Soniox
OtherGuides

Usage summary

Daily cost and activity for a project, broken down per model and summed across all models.

Overview

The usage summary is a project's cost and activity rolled up by UTC day, per model and across all models. It is the same data behind the project's Usage page in the Soniox Console.

Use it to:

  • Report spend - total cost for a billing period, or per model.
  • Chart trends - plot daily cost or request volume over weeks and months.
  • Attribute cost - see which models account for most of the spend.

For a per-request record instead, see usage logs.

Summaries are available via the GET /v1/usage/summary API.

Choosing a window

start_time is inclusive and end_time is exclusive, both ISO 8601 UTC. A UTC day is included when the window covers any part of it, so an end_time at exactly midnight leaves out its own day: 2026-04-01T00:00:00Z to 2026-04-03T00:00:00Z returns April 1 and April 2. A window may cover at most 366 UTC days.

What gets returned

The response has a total entry covering all models, and a models array with one entry per model that recorded usage. The total entry is the one with a model of null, and a project with no usage gets an empty models array.

Every entry carries a days array of UTC dates, and the per-day arrays align to it by index. Every day in the window appears, so days with no usage are zeros.

GET /v1/usage/summary?start_time=2026-04-01T00:00:00Z&end_time=2026-04-03T00:00:00Z
Authorization: Bearer <SONIOX_API_KEY>
{
  "total": {
    "model": null,
    "days": ["2026-04-01", "2026-04-02"],
    "total_cost_usd": "0.2567250000",
    "total_input_cost_usd": "0.0415500000",
    "total_output_cost_usd": "0.2151750000",
    "total_duration_cost_usd": "0.0000000000",
    "cost_usd": ["0.1711500000", "0.0855750000"],
    "input_cost_usd": ["0.0277000000", "0.0138500000"],
    "output_cost_usd": ["0.1434500000", "0.0717250000"],
    "duration_cost_usd": ["0.0000000000", "0.0000000000"],
    "total_num_requests": 285,
    "total_input_text_tokens": 4800,
    "total_input_audio_tokens": 15000,
    "total_input_audio_duration_ms": 1800000,
    "total_output_text_tokens": 10800,
    "total_output_audio_tokens": 8250,
    "total_output_audio_duration_ms": 990000,
    "total_duration_ms": 0,
    "num_requests": [190, 95],
    "input_text_tokens": [3200, 1600],
    "input_audio_tokens": [10000, 5000],
    "input_audio_duration_ms": [1200000, 600000],
    "output_text_tokens": [7200, 3600],
    "output_audio_tokens": [5500, 2750],
    "output_audio_duration_ms": [660000, 330000],
    "duration_ms": [0, 0]
  },
  "models": [
    {
      "model": "stt-async-v5",
      "days": ["2026-04-01", "2026-04-02"],
      "total_cost_usd": "0.0613500000",
      "total_input_cost_usd": "0.0235500000",
      "total_output_cost_usd": "0.0378000000",
      "total_duration_cost_usd": "0.0000000000",
      "cost_usd": ["0.0409000000", "0.0204500000"],
      "input_cost_usd": ["0.0157000000", "0.0078500000"],
      "output_cost_usd": ["0.0252000000", "0.0126000000"],
      "duration_cost_usd": ["0.0000000000", "0.0000000000"],
      "total_num_requests": 60,
      "total_input_text_tokens": 300,
      "total_input_audio_tokens": 15000,
      "total_input_audio_duration_ms": 1800000,
      "total_output_text_tokens": 10800,
      "total_output_audio_tokens": 0,
      "total_output_audio_duration_ms": 0,
      "total_duration_ms": 0,
      "num_requests": [40, 20],
      "input_text_tokens": [200, 100],
      "input_audio_tokens": [10000, 5000],
      "input_audio_duration_ms": [1200000, 600000],
      "output_text_tokens": [7200, 3600],
      "output_audio_tokens": [0, 0],
      "output_audio_duration_ms": [0, 0],
      "duration_ms": [0, 0]
    },
    {
      "model": "tts-rt-v2",
      "days": ["2026-04-01", "2026-04-02"],
      "total_cost_usd": "0.1953750000",
      "total_input_cost_usd": "0.0180000000",
      "total_output_cost_usd": "0.1773750000",
      "total_duration_cost_usd": "0.0000000000",
      "cost_usd": ["0.1302500000", "0.0651250000"],
      "input_cost_usd": ["0.0120000000", "0.0060000000"],
      "output_cost_usd": ["0.1182500000", "0.0591250000"],
      "duration_cost_usd": ["0.0000000000", "0.0000000000"],
      "total_num_requests": 225,
      "total_input_text_tokens": 4500,
      "total_input_audio_tokens": 0,
      "total_input_audio_duration_ms": 0,
      "total_output_text_tokens": 0,
      "total_output_audio_tokens": 8250,
      "total_output_audio_duration_ms": 990000,
      "total_duration_ms": 0,
      "num_requests": [150, 75],
      "input_text_tokens": [3000, 1500],
      "input_audio_tokens": [0, 0],
      "input_audio_duration_ms": [0, 0],
      "output_text_tokens": [0, 0],
      "output_audio_tokens": [5500, 2750],
      "output_audio_duration_ms": [660000, 330000],
      "duration_ms": [0, 0]
    }
  ]
}

See GET /v1/usage/summary for the full schema and field types.

Only successfully started requests are counted. Requests rejected before they start - for example, due to an invalid API key, insufficient funds, or a validation error - are not included.

Usage logs

Per-request record of every transcription or speech generation processed by Soniox - model, audio duration, tokens, cost, and an optional client_reference_id.

Concurrency limits

Live counts of active real-time requests alongside the configured concurrency limits for the project and the organization that owns it, plus historical per-period concurrency.