> Source: https://vitna.ai/docs/api/v1/prices/tape
> Raw Markdown: https://vitna.ai/docs/api/v1/prices/tape.md
> Corpus index: https://vitna.ai/llms.txt
# Tape
Every current price in one class, flattened to one row per priced cell.
```
GET /api/v1/markets/{class}/tape
```
```bash
curl https://vitna.ai/api/v1/markets/model/tape
```
## Path parameters
| Parameter | Values |
|---|---|
| `class` | `model`, `tooling`, `retrieval`, `compute`, `extraction`, `speech`, `translation`, `image`, `video`, `music` |
Anything else answers `404 unknown_class`.
## Response
```json
{
"class": "model",
"tape": [
{
"sku": "gpt-5-pro",
"name": "gpt-5-pro",
"provider": "OpenAI",
"market": "First-party",
"featured": true,
"dimension": "input_per_mtok",
"dimensionLabel": "Input price",
"amountUsd": 15,
"unit": "USD per 1M tokens",
"since": "2026-08-07T00:00:00.000Z",
"confirmedAt": "2026-08-23T08:00:11.402Z",
"fetchedAt": "2026-08-23T08:00:11.402Z",
"stale": false,
"derived": false,
"sourceUrl": "https://openai.com/api/pricing/",
"evidenceSha256": "9f2c..."
}
],
"meta": { "generatedAt": "...", "source": "database", "count": 918, "units": ["USD per 1M tokens"] }
}
```
## Fields
| Field | Meaning |
|---|---|
| `sku` | Slug, for `/skus/{slug}/history` |
| `provider` | Who sells it |
| `dimension` | What it is metered by |
| `amountUsd` | The price, in `unit` |
| `since` | When this meter's price started, in this band: the `since` of its open period in `/skus/{slug}/history`, not the oldest date across the sku |
| `confirmedAt` | When it was last confirmed |
| `fetchedAt` | When the document was read |
| `stale` | Past its source's cadence |
| `derived` | Computed by Vitna rather than read from the page |
| `derivation` | How, when `derived` is true |
| `sourceUrl` | The page a human should read |
| `evidenceSha256` | The archived document |
| `observationId` | The leaf this figure is, for [its proof](../verification/proof.md) |
Model rows additionally carry `market` and `featured`. A derived row carries
`derivation` in every class. Compute rows carry the key on every row, as `null`
where the figure was read as printed; every other class leaves it out. A model
row served from the committed snapshot (`meta.source: "snapshot"`) holds no read
per figure, so a derived figure there says that it was derived and not how.
A row priced in a [context band](#context-bands) also carries `bandFromTokens`,
`bandToTokens` and `bandLabel`.
## The leaf behind a figure
`observationId` names the [observation](../../../concepts/observation.md) this
figure is, which is what turns a number on the board into something you can
prove is in the signed record:
```bash
curl "https://vitna.ai/api/v1/observations/<observationId>/proof"
```
It is the observation that **last confirmed** the price, which is the same read
`confirmedAt` and `evidenceSha256` describe. All three on one row therefore
refer to one read, so checking the document and checking the leaf are checks of
the same thing. `fetchedAt`, `stale`, `sourceUrl` and `derived` are that read's
too.
That holds per row, not per sku. One model's figures can come from different
reads: OpenAI's and Anthropic's flex and priority rates come from a second
source, the tiers page, read in a fetch of its own, and a table a page stops
printing keeps its periods open on the last read that saw it while the rest of
the row is confirmed every day. Each figure carries its own read, so a fresh
input price is never called stale because its batch rate is, and a batch rate
never cites a document it is not in.
> [!NOTE]
> Until 2026-11-16 the model tape copied one read onto every figure of a model:
> the oldest of its reads for `confirmedAt` and `fetchedAt`, any of them for
> `stale`, and the input price's document for `evidenceSha256`. On that day 100
> of 1,578 model figures carried a read that was not their own. Anything that
> describes a whole model in one line, a board row on the site or an entry in
> the [LiteLLM cost map](litellm-cost-map.md), still gives the oldest of its
> reads and is stale if any of its figures is, which is the right answer for
> one line and the wrong one for a figure.
One id per row of the tape, not per sku. A single fetch writes one observation
per cell it reads, so a model priced on four meters has four leaves even though
one document covers them all. That is why the tape carries the id and the board
does not.
> [!NOTE]
> `observationId` is `null` when an instance is serving a committed snapshot
> written before the ids were carried. Null rather than a borrowed id: inventing
> one from the row's other identifiers would produce a proof for a figure nobody
> asked about. The live record answers with the id.
Ids are strings. They are `bigserial`, and a JSON number stops being exact above
2^53.
## Context bands
Some providers price one model differently by how much context a request
carries. A price therefore applies in a band rather than universally, and a sku
priced that way publishes **one entry per band per meter**.
| Field | Meaning |
|---|---|
| `bandFromTokens` | Exclusive lower bound |
| `bandToTokens` | Upper bound, `null` when unbounded |
| `bandLabel` | What the provider calls it |
So a model split at 272,000 tokens publishes an input price for `(0, 272000]`
and another for `(272000, null]`, each naming its own band.
> [!NOTE]
> A sku priced once carries **no band keys at all**, rather than a band of
> `(0, null]`. That is deliberate: a consumer written before bands existed reads
> exactly the same rows for exactly the same skus, so the addition breaks
> nothing already parsing this tape.
A band is not a [dimension](../../../concepts/dimension.md) and not a
[sku](../../../concepts/sku.md). It is a property of the price, which is why it
travels on the row rather than multiplying either registry.
## One row per cell
A model publishing input, cached input and output prices produces three rows.
This is the flat shape on purpose: it is joinable and countable, where the board
shape the site renders is not.
> [!WARNING]
> A cell a provider does not publish is absent, not zero. Do not read a missing
> `batch_input_per_mtok` as free batching. See
> [dimension](../../../concepts/dimension.md).
## Empty classes answer 200 with an empty tape
A registered class with nothing priced returns `"tape": []`, which is the honest
answer and the same one the site gives. A `404` would say the class does not
exist, which is different and untrue.
An empty tape means one of two things, and [`/markets`](markets.md) says which:
a class Vitna does not read yet (`wired: false`), or a class it reads whose
sellers price nothing today (`wired: true`). `video` is the second kind since
Google shut down Veo 3.1 Preview on 2026-10-22, which took every figure the
class held.
## `meta.units`
The distinct units present, which is more than one for most classes.
The speech tape carries two units across three meters, since transcription is
billed by the audio-minute pre-recorded and again streaming, and synthesis by
the million characters. The retrieval and extraction tapes are single-unit. The
tooling tape is metered
four ways. The model tape carries two, because a model that emits images is
billed by the image rather than by the token.
An extraction row carries one field no other tape has, `page`, which says which
kind of page its figure is for. Two per-page rates are not comparable without
it: the cheapest is a page read for its characters and the dearest is a page
read against a schema.
> [!WARNING]
> Read `unit` off the row, never off the class. Within one model tape a row may
> be quoted per million tokens and the next per image, and treating the first
> unit you see as the tape's unit is how a per-image price gets compared against
> a per-token one.
## Caching
`public, max-age=60, stale-while-revalidate=3600`.