# Read calling API key

The API key the request is sent with: its label, spending limit and reset window, spend and
expiry, in OpenRouter's format. All amounts are in EUR, also in fields named `*_usd` (kept
for OpenRouter compatibility). Usage is confirmed spend across gateway nodes; daily,
weekly (Monday) and monthly windows use UTC settlement time. `limit_remaining` excludes
concurrent reservations. `gateway_credits` exposes the same organization's prepaid
funding, confirmed usage and reservations across all its keys as exact EUR strings.
Reloads and process restarts preserve confirmed usage in the financial journal.

`GET https://api.tokenlane.de/v1/key`

## 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 GET \
  --url 'https://api.tokenlane.de/v1/key' \
  --header 'Authorization: Bearer YOUR_API_KEY'
```

## node

```node
const response = await fetch("https://api.tokenlane.de/v1/key", {
  method: "GET",
  headers: {
    "Authorization": "Bearer " + process.env.TOKENLANE_API_KEY,
  },
});
console.log(await response.text());
```

## python

```python
import os
import urllib.request

request = urllib.request.Request(
    "https://api.tokenlane.de/v1/key",
    method="GET",
    headers={
        "Authorization": "Bearer " + os.environ["TOKENLANE_API_KEY"],
    },
)

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/key", {
  method: "GET",
  headers: {
    "Authorization": "Bearer " + process.env.TOKENLANE_API_KEY,
  },
});
console.log(await response.text());
```

## Response 200: application/json

The API key used for the request; amounts in EUR

```json
{
  "data": {
    "allowed_data_regions": [
      "europe"
    ],
    "budgets": [
      {
        "budget_id": null,
        "currency": "EUR",
        "guardrail_id": null,
        "include_byok": false,
        "limit_usd": 100,
        "remaining_usd": 100,
        "reset_interval": "weekly",
        "resets_at": "2026-10-26T00:00:00Z",
        "scope": "key_limit",
        "spend_usd": 0
      }
    ],
    "byok_usage": 0,
    "byok_usage_daily": 0,
    "byok_usage_monthly": 0,
    "byok_usage_weekly": 0,
    "creator_user_id": null,
    "effective_budget": {
      "budget_id": null,
      "currency": "EUR",
      "guardrail_id": null,
      "include_byok": false,
      "limit_usd": 100,
      "remaining_usd": 100,
      "reset_interval": "weekly",
      "resets_at": "2026-10-26T00:00:00Z",
      "scope": "key_limit",
      "spend_usd": 0
    },
    "expires_at": "2027-12-31T23:59:59Z",
    "free_model_daily_requests": {
      "limit": 0,
      "remaining": 0,
      "used": 0
    },
    "gateway_rate_limits": {
      "effective": {
        "max_parallel_requests": 4,
        "rpm": 60,
        "tpm": 10000
      },
      "key": {
        "max_parallel_requests": 4,
        "rpm": 60,
        "tpm": 10000
      },
      "organization": {
        "max_parallel_requests": null,
        "rpm": null,
        "tpm": null
      },
      "scope": "cluster"
    },
    "include_byok_in_limit": false,
    "is_free_tier": false,
    "is_management_key": false,
    "is_provisioning_key": false,
    "label": "ci-pipeline",
    "limit": 100,
    "limit_remaining": 100,
    "limit_reset": "weekly",
    "organization_id": "org_01k7tm2c4e6g8j0k2m4p6r8t0v",
    "rate_limit": {
      "interval": "10s",
      "note": "This field is deprecated and safe to ignore.",
      "requests": -1
    },
    "usage": 0,
    "usage_daily": 0,
    "usage_monthly": 0,
    "usage_weekly": 0,
    "workspace_id": null
  }
}
```

### s19: object

Response of `GET /v1/key`, in OpenRouter's shape.

{}

- data (required): s308

### s308: object

The API key the request was sent with.

{}

```json
{
  "allowed_data_regions": [
    "europe"
  ],
  "budgets": [
    {
      "budget_id": null,
      "currency": "EUR",
      "guardrail_id": null,
      "include_byok": false,
      "limit_usd": 100,
      "remaining_usd": 100,
      "reset_interval": "weekly",
      "resets_at": "2026-10-26T00:00:00Z",
      "scope": "key_limit",
      "spend_usd": 0
    }
  ],
  "byok_usage": 0,
  "byok_usage_daily": 0,
  "byok_usage_monthly": 0,
  "byok_usage_weekly": 0,
  "creator_user_id": null,
  "effective_budget": {
    "budget_id": null,
    "currency": "EUR",
    "guardrail_id": null,
    "include_byok": false,
    "limit_usd": 100,
    "remaining_usd": 100,
    "reset_interval": "weekly",
    "resets_at": "2026-10-26T00:00:00Z",
    "scope": "key_limit",
    "spend_usd": 0
  },
  "expires_at": "2027-12-31T23:59:59Z",
  "free_model_daily_requests": {
    "limit": 0,
    "remaining": 0,
    "used": 0
  },
  "gateway_rate_limits": {
    "effective": {
      "max_parallel_requests": 4,
      "rpm": 60,
      "tpm": 10000
    },
    "key": {
      "max_parallel_requests": 4,
      "rpm": 60,
      "tpm": 10000
    },
    "organization": {
      "max_parallel_requests": null,
      "rpm": null,
      "tpm": null
    },
    "scope": "cluster"
  },
  "include_byok_in_limit": false,
  "is_free_tier": false,
  "is_management_key": false,
  "is_provisioning_key": false,
  "label": "ci-pipeline",
  "limit": 100,
  "limit_remaining": 100,
  "limit_reset": "weekly",
  "organization_id": "org_01k7tm2c4e6g8j0k2m4p6r8t0v",
  "rate_limit": {
    "interval": "10s",
    "note": "This field is deprecated and safe to ignore.",
    "requests": -1
  },
  "usage": 0,
  "usage_daily": 0,
  "usage_monthly": 0,
  "usage_weekly": 0,
  "workspace_id": null
}
```

- allowed_data_regions (required): s793

### s793: array

Compliance-region setting of the effective policy: `global` for no minimum compliance
requirement, otherwise `europe`. Route eligibility also applies the remaining policy restrictions.

{}

```json
[
  "europe"
]
```

### s98: string

Compliance regions represented by the gateway's effective policy and generation metadata.

"global", "europe"

{}

- budgets (required): s794

### s794: array

Every budget that applies to the key, in the order enforcement checks them: the
workspace budget (`workspace`), then the key's own limit (`key_limit`). Empty without a
budget. The organization's prepaid credits are `gateway_credits`.

{}

### s144: object

One budget that applies to the key, with the spend counted against it. Amounts are in
**EUR** despite the `_usd` suffix, which is kept for OpenRouter compatibility.

{}

```json
{
  "budget_id": null,
  "currency": "EUR",
  "guardrail_id": null,
  "include_byok": false,
  "limit_usd": 100,
  "remaining_usd": 100,
  "reset_interval": "weekly",
  "resets_at": "2026-10-26T00:00:00Z",
  "scope": "key_limit",
  "spend_usd": 0
}
```

- budget_id (required): s783

### s783: string | null

ID of the workspace (`ws_…`) for the `workspace` budget; null for `key_limit`.

{}

- currency (required): s784

### s784: string

Currency of limit_usd, spend_usd and remaining_usd. Always EUR; the suffixes are compatibility names.

{}

```json
"EUR"
```

- guardrail_id (required): s785

### s785: string | null

ID of the guardrail carrying this budget; null for `key_limit`.

{}

- include_byok (required): s786

### s786: boolean

Whether spend on own provider keys (BYOK) counts toward this budget. Always false.

{}

- limit_usd (required): s787

### s787: number

Limit in EUR for the current window.

double

{}

```json
100
```

- remaining_usd (required): s788

### s788: number

Spendable EUR after confirmed spend and open reservations, never below zero.

double

{}

```json
100
```

- reset_interval (required): s789

### s789: string | null

UTC reset window of a key or workspace budget; absence denotes a lifetime budget.

"daily", "weekly", "monthly", null

{}

- resets_at (required): s790

### s790: string | null

RFC 3339 UTC instant at which the window starts again, or null for a lifetime budget.

date-time

{}

```json
"2026-10-26T00:00:00Z"
```

- scope (required): s791

### s791: string

Which budget this is: `workspace`, the budget shared by the key's workspace, or
`key_limit`, the key's own limit. Both must have headroom for a request.

"workspace", "key_limit"

{}

- spend_usd (required): s792

### s792: number

Spend in EUR counted against the limit in the current window. Confirmed across all gateway nodes.

double

{}

```json
0
```

- byok_usage (required): s795

### s795: number

Spend on own provider keys (BYOK) in EUR. Always 0: the gateway has no BYOK.

double

{}

```json
0
```

- byok_usage_daily (required): s796

### s796: number

BYOK spend in EUR in the current UTC day. Always 0.

double

{}

```json
0
```

- byok_usage_monthly (required): s797

### s797: number

BYOK spend in EUR in the current UTC month. Always 0.

double

{}

```json
0
```

- byok_usage_weekly (required): s798

### s798: number

BYOK spend in EUR in the current UTC week. Always 0.

double

{}

```json
0
```

- creator_user_id (required): s799

### s799: string | null

Member who created the key, or null when the inference snapshot has no creator identity.
The gateway does not substitute the owning organization for an unknown member.

{}

- effective_budget (required): s800

### s800: object | null

One budget that applies to the key, with the spend counted against it. Amounts are in
**EUR** despite the `_usd` suffix, which is kept for OpenRouter compatibility.

{}

```json
{
  "budget_id": null,
  "currency": "EUR",
  "guardrail_id": null,
  "include_byok": false,
  "limit_usd": 100,
  "remaining_usd": 100,
  "reset_interval": "weekly",
  "resets_at": "2026-10-26T00:00:00Z",
  "scope": "key_limit",
  "spend_usd": 0
}
```

- budget_id (required): s783

ID of the workspace (`ws_…`) for the `workspace` budget; null for `key_limit`.

- currency (required): s784

Currency of limit_usd, spend_usd and remaining_usd. Always EUR; the suffixes are compatibility names.

- guardrail_id (required): s785

ID of the guardrail carrying this budget; null for `key_limit`.

- include_byok (required): s786

Whether spend on own provider keys (BYOK) counts toward this budget. Always false.

- limit_usd (required): s787

Limit in EUR for the current window.

- remaining_usd (required): s788

Spendable EUR after confirmed spend and open reservations, never below zero.

- reset_interval (required): s789

UTC reset window of a key or workspace budget; absence denotes a lifetime budget.

- resets_at (required): s790

RFC 3339 UTC instant at which the window starts again, or null for a lifetime budget.

- scope (required): s1181

### s1181: string

Which budget this is: `workspace`, the budget shared by the key's workspace, or
`key_limit`, the key's own limit. Both must have headroom for a request.

"workspace", "key_limit"

{}

- spend_usd (required): s792

Spend in EUR counted against the limit in the current window. Confirmed across all gateway nodes.

- expires_at (optional): s801

### s801: string | null

From this instant (RFC 3339, UTC) requests with the key fail with 401
`authentication`; null if it does not expire. A stream that is already running
finishes.

date-time

{}

```json
"2027-12-31T23:59:59Z"
```

- free_model_daily_requests (required): s802

### s802: object

Daily quota for free model variants (`:free` at OpenRouter). The gateway has none, so
every count is 0.

{}

```json
{
  "limit": 0,
  "remaining": 0,
  "used": 0
}
```

- limit (required): s661

### s661: integer

Free-model requests allowed per UTC day.

int64

{}

```json
0
```

- remaining (required): s662

### s662: integer

Free-model requests left today (UTC).

int64

{}

```json
0
```

- used (required): s663

### s663: integer

Free-model requests made today (UTC).

int64

{}

```json
0
```

- gateway_byok_quota (optional): s803

### s803: oneOf

Current allowance and endpoint resources shared by all organizations of this identity.
Byte counters include in-flight reservations; unknown outcomes retain coverage.

{}

oneOf: s1182

### s1182: object

Current shared customer-identity quota, read from the authoritative financial journal.

{}

```json
{
  "day_bytes": 100,
  "day_limit": 1073741824,
  "free_limit": 100000,
  "free_remaining": 99990,
  "free_used": 10,
  "month": "2026-11",
  "month_bytes": 100,
  "month_limit": 10737418240,
  "parallel": 0,
  "parallel_limit": 8
}
```

- day_bytes (required): s1308

### s1308: integer

Rolling transfer debt including active reservations and their bounded expiry margin.

int64

{"minimum":"0"}

- day_limit (required): s1309

### s1309: integer

Operator-approved rolling 24-hour endpoint transfer limit, default 1 GiB.

int64

{"minimum":"0"}

- free_limit (required): s1310

### s1310: integer

Current configured free allowance.

int64

{"minimum":"0"}

- free_remaining (required): s1311

### s1311: integer

Free requests currently available; never a historical request ordinal.

int64

{"minimum":"0"}

- free_used (required): s1312

### s1312: integer

Consumed and reserved free requests across all organizations of the identity.

int64

{"minimum":"0"}

- month (required): s1313

### s1313: string

UTC calendar month, YYYY-MM.

{}

- month_bytes (required): s1314

### s1314: integer

Decoded application bytes and active reservations in this UTC month.

int64

{"minimum":"0"}

- month_limit (required): s1315

### s1315: integer

Operator-approved monthly endpoint transfer limit, default 10 GiB.

int64

{"minimum":"0"}

- parallel (required): s1316

### s1316: integer

Endpoint requests with unexpired parallelism reservations.

int64

{"minimum":"0"}

- parallel_limit (required): s1317

### s1317: integer

Operator-approved concurrent endpoint request limit, default eight.

int64

{"minimum":"0"}

oneOf: s588

### s588: null

{}

- gateway_credits (optional): s804

### s804: oneOf

Gateway extension: the organization's prepaid account across all gateway nodes.
Absent when prepaid has never been configured. Confirmed usage survives restarts.

{}

oneOf: s1183

### s1183: object

Exact prepaid amounts shared by every key of the authenticated organization.

{}

```json
{
  "currency": "EUR",
  "remaining_credits": "7",
  "reserved_credits": "1",
  "scope": "cluster",
  "total_credits": "10",
  "total_usage": "2"
}
```

- currency (required): s1318

### s1318: string

Currency of every amount; always EUR.

{}

```json
"EUR"
```

- remaining_credits (required): s1319

### s1319: string

Available credits after usage and reservations, never below zero.

{}

```json
"7"
```

- reserved_credits (required): s1320

### s1320: string

Open reservations, including requests with missing final usage.

{}

```json
"1"
```

- scope (required): s1321

### s1321: string

Enforcement scope; all gateway nodes share these prepaid amounts.

{}

```json
"cluster"
```

- total_credits (required): s1322

### s1322: string

Cumulative funded amount as an exact decimal string.

{}

```json
"10"
```

- total_usage (required): s1323

### s1323: string

Confirmed usage across all organization keys as an exact decimal string.

{}

```json
"2"
```

oneOf: s588

- gateway_rate_limits (optional): s805

### s805: oneOf

Gateway extension: configured cluster quotas, independent of the deprecated
`rate_limit`. Organization quotas are shared by all its keys and gateway nodes.

{}

oneOf: s1184

### s1184: object

Cluster-wide customer quotas. Both scopes must admit a request; neither replaces the other.

{}

- effective (required): s1324

### s1324: object

The smaller configured limit in each dimension; shared usage can exhaust it sooner.

{}

- max_parallel_requests (required): s955

### s955: integer | null

Simultaneous requests; open streams occupy a slot until completion or cancellation.

int32

{"minimum":"1"}

```json
4
```

- rpm (required): s956

### s956: integer | null

Requests per minute, with a burst up to this number. Authenticated reads also count.

int32

{"minimum":"1"}

```json
60
```

- tpm (required): s957

### s957: integer | null

Prompt plus completion tokens per minute, including in-flight estimates.

int32

{"minimum":"1"}

```json
10000
```

- key (required): s1325

### s1325: object

Quotas configured on this API key.

{}

- max_parallel_requests (required): s955

Simultaneous requests; open streams occupy a slot until completion or cancellation.

- rpm (required): s956

Requests per minute, with a burst up to this number. Authenticated reads also count.

- tpm (required): s957

Prompt plus completion tokens per minute, including in-flight estimates.

- organization (required): s1326

### s1326: object

Quotas shared by every key in the organization.

{}

- max_parallel_requests (required): s955

Simultaneous requests; open streams occupy a slot until completion or cancellation.

- rpm (required): s956

Requests per minute, with a burst up to this number. Authenticated reads also count.

- tpm (required): s957

Prompt plus completion tokens per minute, including in-flight estimates.

- scope (required): s1327

### s1327: string

Enforcement scope: `cluster`. All gateway nodes share these counters.

{}

```json
"cluster"
```

oneOf: s588

- include_byok_in_limit (required): s806

### s806: boolean

Whether spend on own provider keys (BYOK) counts toward the limit. Always false: the
gateway has no BYOK.

{}

- is_free_tier (required): s807

### s807: boolean

Whether this is a free tier key. Always false: there is no free tier.

{}

- is_management_key (required): s808

### s808: boolean

Always false for inference keys. Organization management keys authorize only the separate
control-plane API and are excluded from the gateway inference snapshot.

{}

- is_provisioning_key (required): s809

### s809: boolean

Deprecated alias of `is_management_key`.

{"deprecated":"true"}

- label (required): s810

### s810: string

Name of the key, as set when it was created.

{}

```json
"ci-pipeline"
```

- limit (required): s811

### s811: number | null

Most the key may spend in EUR per `limit_reset` window (or in total), or null without a
limit.

double

{}

```json
100
```

- limit_remaining (required): s812

### s812: number | null

EUR the key may still spend in the current window after confirmed costs and open
reservations, or null without a limit.

double

{}

```json
100
```

- limit_reset (required): s789

UTC reset window of a key or workspace budget; absence denotes a lifetime budget.

- organization_id (required): s813

### s813: string | null

Organization that owns the key; also `user_id` in error responses.

{}

```json
"org_01k7tm2c4e6g8j0k2m4p6r8t0v"
```

- rate_limit (required): s814

### s814: object

Deprecated at OpenRouter and kept only for compatibility; fixed values, ignore it.

{}

```json
{
  "interval": "10s",
  "note": "This field is deprecated and safe to ignore.",
  "requests": -1
}
```

- interval (required): s820

### s820: string

Always `10s`.

{}

```json
"10s"
```

- note (required): s821

### s821: string

Always the note that the field is deprecated.

{}

```json
"This field is deprecated and safe to ignore."
```

- requests (required): s822

### s822: integer

Always -1.

int64

{}

```json
-1
```

- usage (required): s815

### s815: number

Total spend of the key in EUR. Confirmed across all gateway nodes.

double

{}

```json
0
```

- usage_daily (required): s816

### s816: number

Spend in EUR in the current UTC day. Confirmed across all gateway nodes.

double

{}

```json
0
```

- usage_monthly (required): s817

### s817: number

Spend in EUR in the current UTC month. Confirmed across all gateway nodes.

double

{}

```json
0
```

- usage_weekly (required): s818

### s818: number

Spend in EUR in the current UTC week (Monday to Sunday). Confirmed across all gateway nodes.

double

{}

```json
0
```

- workspace_id (required): s819

### s819: string | null

Actual workspace the key belongs to (`ws_…`), or null without a workspace assignment.
Workspace membership is independent of whether the workspace has a spending limit.

{}

## Response 401: application/json

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

### 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"
]
```

### s7: string

{}

- 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

- 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 429: application/json

Customer quota exhausted (`rate_limited`); retry after Retry-After

## Response 500: application/json

Unexpected gateway error (`internal`)

## Response 503: application/json

Shared customer admission or identity quota unavailable; retry shortly (`no_provider_available` or `byok_unavailable`)
