# Transcribe audio

Turns speech into text. Send the audio as JSON with base64 in `input_audio` (OpenRouter's
form) or as a `multipart/form-data` upload with a `file` part (OpenAI's form, as OpenAI's
SDKs send it). Same response as OpenRouter: `text` and `usage` with the cost in EUR, plus
`language`, `duration` and `segments` with `response_format: verbose_json`.

The gateway picks a European provider of the model (respecting `provider` preferences) and,
if it fails, tries the next one. Whether the provider receives the audio as an upload or
as base64 JSON is part of its configuration, not of the request. The body is validated
completely before any provider is called; every problem is listed in
`error.metadata.issues`. Audio by URL (`input_audio.url`, `source_url`), speaker labels
(`diarize`) and `keyterms` are not supported by this gateway's providers and fail with 400.

Administrative PII requirements are checked for each actual route, including fallbacks
and retries. This endpoint cannot redact its input: a matching requirement returns
`invalid_parameter` with a `not_available` issue at `$.model` before provider I/O.

`POST https://api.tokenlane.de/v1/audio/transcriptions`

## Authorizations

[
  [
    {
      "name": "Authorization",
      "description": "API key as bearer token in the `Authorization` header: `Authorization: Bearer sk-tl-v1-…`. Existing `sk-eu-` keys remain valid. Missing, unknown or expired keys get 401 `authentication`.",
      "type": "http bearer",
      "location": "",
      "scopes": []
    }
  ]
]

## curl

```curl
curl --request POST \
  --url 'https://api.tokenlane.de/v1/audio/transcriptions' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
  "input_audio": {
    "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YQAAAAA=",
    "format": "wav"
  },
  "language": "de",
  "model": "mistralai/voxtral-mini-transcribe-3-0"
}'
```

## node

```node
const response = await fetch("https://api.tokenlane.de/v1/audio/transcriptions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.TOKENLANE_API_KEY,
    "Content-Type": "application/json",
  },
  body: `{
  "input_audio": {
    "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YQAAAAA=",
    "format": "wav"
  },
  "language": "de",
  "model": "mistralai/voxtral-mini-transcribe-3-0"
}`,
});
console.log(await response.text());
```

## python

```python
import os
import urllib.request

body = (r'''{
  "input_audio": {
    "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YQAAAAA=",
    "format": "wav"
  },
  "language": "de",
  "model": "mistralai/voxtral-mini-transcribe-3-0"
}''').encode("utf-8")

request = urllib.request.Request(
    "https://api.tokenlane.de/v1/audio/transcriptions",
    method="POST",
    headers={
        "Authorization": "Bearer " + os.environ["TOKENLANE_API_KEY"],
        "Content-Type": "application/json",
    },
    data=body,
)

with urllib.request.urlopen(request) as response:
    print(response.read().decode("utf-8"))
```

## vercel

```vercel
// This operation uses HTTP directly.
const response = await fetch("https://api.tokenlane.de/v1/audio/transcriptions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.TOKENLANE_API_KEY,
    "Content-Type": "application/json",
  },
  body: `{
  "input_audio": {
    "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YQAAAAA=",
    "format": "wav"
  },
  "language": "de",
  "model": "mistralai/voxtral-mini-transcribe-3-0"
}`,
});
console.log(await response.text());
```

## header: x-session-id (optional)

Groups the generation into a session, immediately available from GET /v1/sessions/{id}. Use 1 to 256 ASCII letters, digits, '-', '_', '.' or ':'; an ID cannot consist only of dots. A non-null session_id in JSON or multipart takes precedence. Never sent to the provider.

### s0: string | null

{}

## header: Idempotency-Key (optional)

Explicit opt-in to encrypted response replay across gateway nodes. One 1..=255 printable ASCII value per logical operation, scoped to this API key ID. Reuse the same method, path and normalized body. Completed responses are retained for at most 10 minutes; replay is free and creates no generation. Conflicting content or unavailable replay returns 409. A successful replay carries Idempotent-Replayed: true and preserves the original request and generation IDs. See /docs/guides/idempotency.

## Body: application/json

```json
{
  "input_audio": {
    "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YQAAAAA=",
    "format": "wav"
  },
  "language": "de",
  "model": "mistralai/voxtral-mini-transcribe-3-0"
}
```

### s4: object

Audio to transcribe as JSON, in OpenRouter's format: the audio is base64 in `input_audio`.

The body is validated before any provider is called; every problem is listed in
`error.metadata.issues`. The audio may have at most 50 MiB decoded, within the 50 MiB body
(as base64 about 37 MiB of audio fit; upload larger files as `multipart/form-data`).
Unknown parameters are ignored and named in `x-ignored-params`.

{}

```json
{
  "input_audio": {
    "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YQAAAAA=",
    "format": "wav"
  },
  "language": "de",
  "model": "openai/whisper-large-v3"
}
```

- diarize (optional): s240

### s240: boolean

Speaker labels. Not supported by the providers of this gateway: `true` fails with 400
`invalid_parameter`.

{}

```json
false
```

- input_audio (required): s241

### s241: anyOf

The audio as `{"data": <base64>, "format": <format>}`. Formats: aac, flac, m4a, mp3, mp4, mpeg, mpga, oga, ogg, opus, wav, webm. `{"url": …}` (the provider downloads the audio) is not supported by the providers of this gateway and fails with 400 `invalid_parameter`.

{}

anyOf: s201

### s201: object

Audio as base64.

{"additionalProperties":"false"}

```json
{
  "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YQAAAAA=",
  "format": "wav"
}
```

- data (required): s982

### s982: string

The audio file, base64-encoded (standard or URL-safe alphabet, no data URL prefix).

{}

- format (required): s983

### s983: string

Format of the audio: aac, flac, m4a, mp3, mp4, mpeg, mpga, oga, ogg, opus, wav or webm
(any case).

{"pattern":"\"^[a-zA-Z0-9][a-zA-Z0-9+._-]{0,15}$\""}

```json
"wav"
```

anyOf: s202

### s202: object

Audio the provider downloads. Not supported by the providers of this gateway.

{"additionalProperties":"false"}

```json
{
  "format": "mp3",
  "url": "https://example.com/meeting.mp3"
}
```

- format (optional): s984

### s984: string

Format of the audio at the URL.

{"pattern":"\"^[a-zA-Z0-9][a-zA-Z0-9+._-]{0,15}$\""}

```json
"mp3"
```

- url (required): s985

### s985: string

URL of the audio file; fails with 400 `invalid_parameter`.

uri

{"maxLength":"8000"}

- keyterms (optional): s242

### s242: array

Terms to bias recognition toward. Not supported by the providers of this gateway: a
non-empty list fails with 400 `invalid_parameter`; put such terms into `prompt`.

{}

### s7: string

{}

- language (optional): s243

### s243: string

Language of the audio as an ISO-639-1 code, for example `de`; detected if missing.

{}

```json
"de"
```

- metadata (optional): s244

### s244: any

Local metadata: at most 16 string pairs, keys 1..64 and values 0..512 characters.

{}

- model (required): s245

### s245: string

Transcription model, with the same ID as on OpenRouter, or an alias of the gateway.
Models without audio transcription fail with 404 `no_endpoint`; an unknown ID with 400
`model_not_found` and a suggestion in `remedy_hint`.

{}

```json
"openai/whisper-large-v3"
```

- prompt (optional): s246

### s246: string

Text that guides the transcription, for example spellings of names or the previous
part of a longer recording. Passed to the provider as sent.

{}

```json
"Prozesshub, dpa"
```

- provider (optional): s247

### s247: object

Routing preferences, as for chat completions: `only`, `ignore`, `order`,
`allow_fallbacks`, `sort` and `max_price`. Never sent to the provider.

{}

- response_format (optional): s248

### s248: string

`json` (default) returns `text` and `usage`; `verbose_json` adds `language`,
`duration` and timestamped `segments`.

"json", "verbose_json"

{}

```json
"json"
```

- session_id (optional): s249

### s249: string | null

Groups related requests in generation records and `GET /v1/sessions/{id}`. Use 1 to
256 ASCII letters, digits, `-`, `_`, `.` or `:`; not only dots. A non-null body value
takes precedence over `x-session-id`. Never sent to the provider.

{"minLength":"1","maxLength":"256"}

```json
"session-1234"
```

- temperature (optional): s250

### s250: number

Sampling temperature from 0 to 1.

double

{}

```json
0
```

- timestamp_granularities (optional): s251

### s251: array

Timestamp detail with `verbose_json`: `segment`, and `word` for a `words` array.

{}

### s215: string

A timestamp detail level of `verbose_json`.

"word", "segment"

{}

```json
"segment"
```

- trace (optional): s252

### s252: object

Trace metadata for observability; never sent to the provider.

{}

- user (optional): s253

### s253: string

An identifier of the end user; retained locally and only a tenant-scoped hash may reach a route explicitly supporting user.

{"maxLength":"256"}

```json
"user-1234"
```

## Body: multipart/form-data

```json
{
  "file": "meeting.mp3",
  "language": "de",
  "model": "openai/whisper-large-v3"
}
```

### s5: object

Audio to transcribe as a file upload, as OpenAI's SDKs send it.

{}

```json
{
  "file": "meeting.mp3",
  "language": "de",
  "model": "openai/whisper-large-v3"
}
```

- diarize (optional): s254

### s254: boolean

Speaker labels; `true` fails with 400 (not supported by the providers of this gateway).

{}

- file (optional): s255

### s255: string

The audio file, at most 50 MiB; required (`source_url` is not supported). Its format
comes from the file name's extension or the part's content type: aac, flac, m4a, mp3,
mp4, mpeg, mpga, oga, ogg, opus, wav or webm.

binary

{}

- keyterms[] (optional): s256

### s256: array

Terms to bias recognition toward, one part per term; not supported by the providers of
this gateway (400).

{}

- language (optional): s257

### s257: string

Language of the audio as an ISO-639-1 code; detected if missing.

{}

- metadata (optional): s258

### s258: string | null

Local metadata as a JSON object with at most 16 string pairs, keys 1..64 and values
0..512 characters; never sent to the provider.

{}

```json
"{\"workflow\":\"support\"}"
```

- model (required): s259

### s259: string

Transcription model, as in the JSON form.

{}

```json
"openai/whisper-large-v3"
```

- prompt (optional): s260

### s260: string

Text that guides the transcription.

{}

- provider (optional): s261

### s261: string

Routing preferences as a JSON-encoded object.

{}

- response_format (optional): s262

### s262: string

`json` (default) or `verbose_json`.

"json", "verbose_json"

{}

```json
"json"
```

- session_id (optional): s263

### s263: string

Groups related requests in generation records and `GET /v1/sessions/{id}`. Use 1 to
256 ASCII letters, digits, `-`, `_`, `.` or `:`; not only dots. This form field takes
precedence over `x-session-id`. Never sent to the provider.

{"minLength":"1","maxLength":"256"}

- source_url (optional): s264

### s264: string

URL of the audio for the provider to download; not supported by the providers of this
gateway (400). Upload the file instead.

uri

{}

- temperature (optional): s265

### s265: number

Sampling temperature from 0 to 1.

{}

- timestamp_granularities[] (optional): s266

### s266: array

Timestamp detail with `verbose_json`, one part per value.

{}

A timestamp detail level of `verbose_json`.

- trace (optional): s267

### s267: string

Trace metadata as a JSON-encoded object; never sent to the provider.

{}

- user (optional): s268

### s268: string

An identifier of the end user; retained locally and only a tenant-scoped hash may reach a route explicitly supporting user.

{"maxLength":"256"}

## Response 200: application/json

The transcript, with what the provider counted and the cost in EUR in `usage`.

```json
{
  "text": "Guten Tag, hier ist die Zusammenfassung der Sitzung.",
  "usage": {
    "cost": 0.001,
    "currency": "EUR",
    "is_byok": false,
    "seconds": 9.2
  }
}
```

### s6: object

The transcript, in OpenRouter's format, with the cost in EUR.

{}

```json
{
  "text": "Guten Tag, hier ist die Zusammenfassung der Sitzung.",
  "usage": {
    "cost": 0.001,
    "currency": "EUR",
    "is_byok": false,
    "seconds": 9.2
  }
}
```

- text (required): s269

### s269: string

The transcribed text.

{}

```json
"Guten Tag, hier ist die Zusammenfassung der Sitzung."
```

- usage (optional): s270

### s270: object

What the provider counted and the cost in EUR, if it reported anything the model's
prices apply to; otherwise `cost` is missing rather than zero.

{}

```json
{
  "cost": 0.001,
  "currency": "EUR",
  "is_byok": false,
  "seconds": 9.2
}
```

- cost (optional): s1003

### s1003: number

Cost of the request in EUR: tokens at the model's token prices, audio at its price
per second (started seconds count fully).

double

{}

```json
0.001
```

- input_tokens (optional): s1004

### s1004: integer

Input tokens, if the provider counts tokens.

int64

{"minimum":"0"}

```json
83
```

- output_tokens (optional): s1005

### s1005: integer

Output tokens, if the provider counts tokens.

int64

{"minimum":"0"}

```json
30
```

- seconds (optional): s1006

### s1006: number

Duration of the audio in seconds, if the provider reports it.

double

{}

```json
9.2
```

- total_tokens (optional): s1007

### s1007: integer

Input plus output tokens.

int64

{"minimum":"0"}

```json
113
```

- * (optional): s1008

### s1008: any

Public fields: `currency` (always `EUR`), `is_byok` and exact `cost_details`.
Unknown provider usage fields are removed.

{}

- * (optional): s271

### s271: any

Public OpenRouter transcription fields, for example `language`,
`duration`, `segments` and `words` with `verbose_json`. An optional `id` extension
is omitted if it is not a nonempty string of at most 128 bytes or contains the
credential used for that provider, including encoded forms.

{}

## Response 400: application/json

Recognized upstream 400/422 request rejections return non-retryable client errors with safe public field paths. Invalid request: broken JSON or a malformed form (`invalid_request`), invalid fields such as missing or non-base64 audio, an audio format outside the supported list or unsupported options, with every problem in `issues` (`invalid_parameter`), or an unknown model ID with a suggestion in `remedy_hint` (`model_not_found`)

```json
{
  "error": {
    "code": 400,
    "message": "deepseek/deepseek-v4.1-flsh is not a valid model ID",
    "metadata": {
      "docs_url": "/docs#description/model-not-found",
      "issues": [
        {
          "code": "unknown_model",
          "message": "deepseek/deepseek-v4.1-flsh is not a valid model ID",
          "path": "$.model"
        }
      ],
      "remedy_hint": "Did you mean deepseek/deepseek-v4.1-flash?",
      "request_id": "req_01k7tm9qz3f5c8x2v6b4n0m7hd",
      "retryable": false,
      "type": "model_not_found"
    }
  },
  "user_id": "org_01k7tm2c4e6g8j0k2m4p6r8t0v"
}
```

### s3: object

Every response with an HTTP status of 400 or higher has this shape, OpenRouter's error
format. Everything the gateway adds is inside `error.metadata`, so OpenRouter clients see
nothing unfamiliar. See "Errors" in the introduction for all error types.

{}

```json
{
  "error": {
    "code": 400,
    "message": "deepseek/deepseek-v4.1-flsh is not a valid model ID",
    "metadata": {
      "docs_url": "/docs#description/model-not-found",
      "issues": [
        {
          "code": "unknown_model",
          "message": "deepseek/deepseek-v4.1-flsh is not a valid model ID",
          "path": "$.model"
        }
      ],
      "remedy_hint": "Did you mean deepseek/deepseek-v4.1-flash?",
      "request_id": "req_01k7tm9qz3f5c8x2v6b4n0m7hd",
      "retryable": false,
      "type": "model_not_found"
    }
  },
  "user_id": "org_01k7tm2c4e6g8j0k2m4p6r8t0v"
}
```

- error (required): s238

### s238: object

What went wrong.

{}

```json
{
  "code": 400,
  "message": "temperature must be at most 2, got 5 (and 1 more)",
  "metadata": {
    "docs_url": "/docs#description/invalid-parameter",
    "issues": [
      {
        "code": "out_of_range",
        "message": "temperature must be at most 2, got 5",
        "path": "$.temperature"
      },
      {
        "code": "invalid_value",
        "message": "messages[1].role must be one of system, developer, user, assistant, tool, got \"bot\"",
        "path": "$.messages[1].role"
      }
    ],
    "request_id": "req_01k7tm9qz3f5c8x2v6b4n0m7hd",
    "retryable": false,
    "type": "invalid_parameter"
  }
}
```

- code (required): s633

### s633: integer

The HTTP status of the response, as a number.

int32

{"minimum":"0"}

```json
400
```

- message (required): s634

### s634: string

What went wrong, in English. With several problems: the first one and how many more
follow; all of them are in `metadata.issues`. The text may change; match on
`metadata.type` instead.

{}

```json
"temperature must be at most 2, got 5"
```

- metadata (optional): s635

### s635: object

Details for programs: error type, request ID, every problem, a suggested fix and, for
provider errors, which provider failed. Always present on gateway errors.

{}

```json
{
  "docs_url": "/docs#description/rate-limited",
  "provider_error": {
    "category": "rate_limited",
    "provider_name": "deepinfra",
    "retry_after": 2,
    "retryable": true,
    "status": 429
  },
  "provider_name": "deepinfra",
  "remedy_hint": "Retry after the Retry-After interval, or allow fallbacks to other providers (provider.allow_fallbacks).",
  "request_id": "req_01k7tm9qz3f5c8x2v6b4n0m7hd",
  "retry_after": 2,
  "retryable": true,
  "type": "rate_limited"
}
```

- available_providers (optional): s639

### s639: array

Providers that serve the model (when `provider.only` excluded all of them).

{}

```json
[
  "deepinfra",
  "open-inference"
]
```

- docs_url (required): s640

### s640: string

Link to the section of this error type in the documentation.

{}

```json
"/docs#description/model-not-found"
```

- failed_routing_step (optional): s641

### s641: string

The routing step that left no route (routing errors only).

{}

```json
"Filter by Max Price"
```

- issues (optional): s642

### s642: array

Every problem found in the request, so all can be fixed at once (at most 20); for
routing errors one entry per excluded route, for `no_provider_available` one per failed
attempt.

{}

### s123: object

One problem in the request, one reason a route was excluded, or one failed attempt.

{}

```json
{
  "code": "invalid_url",
  "message": "messages[2].content[0].image_url.url must be an http(s) URL or a base64 data URL",
  "path": "$.messages[2].content[0].image_url.url"
}
```

- code (required): s636

### s636: string

Kind of problem, stable for programs.

"required", "invalid_type", "invalid_value", "out_of_range", "empty", "invalid_url", "invalid_base64", "unsupported_media_type", "media_type_mismatch", "media_too_large", "too_many_media", "unsupported_media_transport", "media_fetch_failed", "unknown_tool", "unknown_model", "not_available", "not_allowed", "route_excluded", "bridge_failed", "provider_failed"

{}

```json
"out_of_range"
```

- message (required): s637

### s637: string

The problem in English, naming the field and, if short, the value sent.

{}

```json
"temperature must be at most 2, got 5"
```

- path (required): s638

### s638: string

Where the problem is: JSONPath of the field in the request body, for example
`$.messages[2].content[0].image_url.url`, or `query.<name>` for a query parameter.

{}

```json
"$.temperature"
```

- provider_error (optional): s643

### s643: oneOf

Safe provider diagnostics, identical for HTTP errors and terminal stream events.

{}

oneOf: s1158

### s1158: object

Provider diagnostics without provider-authored text. HTTP and terminal SSE errors use
this same structure; arbitrary upstream messages and metadata are discarded.

{}

```json
{
  "category": "rate_limited",
  "provider_name": "deepinfra",
  "retry_after": 2,
  "retryable": true,
  "status": 429
}
```

- category (required): s1299

### s1299: string

Gateway classification from HTTP status and recognized dialect identifiers.

"rate_limited", "overloaded", "invalid_request", "context_length", "content_filtered", "authentication", "billing", "timeout", "unavailable", "unknown"

{}

```json
"rate_limited"
```

- code (optional): s1300

### s1300: string

Exact identifier from the configured dialect's fixed list; arbitrary values vanish.

{}

```json
"rate_limit_exceeded"
```

- provider_name (required): s1301

### s1301: string

Configured provider name, never a name supplied by the upstream body.

{}

```json
"deepinfra"
```

- retry_after (optional): s1302

### s1302: integer

Bounded seconds from the upstream Retry-After header, when present and numeric.

int64

{"minimum":"0"}

```json
2
```

- retryable (required): s1303

### s1303: boolean

Whether the classified failure can be transient. Unknown failures are not promised retryable.

{}

- status (optional): s1304

### s1304: integer

Actual HTTP status received from the upstream, including 200 for native errors.
Absent when no HTTP status is available.

int32

{"minimum":"0"}

```json
429
```

oneOf: s588

### s588: null

{}

- provider_name (optional): s644

### s644: string

The provider that failed, as in the response field `provider` (provider errors only).

{}

```json
"deepinfra"
```

- raw (optional): s645

### s645: string

Reserved OpenRouter compatibility field. The gateway never fills it: provider
free text is deliberately withheld. Use provider_error instead.

{}

```json
""
```

- remedy_hint (optional): s646

### s646: string

A concrete fix, for example the closest model ID to a mistyped one.

{}

```json
"Did you mean deepseek/deepseek-v4.1-flash?"
```

- request_id (required): s647

### s647: string

ID of the request, the same as the `x-request-id` response header. Quote it when
contacting support.

{}

```json
"req_01k7tm9qz3f5c8x2v6b4n0m7hd"
```

- requested_providers (optional): s648

### s648: array

Providers named in `provider.only` (when it excluded all routes).

{}

```json
[
  "scaleway"
]
```

- retry_after (optional): s649

### s649: integer

Seconds to wait before retrying; also sent as the `Retry-After` header (429 and 503).

int64

{"minimum":"0"}

```json
2
```

- retryable (required): s650

### s650: boolean

Whether sending the identical request again can succeed (for example after a timeout
or rate limit), as opposed to errors that need a changed request.

{}

- routing_funnel (optional): s651

### s651: array

How routing narrowed down the providers: each step with the number of routes left
(routing errors only, same format as OpenRouter).

{}

### s200: object

One routing step, as in OpenRouter's `routing_funnel`.

{}

```json
{
  "endpoint_count": 0,
  "reason": "provider.max_price",
  "step": "Filter by Max Price"
}
```

- endpoint_count (required): s979

### s979: integer

Number of routes (providers of the model) left after the step.

{"minimum":"0"}

```json
2
```

- reason (optional): s980

### s980: string

The request field the step filtered on.

{}

```json
"provider.only"
```

- step (required): s981

### s981: string

Name of the step, as at OpenRouter.

{}

```json
"Initial Endpoints"
```

- type (required): s652

### s652: string

Stable error type to match on in code; see "Errors" in the introduction. Messages may
change, the type does not.

"invalid_request", "invalid_parameter", "unsupported_parameter", "context_length_exceeded", "authentication", "insufficient_credits", "workspace_budget_exceeded", "permission_denied", "moderation", "model_not_found", "no_endpoint", "not_found", "method_not_allowed", "timeout", "payload_too_large", "media_fetch_failed", "rate_limited", "provider_error", "idempotency_conflict", "idempotency_in_progress", "idempotency_unavailable", "provider_invalid_response", "no_provider_available", "byok_invalid_credential", "byok_rate_limited", "byok_unavailable", "feature_unavailable", "internal"

{}

```json
"invalid_parameter"
```

- user_id (optional): s239

### s239: string | null

Organization of the API key, if the key was recognized.

{}

```json
"org_01k7tm2c4e6g8j0k2m4p6r8t0v"
```

## Response 401: application/json

Missing, invalid or expired API key (`authentication`)

## Response 402: application/json

The API key spending limit, the workspace budget (`workspace_budget_exceeded`) or the organization prepaid balance cannot cover the estimated request reservation, including fees, media and concurrent reservations (`insufficient_credits` for key and organization). No paid upstream call starts without a reservation.

## Response 403: application/json

The organization, workspace or key policy does not allow the model (`permission_denied`); `remedy_hint` names the models it may use

## Response 404: application/json

The model exists, but none of its providers fits the request: it does not transcribe audio, or `provider` filters or `max_price` exclude every provider. `issues` names the reason per provider (`no_endpoint`)

## Response 408: application/json

The provider did not connect or did not finish its response within the time limit, or the request body stopped arriving (`timeout`)

## Response 409: application/json

idempotency_conflict: this key has different request content; use a new key. idempotency_in_progress: the original is running; respect Retry-After. idempotency_unavailable: no safe replay is possible; do not silently recompute. See remedy_hint.

## Response 413: application/json

The request body or the decoded audio is larger than 50 MiB (`payload_too_large`)

## Response 429: application/json

Customer quota or upstream rate limit exhausted (`rate_limited`)

## Response 500: application/json

Unexpected gateway error (`internal`)

## Response 501: application/json

feature_unavailable: A required feature is permanently unconfigured on this gateway, for example encrypted idempotency replay without its encryption key, PII redaction without a detector, or BYOK import without import keys. Ask the operator to configure it or remove the optional feature from the request. Retrying the identical request cannot enable the feature: retryable is false and no Retry-After header is sent. Temporary cache, database, detector or provider outages, pending imports and missing or revoked individual customer credentials retain their existing error types.

## Response 502: application/json

The only provider tried failed (`provider_error`, with `provider_name` and structured `provider_error` diagnostics; provider text is withheld) or sent a response without `text`, larger than 32 MiB or too complex to parse (`provider_invalid_response`)

## Response 503: application/json

Every provider failed, the gateway is busy with other large request bodies, or this gateway instance is shutting down (`no_provider_available`)
