Read generation content

The request's messages and what the client received of the first choice (text, reasoning and tool calls), plus the error if the generation failed, in OpenRouter's format. Streams are recorded as they pass, without holding them back. The gateway's additional data.previous_errors lists up to 16 earlier failed attempts, even after a successful fallback (data.error stays null). On failure the same history is also available at OpenRouter's data.error.previous_errors. The terminal provider error is not repeated as a previous attempt; when every provider failed, the aggregate error lists all attempts.

Only generations of API keys whose policy allows content capture (capture) have content, and only such keys of the same organization and workspace can read it; for every other key and generation the answer is 404. Without that opt-in, the gateway stores no prompts or answers anywhere. Messages are kept up to 768 KiB of JSON and answers up to 256 KiB per generation; longer content is cut and marked with truncated. This gateway instance keeps the most recent 32 MiB of content in memory. Active captures share a separate 16 MiB reservation for their bounded input, output and attempt history. If admission would exceed it, the request proceeds without content (this endpoint returns 404), while generation metadata and billing are recorded normally. Queued content is also bounded to 32 MiB. Reservations are released when content moves into that queue or is dropped. Downloads reserve space for the content copy and encoded response from the shared response budget before copying. Slow downloads keep that reservation until their bytes are sent or dropped; memory pressure returns 503 with Retry-After after a bounded wait.

GET https://api.tokenlane.de/v1/generation/content

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": [] } ] ]

Values starting with YOUR_ are placeholders. Replace them with appropriate values before sending.

curl

curl --request GET \
  --url 'https://api.tokenlane.de/v1/generation/content?id=YOUR_ID' \
  --header 'Authorization: Bearer YOUR_API_KEY'

node

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

python

import os
import urllib.request

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

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

vercel

// This operation uses HTTP directly.
const response = await fetch("https://api.tokenlane.de/v1/generation/content?id=YOUR_ID", {
  method: "GET",
  headers: {
    "Authorization": "Bearer " + process.env.TOKENLANE_API_KEY,
  },
});
console.log(await response.text());

query: id (required)

The generation ID, e.g. the id of a chat completion

s7: string

{}

Response 200: application/json

Prompt and answer, previous failed attempts even after successful fallback, and the terminal error only if the generation failed

{
  "data": {
    "error": null,
    "id": "gen-01k7tm9qz3f5c8x2v6b4n0m7hd",
    "input": {
      "messages": [
        {
          "content": "What is the capital of Austria?",
          "role": "user"
        }
      ],
      "truncated": false
    },
    "output": {
      "completion": "Vienna.",
      "reasoning": null,
      "tool_calls": [],
      "truncated": false
    },
    "previous_errors": []
  }
}

s18: object

Response of GET /v1/generation/content, in OpenRouter's shape.

{}

  • data (required): s307

s307: object

Prompt and answer of the generation.

{}

{
  "error": null,
  "id": "gen-01k7tm9qz3f5c8x2v6b4n0m7hd",
  "input": {
    "messages": [
      {
        "content": "What is the capital of Austria?",
        "role": "user"
      }
    ],
    "truncated": false
  },
  "output": {
    "completion": "Vienna.",
    "reasoning": null,
    "tool_calls": [],
    "truncated": false
  },
  "previous_errors": []
}
  • error (required): s667

s667: object | null

The error a failed generation ended with, in OpenRouter's shape.

{}

{
  "message": "Provider scaleway returned an error (HTTP 500)",
  "previous_errors": [],
  "provider_name": "scaleway",
  "raw": null,
  "status": 502
}
  • message (required): s1159

s1159: string | null

The error message the client received.

{}

"Provider scaleway returned an error (HTTP 500)"
  • previous_errors (required): s1160

s1160: array

Earlier failed attempts in order, at most the first 16; the same as data.previous_errors. A single terminal provider failure is not repeated. An aggregate error after every provider failed includes all attempts, up to the limit.

{}

s132: object

A provider attempt that failed before the gateway tried the next provider.

{}

{
  "code": 429,
  "message": "Provider mistral is rate limited",
  "provider_name": "mistral",
  "raw": null
}
  • code (required): s680

s680: integer

HTTP status the attempt ended with.

int32

{"minimum":"0"}

429
  • message (required): s681

s681: string

What went wrong.

{}

"Provider mistral is rate limited"
  • provider_error (optional): s682

s682: oneOf

Safe provider diagnostics; identical to error.metadata.provider_error.

{}

oneOf: s1165

s1165: object

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

{}

{
  "category": "rate_limited",
  "provider_name": "deepinfra",
  "retry_after": 2,
  "retryable": true,
  "status": 429
}
  • category (required): s1306

s1306: string

Gateway classification from HTTP status and recognized dialect identifiers.

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

{}

"rate_limited"
  • code (optional): s1300

s1300: string

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

{}

"rate_limit_exceeded"
  • provider_name (required): s1301

s1301: string

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

{}

"deepinfra"
  • retry_after (optional): s1302

s1302: integer

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

int64

{"minimum":"0"}

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"}

429

oneOf: s588

s588: null

{}

  • provider_name (required): s683

s683: string | null

The provider that was tried, or null.

{}

"mistral"
  • raw (required): s684

s684: string | null

Reserved OpenRouter compatibility field; always null. Provider text is withheld.

{}

  • provider_error (optional): s1161

s1161: oneOf

Safe provider diagnostics; identical to error.metadata.provider_error.

{}

oneOf: s1305

s1305: object

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

{}

{
  "category": "rate_limited",
  "provider_name": "deepinfra",
  "retry_after": 2,
  "retryable": true,
  "status": 429
}
  • category (required): s1347

s1347: string

Gateway classification from HTTP status and recognized dialect identifiers.

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

{}

"rate_limited"
  • code (optional): s1300

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

  • provider_name (required): s1301

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

  • retry_after (optional): s1302

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

  • retryable (required): s1303

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

  • status (optional): s1304

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

oneOf: s588

  • provider_name (required): s1162

s1162: string | null

The provider whose error the client received, or null.

{}

"scaleway"
  • raw (required): s684

Reserved OpenRouter compatibility field; always null. Provider text is withheld.

  • status (required): s1163

s1163: integer | null

HTTP status the client received.

int32

{"minimum":"0"}

502
  • id (required): s668

s668: string

ID of the generation.

{}

"gen-01k7tm9qz3f5c8x2v6b4n0m7hd"
  • input (required): s669

s669: object

What the request sent.

{}

{
  "messages": [
    {
      "content": "What is the capital of Austria?",
      "role": "user"
    }
  ],
  "truncated": false
}
  • messages (required): s685

s685: array

The messages of the request. When truncated, long strings are cut and later messages or fields are missing; what is there is valid JSON.

{}

[
  {
    "content": "What is the capital of Austria?",
    "role": "user"
  }
]

s1164: object

{}

  • truncated (required): s686

s686: boolean

Whether the messages were longer than the gateway keeps (768 KiB of JSON) and were cut.

{}

false
  • output (required): s670

s670: object

What the client received of the first choice.

{}

{
  "completion": "Vienna.",
  "reasoning": null,
  "tool_calls": [],
  "truncated": false
}
  • completion (required): s687

s687: string | null

The text of the answer, or null if it had none (for example only tool calls, or the generation failed before any text).

{}

"Vienna."
  • reasoning (required): s688

s688: string | null

The reasoning the client received, or null.

{}

  • tool_calls (required): s689

s689: array

Tool calls of the answer, in order.

{}

s135: object

One tool call of an answer.

{}

{
  "arguments": "{\"city\":\"Vienna\"}",
  "id": "call_1",
  "name": "get_weather"
}
  • arguments (required): s691

s691: string

The arguments as the model wrote them (usually JSON).

{}

"{\"city\":\"Vienna\"}"
  • id (required): s692

s692: string | null

ID of the call, or null if the model sent none.

{}

"call_1"
  • name (required): s693

s693: string | null

Name of the called function, or null if the model sent none.

{}

"get_weather"
  • truncated (required): s690

s690: boolean

Whether the answer was longer than the gateway keeps (256 KiB) and was cut.

{}

false
  • previous_errors (optional): s671

s671: array

Earlier failed attempts in order, at most the first 16. Available even when a fallback succeeded (error is null) or the client cancelled. On failure this is also returned in error.previous_errors. A final single-provider error is not repeated here; an aggregate error after all providers failed includes every attempt, up to the limit. This additional gateway field does not change the generation's terminal status.

{"maxItems":"16"}

[]
  • response_format (optional): s672

s672: object

Original output format including its JSON Schema, only with content capture; valid JSON bounded to 64 KiB.

{}

  • response_format_truncated (optional): s673

s673: boolean

Whether response_format was structurally shortened. Absent when that field was not captured.

{}

false
  • stop (optional): s674

s674: any

Original stop sequences, only with content capture; valid JSON bounded to 64 KiB.

{}

  • stop_truncated (optional): s675

s675: boolean

Whether stop was structurally shortened. Absent when that field was not captured.

{}

false
  • tool_choice (optional): s676

s676: any

Original tool selection including the function name, only with content capture; valid JSON bounded to 64 KiB.

{}

  • tool_choice_truncated (optional): s677

s677: boolean

Whether tool_choice was structurally shortened. Absent when that field was not captured.

{}

false
  • tools (optional): s678

s678: array

Original tool definitions and parameter schemas, only with content capture; valid JSON bounded to 64 KiB.

{}

  • tools_truncated (optional): s679

s679: boolean

Whether tools was structurally shortened. Absent when that field was not captured.

{}

false

Response 400: application/json

The query parameter id is missing, empty or given more than once (invalid_parameter)

{
  "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.

{}

{
  "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.

{}

{
  "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"}

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.

{}

"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.

{}

{
  "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).

{}

[
  "deepinfra",
  "open-inference"
]
  • docs_url (required): s640

s640: string

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

{}

"/docs#description/model-not-found"
  • failed_routing_step (optional): s641

s641: string

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

{}

"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.

{}

{
  "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"

{}

"out_of_range"
  • message (required): s637

s637: string

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

{}

"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.

{}

"$.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.

{}

{
  "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"

{}

"rate_limited"
  • code (optional): s1300

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

  • provider_name (required): s1301

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

  • retry_after (optional): s1302

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

  • retryable (required): s1303

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

  • status (optional): s1304

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

oneOf: s588

  • provider_name (optional): s644

s644: string

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

{}

"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.

{}

""
  • remedy_hint (optional): s646

s646: string

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

{}

"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.

{}

"req_01k7tm9qz3f5c8x2v6b4n0m7hd"
  • requested_providers (optional): s648

s648: array

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

{}

[
  "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"}

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.

{}

{
  "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"}

2
  • reason (optional): s980

s980: string

The request field the step filtered on.

{}

"provider.only"
  • step (required): s981

s981: string

Name of the step, as at OpenRouter.

{}

"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"

{}

"invalid_parameter"
  • user_id (optional): s239

s239: string | null

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

{}

"org_01k7tm2c4e6g8j0k2m4p6r8t0v"

Response 401: application/json

Missing, invalid or expired API key (authentication)

Response 404: application/json

No content for this ID and key: the key's policy does not allow content capture, the generation was made without capture, by another organization or workspace, has not ended, is unknown, was not admitted due to capture memory pressure, or is no longer kept (not_found)

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

Content reads cannot reserve response memory within the bounded wait (no_provider_available). Finish or cancel pending downloads and retry with Retry-After.