Limits and cost

API keys and MCP are included from the Studio plan. Below it, /api/mcp answers with HTTP 403 tier_required.

Generating costs credits; reading does not. list_brands, get_costs, and get_asset are free.

A flux_schnell image at square_hd costs 1 credit. Other models cost more — the exact amount comes back in cost_credits on every generate_image response, along with your new_balance, so you never have to guess.

Every generation also writes a cost line you can read back with get_costs, and each line is tied to the asset it paid for. Group by ref to see spend per asset:

{ "jsonrpc": "2.0", "id": 7, "method": "tools/call",
  "params": { "name": "get_costs",
              "arguments": { "gruppierung": "ref" } } }

If a generation fails after credits were taken, they are returned automatically.

Not available yet

Named plainly, because a gap you know about is easier to work around than one you discover:

• No speech or audio tools. There is no generate_tts. Ikrames' signing pipeline covers images and MP4 video; it does not yet cover audio files, so an audio tool would hand out material carrying no marking at all. Until that is solved, the tool does not exist.
• No video generation over MCP. create_composition builds a draft; rendering happens in the app.
• Enquiries are read-only. list_leads and get_lead read; nothing over MCP marks an enquiry as handled, replies to it, or deletes it. Deleting in particular stays in the app on purpose: it is the one action a person can ask you for under data-protection law, and it should not be one mistaken tool call away.
• No publishing over MCP. Nothing here posts to a platform. That is also what keeps the visible-labelling duty in one place, described at the top of this page.