moved to **mcp.percify.io**, served by the same API. Connections set up with the earlier URL keep working.
</Update>

<Update label="2026-09-13" description="Composer for agents and scripts">
  The **Composer API** at `api.percify.io/v3/composer/api`, on the same `pk_live` key and the same Scale-and-above plan gate as the rest of the API. See [the Composer API](/api-reference/composer).
</Update>

<Update label="2026-09-09" description="GPT Image 2.5">
  **GPT Image 2.5 Flare** and **Sunburst** at 2 credits a run, with **Flare Edit** and **Sunburst Edit** at 4. See [every model and its price](/models).
</Update>

<Update label="2026-08-29" description="Realtime video and Gemini TTS">
  **Realtime Video** from text or from an image at 60 credits, and **Gemini TTS** at 4 credits. See [Realtime](/create/realtime-video).
</Update>

<Update label="2026-08-16" description="Seedance 2.5 and Wan 2.7">
  **Seedance 2.5** text-to-video and image-to-video at 120 credits, the image-to-video **Turbo** at 150, **Wan 2.7 Video Edit** at 140, and **P-Video Replace** at 26.
</Update>

## How to follow changes

* Model prices and clip lengths change as models are added. [`GET /v1/models`](/api-reference/models) always returns the current catalogue, and the Playground shows each model's price before you run it.
* Every docs page carries the date it was last updated, under its title.
* Breaking API changes are avoided rather than versioned away: routes are added, and existing ones keep answering. Where a URL had to move, a redirect keeps the old one working.

## Related

<CardGroup cols={2}>
  <Card title="Every model and its price" icon="sliders" href="/models">
    The current catalogue, grouped by what it makes.
  </Card>

  <Card title="The Percify API" icon="code" href="/api-reference/introduction">
    Base URL, keys and plans.
  </Card>

  <Card title="The MCP server" icon="plug" href="/mcp-server">
    All 55 tools, grouped by job.
  </Card>

  <Card title="Pricing" icon="coins" href="/percify/payments">
    Plans, credit packs and billing.
  </Card>
</CardGroup>