AnyInt Gateway Developer APIOpenAPI 3.1.0Contract version 0.1.0

API reference

Use one gateway and API key across OpenAI-compatible, Anthropic, Gemini, and asynchronous media workflows.

Server: https://api.anyint.aiThe AnyInt Gateway origin serving this OpenAPI document.

Read-only reference

This page never collects API keys or sends requests. Run examples in your own secured environment.

Search endpoints

73 endpoints

ChatRoom Integration

4 endpoints

Discover key-scoped models and enterprise capabilities for independent ChatRoom clients.

POST /v1/tasks/request-costs

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/tasks/request-costs' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "request_ids": [
    "req_example:async"
  ]
}'

Authentication

ApiKeyAuthhttp · bearerDeveloper API key passed as Bearer token. In organization tenants, subscription funding is available only to the subscription-bound key or keys owned by the same holder; other members use enterprise wallet or credit admission. Personal-tenant subscription credit priority is unchanged. While explicitly enabled session compatibility remains active, a verified legacy or native AnyInt identity session may select an owned personal-account key with x-anyint-gateway-key-id (1–255 characters; imported source IDs remain accepted). Native model execution requires this explicit selector; retained read-only metadata may use the default owned key. Missing, disabled, expired, or foreign selections fail without falling back to another key. API key credentials retain precedence over the session-only selector.

Request body

Required

application/json

Example

{
  "request_ids": [
    "req_example:async"
  ]
}

Responses

200OK

application/json

Example

{
  "request_costs": [
    {
      "request_id": "req_example:async",
      "credits": 125
    }
  ]
}

Native ChatRoom metadata authenticated with a Developer API key. Preserves existing tenant/key visibility and imported stable asset ownership references.

GET /v1/chatroom/models

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/chatroom/models?scope=<scope>' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
scope	query	string	Required	—
limit	query	integer	Optional	—`Example: 1000`

Responses

200Success; no-store

application/json

Example

{
  "success": true,
  "data": {
    "models": [],
    "total": 0
  }
}

Native ChatRoom metadata authenticated with a Developer API key. Preserves existing tenant/key visibility and imported stable asset ownership references.

GET /v1/chatroom/enterprise-context

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/chatroom/enterprise-context' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Responses

200Success; no-store

application/json

Example

{
  "success": true,
  "data": {
    "featureControls": {
      "seedanceAuthorizedAssets": false
    }
  }
}

Native ChatRoom metadata authenticated with a Developer API key. Preserves existing tenant/key visibility and imported stable asset ownership references.

GET /v1/chatroom/key-context

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/chatroom/key-context' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Responses

200Success; no-store

application/json

Example

{
  "success": true,
  "data": {
    "userId": "user_example",
    "apiKeyId": "key_example",
    "featureControls": {
      "seedanceAuthorizedAssets": false
    }
  }
}

Chat

2 endpoints

Create OpenAI-compatible conversational responses.

When routed through a Gemini adapter, usage includes gemini_usage_metadata with the original token counters for precise modality and cache billing. OpenAI output totals include Gemini thinking tokens; detailed native counters are preserved in Chat Completions, its SSE usage frames, and nonstreaming Responses. Gemini Chat Completions streams emit a terminal choice with finish_reason before data: [DONE]: STOP maps to stop and MAX_TOKENS maps to length. An upstream EOF without a finish reason does not synthesize successful completion. When billing is enabled, built-in web search declared in tools or Responses input.additional_tools requires a compiled price rule covering web_search_queries and the request dimensions. Namespace tool declarations are checked without treating client functions as built-in search. Missing coverage returns HTTP 503 search_tool_pricing_not_configured before initial funding reservation; each actual candidate, including fallback and supply-tier routes, is checked again before provider dispatch. Client function tools are unaffected. Invalid request envelopes, missing model/messages and non-boolean stream values return HTTP 400 before funding or provider dispatch. Provider extension fields are preserved.

POST /v1/chat/completions

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/chat/completions' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "messages": [
    {
      "role": "user",
      "content": "Explain edge computing in 2 sentences."
    }
  ]
}'

Authentication

Parameters

Name	Location	Type	Required	Description
X-Client-Message-Id	header	string	Optional	Opt in to durable tenant-scoped execution deduplication. Reuse only with the identical request body and API key. Completed or possibly dispatched requests never expire into another execution, including after Redis loss. Upstream errors or settlement rollback after dispatch require a new message ID for another execution; failures before dispatch may retry the same ID.
X-Resume-Message-Id	header	string	Optional	Replay a previously generated SSE stream under the original API key and identical request body. This request does not dispatch or bill the provider. Cache retention is 10 minutes and total output is limited to 4 MiB; interrupted generations require a new message ID for continuation.
X-Resume-From-Offset	header	integer	Optional	Number of complete SSE events already consumed, matching the last SSE id. Starts at 0; UTF-8 bytes, tokens and characters are not valid units. Takes precedence over Last-Event-ID.
Last-Event-ID	header	integer	Optional	Alternative complete SSE event offset when X-Resume-From-Offset is absent.

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "messages": [
    {
      "role": "user",
      "content": "Explain edge computing in 2 sentences."
    }
  ]
}

Responses

200OK

application/json

Example

{
  "id": "chatcmpl_example",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Edge computing processes data near its source, reducing latency and bandwidth use."
      },
      "finish_reason": "stop"
    }
  ]
}

POST /openai/v1/chat/completions

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/openai/v1/chat/completions' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "messages": [
    {
      "role": "user",
      "content": "Explain edge computing in 2 sentences."
    }
  ]
}'

Authentication

Parameters

Name	Location	Type	Required	Description
X-Client-Message-Id	header	string	Optional	Opt in to durable tenant-scoped execution deduplication. Reuse only with the identical request body and API key. Completed or possibly dispatched requests never expire into another execution, including after Redis loss. Upstream errors or settlement rollback after dispatch require a new message ID for another execution; failures before dispatch may retry the same ID.
X-Resume-Message-Id	header	string	Optional	Replay a previously generated SSE stream under the original API key and identical request body. This request does not dispatch or bill the provider. Cache retention is 10 minutes and total output is limited to 4 MiB; interrupted generations require a new message ID for continuation.
X-Resume-From-Offset	header	integer	Optional	Number of complete SSE events already consumed, matching the last SSE id. Starts at 0; UTF-8 bytes, tokens and characters are not valid units. Takes precedence over Last-Event-ID.
Last-Event-ID	header	integer	Optional	Alternative complete SSE event offset when X-Resume-From-Offset is absent.

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "messages": [
    {
      "role": "user",
      "content": "Explain edge computing in 2 sentences."
    }
  ]
}

Responses

200OK

application/json

Example

{
  "id": "chatcmpl_example",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Edge computing processes data near its source, reducing latency and bandwidth use."
      },
      "finish_reason": "stop"
    }
  ]
}

Responses

2 endpoints

Create responses with the OpenAI Responses API shape.

POST /v1/responses

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/responses' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "input": "Write a short welcome message."
}'

Authentication

Parameters

Name	Location	Type	Required	Description
X-Client-Message-Id	header	string	Optional	Opt in to durable tenant-scoped execution deduplication. Reuse only with the identical request body and API key. Completed or possibly dispatched requests never expire into another execution, including after Redis loss. Upstream errors or settlement rollback after dispatch require a new message ID for another execution; failures before dispatch may retry the same ID.
X-Resume-Message-Id	header	string	Optional	Replay a previously generated SSE stream under the original API key and identical request body. This request does not dispatch or bill the provider. Cache retention is 10 minutes and total output is limited to 4 MiB; interrupted generations require a new message ID for continuation.
X-Resume-From-Offset	header	integer	Optional	Number of complete SSE events already consumed, matching the last SSE id. Starts at 0; UTF-8 bytes, tokens and characters are not valid units. Takes precedence over Last-Event-ID.
Last-Event-ID	header	integer	Optional	Alternative complete SSE event offset when X-Resume-From-Offset is absent.

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "input": "Write a short welcome message."
}

Responses

200OK

application/json

Example

{
  "id": "resp_example",
  "object": "response",
  "status": "completed"
}

POST /openai/v1/responses

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/openai/v1/responses' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "input": "Write a short welcome message."
}'

Authentication

Parameters

Name	Location	Type	Required	Description
X-Client-Message-Id	header	string	Optional	Opt in to durable tenant-scoped execution deduplication. Reuse only with the identical request body and API key. Completed or possibly dispatched requests never expire into another execution, including after Redis loss. Upstream errors or settlement rollback after dispatch require a new message ID for another execution; failures before dispatch may retry the same ID.
X-Resume-Message-Id	header	string	Optional	Replay a previously generated SSE stream under the original API key and identical request body. This request does not dispatch or bill the provider. Cache retention is 10 minutes and total output is limited to 4 MiB; interrupted generations require a new message ID for continuation.
X-Resume-From-Offset	header	integer	Optional	Number of complete SSE events already consumed, matching the last SSE id. Starts at 0; UTF-8 bytes, tokens and characters are not valid units. Takes precedence over Last-Event-ID.
Last-Event-ID	header	integer	Optional	Alternative complete SSE event offset when X-Resume-From-Offset is absent.

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "input": "Write a short welcome message."
}

Responses

200OK

application/json

Example

{
  "id": "resp_example",
  "object": "response",
  "status": "completed"
}

Text Completions

2 endpoints

Create legacy OpenAI-compatible text completions.

POST /v1/completions

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/completions' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "prompt": "Once upon a time"
}'

Authentication

Parameters

Name	Location	Type	Required	Description
X-Client-Message-Id	header	string	Optional	Opt in to durable tenant-scoped execution deduplication. Reuse only with the identical request body and API key. Completed or possibly dispatched requests never expire into another execution, including after Redis loss. Upstream errors or settlement rollback after dispatch require a new message ID for another execution; failures before dispatch may retry the same ID.
X-Resume-Message-Id	header	string	Optional	Replay a previously generated SSE stream under the original API key and identical request body. This request does not dispatch or bill the provider. Cache retention is 10 minutes and total output is limited to 4 MiB; interrupted generations require a new message ID for continuation.
X-Resume-From-Offset	header	integer	Optional	Number of complete SSE events already consumed, matching the last SSE id. Starts at 0; UTF-8 bytes, tokens and characters are not valid units. Takes precedence over Last-Event-ID.
Last-Event-ID	header	integer	Optional	Alternative complete SSE event offset when X-Resume-From-Offset is absent.

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "prompt": "Once upon a time"
}

Responses

200OK

application/json

Example

{
  "id": "cmpl_example",
  "object": "text_completion",
  "choices": [
    {
      "index": 0,
      "text": " there was a quiet coast."
    }
  ]
}

POST /openai/v1/completions

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/openai/v1/completions' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "prompt": "Once upon a time"
}'

Authentication

Parameters

Name	Location	Type	Required	Description
X-Client-Message-Id	header	string	Optional	Opt in to durable tenant-scoped execution deduplication. Reuse only with the identical request body and API key. Completed or possibly dispatched requests never expire into another execution, including after Redis loss. Upstream errors or settlement rollback after dispatch require a new message ID for another execution; failures before dispatch may retry the same ID.
X-Resume-Message-Id	header	string	Optional	Replay a previously generated SSE stream under the original API key and identical request body. This request does not dispatch or bill the provider. Cache retention is 10 minutes and total output is limited to 4 MiB; interrupted generations require a new message ID for continuation.
X-Resume-From-Offset	header	integer	Optional	Number of complete SSE events already consumed, matching the last SSE id. Starts at 0; UTF-8 bytes, tokens and characters are not valid units. Takes precedence over Last-Event-ID.
Last-Event-ID	header	integer	Optional	Alternative complete SSE event offset when X-Resume-From-Offset is absent.

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "prompt": "Once upon a time"
}

Responses

200OK

application/json

Example

{
  "id": "cmpl_example",
  "object": "text_completion",
  "choices": [
    {
      "index": 0,
      "text": " there was a quiet coast."
    }
  ]
}

Embeddings

2 endpoints

Create vector embeddings from text input.

POST /v1/embeddings

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/embeddings' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "input": "A calm ocean at dawn"
}'

Authentication

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "input": "A calm ocean at dawn"
}

Responses

200OK

application/json

Example

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        0.012,
        -0.008,
        0.021
      ]
    }
  ]
}

POST /openai/v1/embeddings

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/openai/v1/embeddings' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "input": "A calm ocean at dawn"
}'

Authentication

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "input": "A calm ocean at dawn"
}

Responses

200OK

application/json

Example

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        0.012,
        -0.008,
        0.021
      ]
    }
  ]
}

Moderations

2 endpoints

Classify potentially harmful text or image input.

POST /v1/moderations

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/moderations' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "input": "Text to classify"
}'

Authentication

Request body

Required

application/json

Example

{
  "input": "Text to classify"
}

Responses

200OK

application/json

Example

{
  "id": "modr_example",
  "model": "your-model-id",
  "results": [
    {
      "flagged": false,
      "categories": {},
      "category_scores": {}
    }
  ]
}

POST /openai/v1/moderations

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/openai/v1/moderations' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "input": "Text to classify"
}'

Authentication

Request body

Required

application/json

Example

{
  "input": "Text to classify"
}

Responses

200OK

application/json

Example

{
  "id": "modr_example",
  "model": "your-model-id",
  "results": [
    {
      "flagged": false,
      "categories": {},
      "category_scores": {}
    }
  ]
}

Batches

8 endpoints

Submit provider-native JSONL batches when object storage is enabled for the deployment.

GET /v1/batches

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/batches' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
after	query	string	Optional	—
limit	query	integer	Optional	—`Example: 20`

Responses

200OK

application/json

Example

{
  "object": "list",
  "data": [
    {
      "id": "batch_example",
      "object": "batch",
      "endpoint": "/v1/chat/completions",
      "input_file_id": "file_example",
      "completion_window": "24h",
      "status": "in_progress",
      "created_at": 1700000000,
      "request_counts": {
        "total": 100,
        "completed": 0,
        "failed": 0
      }
    }
  ],
  "first_id": "batch_example",
  "last_id": "batch_example",
  "has_more": false
}

Native prepaid batches validate the stored file checksum and strict JSONL before funding. Every item needs a server-owned execution policy for its pinned route and price, including file-upload and batch-create transport bounds. All item reservations commit atomically before provider submission; insufficient aggregate funds return HTTP 402 without submitting a partial batch. Incompatible provider configurations must be split into separate batches. Each submission permits one file upload and one batch create; an ambiguous submission returns batch_submission_recovery_required and retains funding without automatic resubmission. Failed, cancelled or missing item results do not prove zero provider cost and retain funding for reconciliation.

POST /v1/batches

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/batches' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "input_file_id": "file_example",
  "endpoint": "/v1/chat/completions",
  "completion_window": "24h"
}'

Authentication

Request body

Required

application/json

Example

{
  "input_file_id": "file_example",
  "endpoint": "/v1/chat/completions",
  "completion_window": "24h"
}

Responses

200OK

application/json

Example

{
  "id": "batch_example",
  "object": "batch",
  "endpoint": "/v1/chat/completions",
  "input_file_id": "file_example",
  "completion_window": "24h",
  "status": "in_progress",
  "created_at": 1700000000,
  "request_counts": {
    "total": 100,
    "completed": 0,
    "failed": 0
  }
}

GET /openai/v1/batches

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/openai/v1/batches' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
after	query	string	Optional	—
limit	query	integer	Optional	—`Example: 20`

Responses

200OK

application/json

Example

{
  "object": "list",
  "data": [
    {
      "id": "batch_example",
      "object": "batch",
      "endpoint": "/v1/chat/completions",
      "input_file_id": "file_example",
      "completion_window": "24h",
      "status": "in_progress",
      "created_at": 1700000000,
      "request_counts": {
        "total": 100,
        "completed": 0,
        "failed": 0
      }
    }
  ],
  "first_id": "batch_example",
  "last_id": "batch_example",
  "has_more": false
}

POST /openai/v1/batches

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/openai/v1/batches' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "input_file_id": "file_example",
  "endpoint": "/v1/chat/completions",
  "completion_window": "24h"
}'

Authentication

Request body

Required

application/json

Example

{
  "input_file_id": "file_example",
  "endpoint": "/v1/chat/completions",
  "completion_window": "24h"
}

Responses

200OK

application/json

Example

{
  "id": "batch_example",
  "object": "batch",
  "endpoint": "/v1/chat/completions",
  "input_file_id": "file_example",
  "completion_window": "24h",
  "status": "in_progress",
  "created_at": 1700000000,
  "request_counts": {
    "total": 100,
    "completed": 0,
    "failed": 0
  }
}

GET /v1/batches/{batch_id}

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/batches/<batch_id>' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
batch_id	path	string	Required	—

Responses

200OK

application/json

Example

{
  "id": "batch_example",
  "object": "batch",
  "endpoint": "/v1/chat/completions",
  "input_file_id": "file_example",
  "completion_window": "24h",
  "status": "in_progress",
  "created_at": 1700000000,
  "request_counts": {
    "total": 100,
    "completed": 0,
    "failed": 0
  }
}

GET /openai/v1/batches/{batch_id}

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/openai/v1/batches/<batch_id>' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
batch_id	path	string	Required	—

Responses

200OK

application/json

Example

{
  "id": "batch_example",
  "object": "batch",
  "endpoint": "/v1/chat/completions",
  "input_file_id": "file_example",
  "completion_window": "24h",
  "status": "in_progress",
  "created_at": 1700000000,
  "request_counts": {
    "total": 100,
    "completed": 0,
    "failed": 0
  }
}

POST /v1/batches/{batch_id}/cancel

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/batches/<batch_id>/cancel' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
batch_id	path	string	Required	—

Responses

200OK

application/json

Example

{
  "id": "batch_example",
  "object": "batch",
  "endpoint": "/v1/chat/completions",
  "input_file_id": "file_example",
  "completion_window": "24h",
  "status": "in_progress",
  "created_at": 1700000000,
  "request_counts": {
    "total": 100,
    "completed": 0,
    "failed": 0
  }
}

POST /openai/v1/batches/{batch_id}/cancel

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/openai/v1/batches/<batch_id>/cancel' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
batch_id	path	string	Required	—

Responses

200OK

application/json

Example

{
  "id": "batch_example",
  "object": "batch",
  "endpoint": "/v1/chat/completions",
  "input_file_id": "file_example",
  "completion_window": "24h",
  "status": "in_progress",
  "created_at": 1700000000,
  "request_counts": {
    "total": 100,
    "completed": 0,
    "failed": 0
  }
}

Files

5 endpoints

Upload, list, inspect, and download files.

GET /openai/v1/files

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/openai/v1/files' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Responses

200OK

application/json

Example

{
  "object": "list",
  "data": [
    {
      "id": "file_example",
      "object": "file",
      "bytes": 128,
      "created_at": 1700000000,
      "filename": "document.jsonl",
      "purpose": "batch",
      "status": "processed"
    }
  ]
}

Applies API key IP and requests-per-minute policies before storing content. Uploads are model-independent and do not consume inference quotas. Files expire 30 days after upload unless expires_after sets a shorter lifetime (1 hour to 30 days); expired files are no longer listed or downloadable and are purged. Each tenant may keep at most 10,000 active files totalling 10 GiB.

POST /openai/v1/files

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/openai/v1/files' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --form 'file=@path/to/document.jsonl' \
  --form 'purpose=batch'

Authentication

Request body

Required

multipart/form-data

Example

{
  "file": "document.jsonl",
  "purpose": "batch"
}

Responses

200OK

application/json

Example

{
  "id": "file_example",
  "object": "file",
  "bytes": 128,
  "created_at": 1700000000,
  "filename": "document.jsonl",
  "purpose": "batch",
  "status": "processed"
}

GET /openai/v1/files/{file_id}

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/openai/v1/files/<file_id>' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
file_id	path	string	Required	—

Responses

200OK

application/json

Example

{
  "id": "file_example",
  "object": "file",
  "bytes": 128,
  "created_at": 1700000000,
  "filename": "document.jsonl",
  "purpose": "batch",
  "status": "processed"
}

DELETE /openai/v1/files/{file_id}

Request example

cURL

curl \
  --request DELETE \
  --url 'https://api.anyint.ai/openai/v1/files/<file_id>' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
file_id	path	string	Required	—

Responses

200OK

application/json

Example

{
  "id": "file_example",
  "object": "file",
  "deleted": true
}

GET /openai/v1/files/{file_id}/content

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/openai/v1/files/<file_id>/content' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/octet-stream'

Authentication

Parameters

Name	Location	Type	Required	Description
file_id	path	string	Required	—

Responses

200Binary file content

application/octet-stream

Example

<binary>

Audio

3 endpoints

Transcribe audio, translate audio to English, or synthesize speech.

Native prepaid organizations reserve the greater of customer and provider maximum costs before audio provider dispatch. A missing or mismatched server-owned execution bound returns non-retryable HTTP 503 prepaid_execution_bound_unavailable. Multipart bounds include file sizes and content hashes. Insufficient funds return HTTP 402. Successful responses require the configured billable usage; missing required usage returns HTTP 502 and retains funding. Provider errors or unknown outcomes retain funding for audited recovery. Personal and postpaid audio behavior is preserved.

POST /openai/v1/audio/transcriptions

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/openai/v1/audio/transcriptions' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --form 'file=@path/to/audio.wav' \
  --form 'model=your-model-id'

Authentication

Request body

Required

multipart/form-data

Example

{
  "file": "audio.wav",
  "model": "your-model-id"
}

Responses

200OK

application/json

Example

{
  "text": "Example transcript."
}

POST /openai/v1/audio/translations

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/openai/v1/audio/translations' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --form 'file=@path/to/audio.wav' \
  --form 'model=your-model-id'

Authentication

Request body

Required

multipart/form-data

Example

{
  "file": "audio.wav",
  "model": "your-model-id"
}

Responses

200OK

application/json

Example

{
  "text": "Example transcript."
}

POST /openai/v1/audio/speech

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/openai/v1/audio/speech' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: audio/mpeg' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "voice": "your-voice-id",
  "input": "Welcome to AnyInt Gateway."
}'

Authentication

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "voice": "your-voice-id",
  "input": "Welcome to AnyInt Gateway."
}

Responses

200Binary audio content

audio/mpeg

Example

<binary>

Images

4 endpoints

Generate and edit images with OpenAI-compatible requests.

POST /v1/images/edits

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/images/edits' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --form 'image=@path/to/image.png' \
  --form 'model=your-model-id' \
  --form 'prompt=Add a soft blue background.'

Authentication

Request body

Required

multipart/form-data

Example

{
  "image": "image.png",
  "model": "your-model-id",
  "prompt": "Add a soft blue background."
}

Responses

200OK

application/json

Example

{
  "created": 1700000000,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAAB"
    }
  ]
}

POST /openai/v1/images/edits

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/openai/v1/images/edits' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --form 'image=@path/to/image.png' \
  --form 'model=your-model-id' \
  --form 'prompt=Add a soft blue background.'

Authentication

Request body

Required

multipart/form-data

Example

{
  "image": "image.png",
  "model": "your-model-id",
  "prompt": "Add a soft blue background."
}

Responses

200OK

application/json

Example

{
  "created": 1700000000,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAAB"
    }
  ]
}

POST /v1/images/generations

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/images/generations' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "prompt": "A minimal paper sculpture of a cloud",
  "n": 1
}'

Authentication

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "prompt": "A minimal paper sculpture of a cloud",
  "n": 1
}

Responses

200OK

application/json

Example

{
  "created": 1700000000,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAAB"
    }
  ]
}

POST /openai/v1/images/generations

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/openai/v1/images/generations' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "prompt": "A minimal paper sculpture of a cloud",
  "n": 1
}'

Authentication

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "prompt": "A minimal paper sculpture of a cloud",
  "n": 1
}

Responses

200OK

application/json

Example

{
  "created": 1700000000,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAAAAEAAAAB"
    }
  ]
}

Models

4 endpoints

Discover models available through each protocol.

GET /openai/v1/models

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/openai/v1/models' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Responses

200OK

application/json

Example

{
  "object": "list",
  "data": [
    {
      "id": "your-model-id",
      "object": "model",
      "created": 1767225600,
      "owned_by": "configured-provider"
    }
  ]
}

GET /v1/models

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/models' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Responses

200OK

application/json

Example

{
  "object": "list",
  "data": [
    {
      "id": "your-model-id",
      "object": "model",
      "created": 1767225600,
      "owned_by": "configured-provider"
    }
  ]
}

GET /anthropic/v1/models

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/anthropic/v1/models' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Responses

200OK

application/json

Example

{
  "data": [
    {
      "id": "your-model-id",
      "type": "model",
      "display_name": "Configured model",
      "created_at": "2026-01-01T00:00:00.000Z"
    }
  ],
  "has_more": false,
  "first_id": "your-model-id",
  "last_id": "your-model-id"
}

GET /gemini/v1beta/models

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/gemini/v1beta/models' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Responses

200OK

application/json

Example

{
  "models": [
    {
      "name": "models/your-model-id",
      "displayName": "Configured model",
      "supportedGenerationMethods": [
        "generateContent"
      ],
      "inputTokenLimit": 8192,
      "outputTokenLimit": 8192
    }
  ]
}

Async Media

23 endpoints

Create and inspect asynchronous image, video, and music jobs.

Seedance accepts active image and video asset:// references, including mixed reference_image and reference_video content. Each reference must belong to the enterprise's current asset library. Incompatible library references return HTTP 400 authorized_asset_provider_mismatch, retryable=false and user_action=simplify_input before routing, task creation or upstream submission. Register the referenced images and videos in the current library and update their references before retrying.

POST /v1/videos

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/videos' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-name",
  "prompt": "A calm landscape",
  "duration_seconds": 5
}'

Authentication

Request body

Required

application/json

Example

{
  "model": "your-model-name",
  "prompt": "A calm landscape",
  "duration_seconds": 5
}

Responses

200Duplicate task

application/json

Example

{
  "id": "task_example",
  "taskId": "task_example",
  "object": "video",
  "status": "queued",
  "created_at": 0
}

GET /v1/videos/{task_id}

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/videos/<task_id>' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
task_id	path	string	Required	—

Responses

200OK

application/json

Example

{
  "id": "task_example",
  "taskId": "task_example",
  "object": "video",
  "status": "queued",
  "created_at": 0
}

GET /v1/videos/{task_id}/content

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/videos/<task_id>/content' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/octet-stream'

Authentication

Parameters

Name	Location	Type	Required	Description
task_id	path	string	Required	—

Responses

200Generated media

application/octet-stream

Example

<binary>

POST /openai/v1/videos

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/openai/v1/videos' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-name",
  "prompt": "A calm landscape",
  "duration_seconds": 5
}'

Authentication

Request body

Required

application/json

Example

{
  "model": "your-model-name",
  "prompt": "A calm landscape",
  "duration_seconds": 5
}

Responses

200Duplicate task

application/json

Example

{
  "id": "task_example",
  "taskId": "task_example",
  "object": "video",
  "status": "queued",
  "created_at": 0
}

GET /openai/v1/videos/{task_id}

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/openai/v1/videos/<task_id>' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
task_id	path	string	Required	—

Responses

200OK

application/json

Example

{
  "id": "task_example",
  "taskId": "task_example",
  "object": "video",
  "status": "queued",
  "created_at": 0
}

GET /openai/v1/videos/{task_id}/content

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/openai/v1/videos/<task_id>/content' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/octet-stream'

Authentication

Parameters

Name	Location	Type	Required	Description
task_id	path	string	Required	—

Responses

200Generated media

application/octet-stream

Example

<binary>

POST /v1/audio/generations

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/audio/generations' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-name",
  "prompt": "A calm landscape",
  "duration_seconds": 5
}'

Authentication

Request body

Required

application/json

Example

{
  "model": "your-model-name",
  "prompt": "A calm landscape",
  "duration_seconds": 5
}

Responses

200Duplicate task

application/json

Example

{
  "id": "task_example",
  "taskId": "task_example",
  "object": "audio",
  "status": "queued",
  "created_at": 0
}

GET /v1/audio/generations/{task_id}

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/audio/generations/<task_id>' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
task_id	path	string	Required	—

Responses

200OK

application/json

Example

{
  "id": "task_example",
  "taskId": "task_example",
  "object": "audio",
  "status": "queued",
  "created_at": 0
}

GET /v1/audio/generations/{task_id}/content

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/audio/generations/<task_id>/content' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/octet-stream'

Authentication

Parameters

Name	Location	Type	Required	Description
task_id	path	string	Required	—

Responses

200Generated media

application/octet-stream

Example

<binary>

POST /openai/v1/audio/generations

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/openai/v1/audio/generations' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-name",
  "prompt": "A calm landscape",
  "duration_seconds": 5
}'

Authentication

Request body

Required

application/json

Example

{
  "model": "your-model-name",
  "prompt": "A calm landscape",
  "duration_seconds": 5
}

Responses

200Duplicate task

application/json

Example

{
  "id": "task_example",
  "taskId": "task_example",
  "object": "audio",
  "status": "queued",
  "created_at": 0
}

GET /openai/v1/audio/generations/{task_id}

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/openai/v1/audio/generations/<task_id>' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
task_id	path	string	Required	—

Responses

200OK

application/json

Example

{
  "id": "task_example",
  "taskId": "task_example",
  "object": "audio",
  "status": "queued",
  "created_at": 0
}

GET /openai/v1/audio/generations/{task_id}/content

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/openai/v1/audio/generations/<task_id>/content' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/octet-stream'

Authentication

Parameters

Name	Location	Type	Required	Description
task_id	path	string	Required	—

Responses

200Generated media

application/octet-stream

Example

<binary>

POST /v1/async-tasks/image-generations

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/async-tasks/image-generations' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "prompt": "A minimal paper sculpture of a cloud"
}'

Authentication

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "prompt": "A minimal paper sculpture of a cloud"
}

Responses

200Duplicate async task

application/json

Example

{
  "object": "async_task",
  "task": {
    "id": "task_example",
    "requestId": "req_example",
    "tenantId": "tenant_example",
    "protocol": "openai",
    "taskType": "image_generation",
    "status": "submitted",
    "input": {
      "prompt": "Example prompt"
    },
    "artifacts": [],
    "artifactCount": 0,
    "artifact_count": 0,
    "billingSessions": [],
    "billing_sessions": [],
    "createdAt": "2026-01-01T00:00:00.000Z",
    "updatedAt": "2026-01-01T00:00:00.000Z"
  },
  "anyint": {
    "request_id": "req_example",
    "route_decision_id": "route_example"
  },
  "duplicate": true
}

POST /v1/async-tasks/video-generations

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/async-tasks/video-generations' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "prompt": "Slow aerial movement over a quiet coast",
  "duration_seconds": 6,
  "fps": 24
}'

Authentication

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "prompt": "Slow aerial movement over a quiet coast",
  "duration_seconds": 6,
  "fps": 24
}

Responses

200Duplicate async task

application/json

Example

{
  "object": "async_task",
  "task": {
    "id": "task_example",
    "requestId": "req_example",
    "tenantId": "tenant_example",
    "protocol": "openai",
    "taskType": "video_generation",
    "status": "submitted",
    "input": {
      "prompt": "Example prompt"
    },
    "artifacts": [],
    "artifactCount": 0,
    "artifact_count": 0,
    "billingSessions": [],
    "billing_sessions": [],
    "createdAt": "2026-01-01T00:00:00.000Z",
    "updatedAt": "2026-01-01T00:00:00.000Z"
  },
  "anyint": {
    "request_id": "req_example",
    "route_decision_id": "route_example"
  },
  "duplicate": true
}

POST /v1/videos/generations

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/videos/generations' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "prompt": "Slow aerial movement over a quiet coast",
  "duration_seconds": 6,
  "fps": 24
}'

Authentication

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "prompt": "Slow aerial movement over a quiet coast",
  "duration_seconds": 6,
  "fps": 24
}

Responses

200Duplicate task

application/json

Example

{
  "object": "async_task",
  "task": {
    "id": "task_example",
    "requestId": "req_example",
    "tenantId": "tenant_example",
    "protocol": "openai",
    "taskType": "video_generation",
    "status": "submitted",
    "input": {
      "prompt": "Example prompt"
    },
    "artifacts": [],
    "artifactCount": 0,
    "artifact_count": 0,
    "billingSessions": [],
    "billing_sessions": [],
    "createdAt": "2026-01-01T00:00:00.000Z",
    "updatedAt": "2026-01-01T00:00:00.000Z"
  },
  "anyint": {
    "request_id": "req_example",
    "route_decision_id": "route_example"
  },
  "duplicate": true
}

POST /v1/async-tasks/music-generations

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/async-tasks/music-generations' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "prompt": "Warm ambient music with soft piano",
  "duration_seconds": 30
}'

Authentication

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "prompt": "Warm ambient music with soft piano",
  "duration_seconds": 30
}

Responses

200Duplicate async task

application/json

Example

{
  "object": "async_task",
  "task": {
    "id": "task_example",
    "requestId": "req_example",
    "tenantId": "tenant_example",
    "protocol": "openai",
    "taskType": "music_generation",
    "status": "submitted",
    "input": {
      "prompt": "Example prompt"
    },
    "artifacts": [],
    "artifactCount": 0,
    "artifact_count": 0,
    "billingSessions": [],
    "billing_sessions": [],
    "createdAt": "2026-01-01T00:00:00.000Z",
    "updatedAt": "2026-01-01T00:00:00.000Z"
  },
  "anyint": {
    "request_id": "req_example",
    "route_decision_id": "route_example"
  },
  "duplicate": true
}

POST /v1/music/generations

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/music/generations' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "prompt": "Warm ambient music with soft piano",
  "duration_seconds": 30
}'

Authentication

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "prompt": "Warm ambient music with soft piano",
  "duration_seconds": 30
}

Responses

200Duplicate task

application/json

Example

{
  "object": "async_task",
  "task": {
    "id": "task_example",
    "requestId": "req_example",
    "tenantId": "tenant_example",
    "protocol": "openai",
    "taskType": "music_generation",
    "status": "submitted",
    "input": {
      "prompt": "Example prompt"
    },
    "artifacts": [],
    "artifactCount": 0,
    "artifact_count": 0,
    "billingSessions": [],
    "billing_sessions": [],
    "createdAt": "2026-01-01T00:00:00.000Z",
    "updatedAt": "2026-01-01T00:00:00.000Z"
  },
  "anyint": {
    "request_id": "req_example",
    "route_decision_id": "route_example"
  },
  "duplicate": true
}

GET /v1/async-tasks

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/async-tasks' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Responses

200OK

application/json

Example

{
  "object": "list",
  "data": [
    {
      "id": "task_example",
      "requestId": "req_example",
      "tenantId": "tenant_example",
      "protocol": "openai",
      "taskType": "image_generation",
      "status": "queued",
      "input": {
        "prompt": "Example prompt"
      },
      "artifacts": [],
      "artifactCount": 0,
      "artifact_count": 0,
      "billingSessions": [],
      "billing_sessions": [],
      "createdAt": "2026-01-01T00:00:00.000Z",
      "updatedAt": "2026-01-01T00:00:00.000Z"
    }
  ]
}

GET /v1/async-tasks/{task_id}

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/async-tasks/<task_id>' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
task_id	path	string	Required	—

Responses

200OK

application/json

Example

{
  "object": "async_task",
  "task": {
    "id": "task_example",
    "requestId": "req_example",
    "tenantId": "tenant_example",
    "protocol": "openai",
    "taskType": "image_generation",
    "status": "queued",
    "input": {
      "prompt": "Example prompt"
    },
    "artifacts": [],
    "artifactCount": 0,
    "artifact_count": 0,
    "billingSessions": [],
    "billing_sessions": [],
    "createdAt": "2026-01-01T00:00:00.000Z",
    "updatedAt": "2026-01-01T00:00:00.000Z"
  }
}

GET /v1/tasks/{task_id}

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/tasks/<task_id>' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
task_id	path	string	Required	—

Responses

200OK

application/json

Example

{
  "object": "generation_task",
  "task": {
    "id": "task_example",
    "requestId": "req_example",
    "tenantId": "tenant_example",
    "protocol": "openai",
    "taskType": "image_generation",
    "status": "queued",
    "input": {
      "prompt": "Example prompt"
    },
    "artifacts": [],
    "artifactCount": 0,
    "artifact_count": 0,
    "billingSessions": [],
    "billing_sessions": [],
    "createdAt": "2026-01-01T00:00:00.000Z",
    "updatedAt": "2026-01-01T00:00:00.000Z"
  }
}

POST /v1/tasks/{task_id}/cancel

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/tasks/<task_id>/cancel' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
task_id	path	string	Required	—

Responses

200OK

application/json

Example

{
  "object": "generation_task",
  "task": {
    "id": "task_example",
    "requestId": "req_example",
    "tenantId": "tenant_example",
    "protocol": "openai",
    "taskType": "image_generation",
    "status": "queued",
    "input": {
      "prompt": "Example prompt"
    },
    "artifacts": [],
    "artifactCount": 0,
    "artifact_count": 0,
    "billingSessions": [],
    "billing_sessions": [],
    "createdAt": "2026-01-01T00:00:00.000Z",
    "updatedAt": "2026-01-01T00:00:00.000Z"
  }
}

POST /v1/async-tasks/{task_id}/cancel

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/async-tasks/<task_id>/cancel' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
task_id	path	string	Required	—

Responses

200OK

application/json

Example

{
  "object": "generation_task",
  "task": {
    "id": "task_example",
    "requestId": "req_example",
    "tenantId": "tenant_example",
    "protocol": "openai",
    "taskType": "image_generation",
    "status": "queued",
    "input": {
      "prompt": "Example prompt"
    },
    "artifacts": [],
    "artifactCount": 0,
    "artifact_count": 0,
    "billingSessions": [],
    "billing_sessions": [],
    "createdAt": "2026-01-01T00:00:00.000Z",
    "updatedAt": "2026-01-01T00:00:00.000Z"
  }
}

GET /v1/async-tasks/{task_id}/artifacts/{artifact_id}

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/async-tasks/<task_id>/artifacts/<artifact_id>?tenant_id=<tenant_id>&expires_at=<expires_at>&signature=<signature>' \
  --header 'Accept: application/octet-stream'

Authentication

No authentication required

Parameters

Name	Location	Type	Required	Description
task_id	path	string	Required	—
artifact_id	path	string	Required	—
tenant_id	query	string	Required	—
expires_at	query	integer	Required	—
signature	query	string	Required	—

Responses

200Binary artifact content

application/octet-stream

Example

<binary>

Authorized Assets

5 endpoints

Management is scoped to the registering API key's user within the enterprise, including that user's other keys. Keys without a user owner manage only their own registrations. Unknown ownership is not manageable. Other users' assets return 404. Listing includes only the enterprise's current asset library. Earlier-library assets remain readable by ID, but retry and generation require registration in the current library. Active asset:// generation references retain enterprise scope.

GET /v1/seedance/assets

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/seedance/assets' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Responses

200OK

application/json

Example

{
  "items": [
    {
      "id": "asset_example",
      "fileObjectId": null,
      "displayName": "Portrait reference",
      "libraryType": "virtual_portrait",
      "assetType": "image",
      "status": "ACTIVE",
      "assetUri": "asset://provider_asset_example",
      "errorCode": null,
      "errorMessage": null,
      "providerGroupId": null,
      "sourceUrlExpiresAt": null,
      "createdAt": "2026-01-01T00:00:00.000Z",
      "updatedAt": "2026-01-01T00:00:00.000Z"
    }
  ]
}

POST /v1/seedance/assets

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/seedance/assets' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "sourceUrl": "https://cdn.example.com/portrait.png",
  "displayName": "Portrait reference",
  "assetType": "image"
}'

Authentication

Request body

Required

application/json

Example

{
  "sourceUrl": "https://cdn.example.com/portrait.png",
  "displayName": "Portrait reference",
  "assetType": "image"
}

Responses

201Registered

application/json

Example

{
  "id": "asset_example",
  "fileObjectId": null,
  "displayName": "Portrait reference",
  "libraryType": "virtual_portrait",
  "assetType": "image",
  "status": "ACTIVE",
  "assetUri": "asset://provider_asset_example",
  "errorCode": null,
  "errorMessage": null,
  "providerGroupId": null,
  "sourceUrlExpiresAt": null,
  "createdAt": "2026-01-01T00:00:00.000Z",
  "updatedAt": "2026-01-01T00:00:00.000Z"
}

GET /v1/seedance/assets/{asset_id}

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/seedance/assets/<asset_id>' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
asset_id	path	string	Required	—

Responses

200OK

application/json

Example

{
  "id": "asset_example",
  "fileObjectId": null,
  "displayName": "Portrait reference",
  "libraryType": "virtual_portrait",
  "assetType": "image",
  "status": "ACTIVE",
  "assetUri": "asset://provider_asset_example",
  "errorCode": null,
  "errorMessage": null,
  "providerGroupId": null,
  "sourceUrlExpiresAt": null,
  "createdAt": "2026-01-01T00:00:00.000Z",
  "updatedAt": "2026-01-01T00:00:00.000Z"
}

DELETE /v1/seedance/assets/{asset_id}

Request example

cURL

curl \
  --request DELETE \
  --url 'https://api.anyint.ai/v1/seedance/assets/<asset_id>' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>'

Authentication

Parameters

Name	Location	Type	Required	Description
asset_id	path	string	Required	—

Responses

204Deleted

POST /v1/seedance/assets/{asset_id}/retry

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/v1/seedance/assets/<asset_id>/retry' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "sourceUrl": "https://cdn.example.com/portrait.png"
}'

Authentication

Parameters

Name	Location	Type	Required	Description
asset_id	path	string	Required	—

Request body

Required

application/json

Example

{
  "sourceUrl": "https://cdn.example.com/portrait.png"
}

Responses

200Retried

application/json

Example

{
  "id": "asset_example",
  "fileObjectId": null,
  "displayName": "Portrait reference",
  "libraryType": "virtual_portrait",
  "assetType": "image",
  "status": "ACTIVE",
  "assetUri": "asset://provider_asset_example",
  "errorCode": null,
  "errorMessage": null,
  "providerGroupId": null,
  "sourceUrlExpiresAt": null,
  "createdAt": "2026-01-01T00:00:00.000Z",
  "updatedAt": "2026-01-01T00:00:00.000Z"
}

Anthropic Messages

2 endpoints

Use Anthropic-native messages, token counting, and model discovery.

When billing is enabled, built-in web search declared in tools or Responses input.additional_tools requires a compiled price rule covering web_search_queries and the request dimensions. Namespace tool declarations are checked without treating client functions as built-in search. Missing coverage returns HTTP 503 search_tool_pricing_not_configured before initial funding reservation; each actual candidate, including fallback and supply-tier routes, is checked again before provider dispatch. Client function tools are unaffected.

POST /anthropic/v1/messages

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/anthropic/v1/messages' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "max_tokens": 256,
  "messages": [
    {
      "role": "user",
      "content": "Explain edge computing briefly."
    }
  ]
}'

Authentication

Parameters

Name	Location	Type	Required	Description
X-Client-Message-Id	header	string	Optional	Opt in to durable tenant-scoped execution deduplication. Reuse only with the identical request body and API key. Completed or possibly dispatched requests never expire into another execution, including after Redis loss. Upstream errors or settlement rollback after dispatch require a new message ID for another execution; failures before dispatch may retry the same ID.
X-Resume-Message-Id	header	string	Optional	Replay a previously generated SSE stream under the original API key and identical request body. This request does not dispatch or bill the provider. Cache retention is 10 minutes and total output is limited to 4 MiB; interrupted generations require a new message ID for continuation.
X-Resume-From-Offset	header	integer	Optional	Number of complete SSE events already consumed, matching the last SSE id. Starts at 0; UTF-8 bytes, tokens and characters are not valid units. Takes precedence over Last-Event-ID.
Last-Event-ID	header	integer	Optional	Alternative complete SSE event offset when X-Resume-From-Offset is absent.

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "max_tokens": 256,
  "messages": [
    {
      "role": "user",
      "content": "Explain edge computing briefly."
    }
  ]
}

Responses

200OK

application/json

Example

{
  "id": "msg_example",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Edge computing runs workloads near the data source."
    }
  ]
}

POST /anthropic/v1/messages/count_tokens

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/anthropic/v1/messages/count_tokens' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-id",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

Authentication

Request body

Required

application/json

Example

{
  "model": "your-model-id",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}

Responses

200OK

application/json

Example

{
  "input_tokens": 12
}

Gemini Content

4 endpoints

Use Gemini-native content generation and streaming.

Gemini 4 Argon on the Gemini Developer API supports Standard inference only. Omit serviceTier/service_tier or set it to standard; other values return HTTP 400 before upstream dispatch. When billing is enabled, built-in web search declared in tools or Responses input.additional_tools requires a compiled price rule covering web_search_queries and the request dimensions. Namespace tool declarations are checked without treating client functions as built-in search. Missing coverage returns HTTP 503 search_tool_pricing_not_configured before initial funding reservation; each actual candidate, including fallback and supply-tier routes, is checked again before provider dispatch. Client function tools are unaffected.

POST /gemini/v1beta/models/{model}:generateContent

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/gemini/v1beta/models/<model>:generateContent' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "contents": [
    {
      "parts": [
        {
          "text": "Explain edge computing briefly."
        }
      ]
    }
  ]
}'

Authentication

Parameters

Name	Location	Type	Required	Description
model	path	string	Required	—
X-Client-Message-Id	header	string	Optional	Opt in to durable tenant-scoped execution deduplication. Reuse only with the identical request body and API key. Completed or possibly dispatched requests never expire into another execution, including after Redis loss. Upstream errors or settlement rollback after dispatch require a new message ID for another execution; failures before dispatch may retry the same ID.
X-Resume-Message-Id	header	string	Optional	Replay a previously generated SSE stream under the original API key and identical request body. This request does not dispatch or bill the provider. Cache retention is 10 minutes and total output is limited to 4 MiB; interrupted generations require a new message ID for continuation.
X-Resume-From-Offset	header	integer	Optional	Number of complete SSE events already consumed, matching the last SSE id. Starts at 0; UTF-8 bytes, tokens and characters are not valid units. Takes precedence over Last-Event-ID.
Last-Event-ID	header	integer	Optional	Alternative complete SSE event offset when X-Resume-From-Offset is absent.

Request body

Required

application/json

Example

{
  "contents": [
    {
      "parts": [
        {
          "text": "Explain edge computing briefly."
        }
      ]
    }
  ]
}

Responses

200OK

application/json

Example

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "Edge computing reduces latency."
          }
        ]
      }
    }
  ]
}

POST /gemini/v1beta/models/{model}:streamGenerateContent

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/gemini/v1beta/models/<model>:streamGenerateContent' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: text/event-stream' \
  --header 'Content-Type: application/json' \
  --data '{
  "contents": [
    {
      "parts": [
        {
          "text": "Explain edge computing briefly."
        }
      ]
    }
  ]
}'

Authentication

Parameters

Name	Location	Type	Required	Description
model	path	string	Required	—
alt	query	string	Optional	—
X-Client-Message-Id	header	string	Optional	Opt in to durable tenant-scoped execution deduplication. Reuse only with the identical request body and API key. Completed or possibly dispatched requests never expire into another execution, including after Redis loss. Upstream errors or settlement rollback after dispatch require a new message ID for another execution; failures before dispatch may retry the same ID.
X-Resume-Message-Id	header	string	Optional	Replay a previously generated SSE stream under the original API key and identical request body. This request does not dispatch or bill the provider. Cache retention is 10 minutes and total output is limited to 4 MiB; interrupted generations require a new message ID for continuation.
X-Resume-From-Offset	header	integer	Optional	Number of complete SSE events already consumed, matching the last SSE id. Starts at 0; UTF-8 bytes, tokens and characters are not valid units. Takes precedence over Last-Event-ID.
Last-Event-ID	header	integer	Optional	Alternative complete SSE event offset when X-Resume-From-Offset is absent.

Request body

Required

application/json

Example

{
  "contents": [
    {
      "parts": [
        {
          "text": "Explain edge computing briefly."
        }
      ]
    }
  ]
}

Responses

200Gemini content stream

text/event-stream

Example

data: {"candidates":[{"content":{"role":"model","parts":[{"text":"Edge computing reduces latency."}]}}]}

POST /gemini/v1beta/models/{model}/generateContent

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/gemini/v1beta/models/<model>/generateContent' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
  "contents": [
    {
      "parts": [
        {
          "text": "Explain edge computing briefly."
        }
      ]
    }
  ]
}'

Authentication

Parameters

Name	Location	Type	Required	Description
model	path	string	Required	—
X-Client-Message-Id	header	string	Optional	Opt in to durable tenant-scoped execution deduplication. Reuse only with the identical request body and API key. Completed or possibly dispatched requests never expire into another execution, including after Redis loss. Upstream errors or settlement rollback after dispatch require a new message ID for another execution; failures before dispatch may retry the same ID.
X-Resume-Message-Id	header	string	Optional	Replay a previously generated SSE stream under the original API key and identical request body. This request does not dispatch or bill the provider. Cache retention is 10 minutes and total output is limited to 4 MiB; interrupted generations require a new message ID for continuation.
X-Resume-From-Offset	header	integer	Optional	Number of complete SSE events already consumed, matching the last SSE id. Starts at 0; UTF-8 bytes, tokens and characters are not valid units. Takes precedence over Last-Event-ID.
Last-Event-ID	header	integer	Optional	Alternative complete SSE event offset when X-Resume-From-Offset is absent.

Request body

Required

application/json

Example

{
  "contents": [
    {
      "parts": [
        {
          "text": "Explain edge computing briefly."
        }
      ]
    }
  ]
}

Responses

200OK

application/json

Example

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "Edge computing reduces latency."
          }
        ]
      }
    }
  ]
}

POST /gemini/v1beta/models/{model}/streamGenerateContent

Request example

cURL

curl \
  --request POST \
  --url 'https://api.anyint.ai/gemini/v1beta/models/<model>/streamGenerateContent' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: text/event-stream' \
  --header 'Content-Type: application/json' \
  --data '{
  "contents": [
    {
      "parts": [
        {
          "text": "Explain edge computing briefly."
        }
      ]
    }
  ]
}'

Authentication

Parameters

Name	Location	Type	Required	Description
model	path	string	Required	—
alt	query	string	Optional	—
X-Client-Message-Id	header	string	Optional	Opt in to durable tenant-scoped execution deduplication. Reuse only with the identical request body and API key. Completed or possibly dispatched requests never expire into another execution, including after Redis loss. Upstream errors or settlement rollback after dispatch require a new message ID for another execution; failures before dispatch may retry the same ID.
X-Resume-Message-Id	header	string	Optional	Replay a previously generated SSE stream under the original API key and identical request body. This request does not dispatch or bill the provider. Cache retention is 10 minutes and total output is limited to 4 MiB; interrupted generations require a new message ID for continuation.
X-Resume-From-Offset	header	integer	Optional	Number of complete SSE events already consumed, matching the last SSE id. Starts at 0; UTF-8 bytes, tokens and characters are not valid units. Takes precedence over Last-Event-ID.
Last-Event-ID	header	integer	Optional	Alternative complete SSE event offset when X-Resume-From-Offset is absent.

Request body

Required

application/json

Example

{
  "contents": [
    {
      "parts": [
        {
          "text": "Explain edge computing briefly."
        }
      ]
    }
  ]
}

Responses

200Gemini content stream

text/event-stream

Example

data: {"candidates":[{"content":{"role":"model","parts":[{"text":"Edge computing reduces latency."}]}}]}

Knowledge Crystallization

1 endpoint

Export crystallized AI conversation events for local Markdown notes sync.

GET /v1/knowledge/export

Request example

cURL

curl \
  --request GET \
  --url 'https://api.anyint.ai/v1/knowledge/export' \
  --header 'Authorization: Bearer <ANYINT_API_KEY>' \
  --header 'Accept: application/json'

Authentication

Parameters

Name	Location	Type	Required	Description
cursor	query	string	Optional	—
limit	query	integer	Optional	—
collection_id	query	string	Optional	—

Responses

200OK

application/json

Example

{
  "schema_version": "1.0.0",
  "collection_id": "default",
  "collection_generation": 1,
  "events": [],
  "next_cursor": null,
  "has_more": false,
  "snapshot_upper_bound": "2026-09-30T10:00:00.000Z",
  "pending_summary": {
    "pending_event_count": 0
  },
  "status": "OK"
}

ChatRoom Integration

POST/v1/tasks/request-costsResolve settled request credits

Request example

Authentication

Request body

Responses

GET/v1/chatroom/modelsList available models

Request example

Authentication

Parameters

Responses

GET/v1/chatroom/enterprise-contextRead the independent ChatRoom enterprise feature context

Request example

Authentication

Responses

GET/v1/chatroom/key-contextRead original asset ownership references for the authenticated key

Request example

Authentication

Responses

Chat

POST/v1/chat/completionsCreate chat completion (compatibility alias)Deprecated

Request example

Authentication

Parameters

Request body

Responses

POST/openai/v1/chat/completionsCreate chat completion

Request example

Authentication

Parameters

Request body

Responses

Responses

POST/v1/responsesCreate response (compatibility alias)Deprecated

Request example

Authentication

Parameters

Request body

Responses

POST/openai/v1/responsesCreate response

Request example

Authentication

Parameters

Request body

Responses

Text Completions

POST/v1/completionsCreate text completion (compatibility alias)Deprecated

Request example

Authentication

Parameters

Request body

Responses

POST/openai/v1/completionsCreate text completion

Request example

Authentication

Parameters

Request body

Responses

Embeddings

POST/v1/embeddingsCreate embeddings (compatibility alias)Deprecated

Request example

Authentication

Request body

Responses

POST/openai/v1/embeddingsCreate embeddings

Request example

Authentication

Request body

Responses

Moderations

POST/v1/moderationsCreate moderation (compatibility alias)Deprecated

Request example

Authentication

Request body

Responses

POST/openai/v1/moderationsCreate moderation

Request example

Authentication

Request body

Responses