Billing & limits

What a run costs

A run consumes API credits from the account whose key created it, priced as the sum of what the run actually uses:

• Reasoning — every chat completion Mangrove makes, including the run's final check, is billed per input and output token. Mangrove reasons with glm-5.3.
• Image analysis — a vision step is a completion of its own, billed at the rate for mistral-small-3.2-24b-instruct-2506.
• Task grading — before it starts, a run can be graded on how hard the task is and how much work it is: one Metis decision for both.
• Getting a question-only run ready — a run with no documentUrl or audioUrl first works out what kind of task it is, and one graded as more than a single step also writes a plan before it starts. Each is a completion billed at the rate for mistral-small-3.2-24b-instruct-2506.
• Transcription — the audio_transcribe step is billed per second of audio at the speech-to-text rates.
• Tool calls — web_search, web_crawl, document_parse, save_data, and save_file carry no charge of their own.

All model rates are on the pricing page.

What this means in practice:

• Cost varies per run. Mangrove decides how many steps a task needs, so two runs with the same question can cost different amounts, and a run's cost is unknown when it is accepted — the X-Credits-Remaining header on the 202 response reflects the balance before the run, not the run's cost.
• A spent balance rejects new runs, not reads. POST /v1/agents/runs returns 402 Payment Required when the balance is zero or below. Polling and streaming existing runs keep working, so an outcome already paid for stays readable.
• Interrupted work is not refunded. A run that fails partway has consumed credits for the steps it completed. The events it emitted before failing stay readable.
• A follow-up pays for whatever it repeats. Runs are not resumable and carry no history (One run, one exchange), so a second run that redoes the first one's searches, transcription, or document parsing is billed for that work again. Two ways to keep it down: supply the inputs Mangrove needs up front, and quote the finding you want built on rather than leaving Mangrove to rediscover it. Answering an awaiting_input run is this same case — the new run repeats every step that led up to the question.
• Organisation members. Accounts covered by an organisation subscription are metered for the organisation instead of drawing on personal API credits.

Limits

A run that reaches the 20-round cap stops calling tools and answers with what it has by then. It reports succeeded like any other run, and nothing in the stream marks the difference — a task that needed more work than that comes back with a thinner answer rather than an error. Supplying the inputs up front, or splitting the task into narrower questions, keeps a run well inside the cap.