> ## Documentation Index
> Fetch the complete documentation index at: https://docs.octen.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Web Chat
> Creates a chat completion with search augmentation.
## OpenAPI
````yaml /api-reference/openapi.json post /v1/chat/completions
openapi: 3.1.0
info:
title: Octen API
description: >-
Octen API provides Search, Extract, Embeddings, VL Embeddings, Web Chat,
Broad Search, and Deep Research services. The Search API searches ranked web
results with optional filters, highlights, and full content. The Extract API
extracts clean markdown content from URLs, with optional query-focused
highlights, page classification, and multimedia resources. The Embeddings
API converts text into vector representations. The VL Embeddings API
converts multimodal inputs (text, images, videos) into vector
representations. The Web Chat API provides LLM chat completions with search
augmentation. The Broad Search API automatically decomposes queries into
multiple sub-queries for comprehensive search and synthesis. The Deep
Research API runs a multi-round adaptive research pipeline that produces a
structured research plan, executes iterative web searches, builds a report
brief with evidence, and streams a final long-form report.
version: 1.0.0
servers:
- url: https://api.octen.ai
security:
- apiKeyAuth: []
paths:
/v1/chat/completions:
post:
summary: Web Chat
description: Creates a chat completion with search augmentation.
operationId: web-chat
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionRequest'
examples:
basic:
summary: Basic Chat with Search
value:
model: anthropic/claude-sonnet-4.6
messages:
- role: system
content: Be precise and concise.
- role: user
content: How many stars are there in our galaxy?
web_search: 'on'
stream: false
max_tokens: 2048
temperature: 1
withSearchOptions:
summary: Chat with Search Options
value:
model: anthropic/claude-sonnet-4.6
messages:
- role: system
content: You are a helpful assistant
- role: user
content: what's the weather in Singapore?
web_search: 'on'
web_search_options:
count: 10
include_domains:
- weather.com
time_basis: published
highlight:
enable: true
max_tokens: 300
format: markdown
safesearch: strict
full_content:
enable: true
max_tokens: 2048
stream: false
max_tokens: 2048
temperature: 1
top_p: 1
withToolCalling:
summary: Chat with Tool Calling
value:
model: openai/gpt-5.4
messages:
- role: user
content: What's the weather in Singapore?
web_search: 'off'
tools:
- type: function
function:
name: get_weather
description: Get the current weather for a city
parameters:
type: object
properties:
city:
type: string
description: City name
required:
- city
tool_choice: auto
withToolResponse:
summary: Multi-turn Chat with Tool Response
value:
model: anthropic/claude-sonnet-4.6
messages:
- role: user
content: >-
What's the weather in Beijing? If it's below 20°C, check
Shenzhen as an alternative.
- role: assistant
content: Let me check the weather in Beijing first.
tool_calls:
- id: call_101
type: function
function:
name: get_weather
arguments: '{"city": "Beijing"}'
- role: tool
tool_call_id: call_101
content: >-
{"city": "Beijing", "temperature": 15, "weather":
"cloudy", "humidity": 40, "wind": "NW 4"}
tools:
- type: function
function:
name: get_weather
description: Get the current weather for a city
parameters:
type: object
properties:
city:
type: string
description: City name
required:
- city
web_search: 'off'
stream: false
responses:
'200':
description: >-
Successful chat completion response. When `stream=false`, returns a
single `chat.completion` object. When `stream=true`, returns a
stream of `chat.completion.chunk` objects with types: `search_done`
(search results), `content` (incremental content), `finish`
(completion signal), and `usage` (token usage).
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/ChatCompletionResponse'
- $ref: '#/components/schemas/ChatCompletionChunk'
discriminator:
propertyName: object
mapping:
chat.completion:
$ref: '#/components/schemas/ChatCompletionResponse'
chat.completion.chunk:
$ref: '#/components/schemas/ChatCompletionChunk'
examples:
nonStreaming:
summary: Non-streaming response (chat.completion)
value:
request_id: gen-1749812345-abcd1234
object: chat.completion
created: 1749812345
model: anthropic/claude-sonnet-4.6
choices:
- index: 0
finish_reason: stop
message:
role: assistant
content: According to search results...
search_results:
- query: What is OpenRouter AI
results:
- title: OpenRouter Documentation
url: https://openrouter.ai/docs
highlight: >-
OpenRouter provides a unified API for multiple LLM
providers
full_content: >-
OpenRouter is a platform that allows developers to
access multiple large language models through a
single API...
authors: OpenRouter
time_published: '2024-11-02T00:00:00Z'
time_last_crawled: '2025-01-10T12:30:00Z'
latency: 62
meta:
usage:
num_search_queries: 1
full_content_tokens: 0
prompt_tokens: 58
completion_tokens: 32
total_tokens: 90
reasoning_tokens: 0
latency: 1200
nonStreamingReasoning:
summary: Non-streaming reasoning model response (no search)
value:
request_id: gen-1749812456-xyz7890
object: chat.completion
created: 1749812456
model: google/gemini-3.1-pro-preview
choices:
- index: 0
finish_reason: stop
message:
role: assistant
content: >-
The question asks for the most widely
recognized top university in South Korea. Seoul
National University is generally ranked
first.
Seoul National University
meta:
usage:
num_search_queries: 0
full_content_tokens: 0
prompt_tokens: 18
completion_tokens: 120
total_tokens: 138
reasoning_tokens: 64
latency: 3500
nonStreamingToolCalls:
summary: >-
Non-streaming response with tool calls (finish_reason:
tool_calls)
value:
request_id: gen-1749812500-tool001
object: chat.completion
created: 1749812500
model: anthropic/claude-sonnet-4.6
choices:
- index: 0
finish_reason: tool_calls
message:
role: assistant
content: Let me check the weather in Beijing first.
tool_calls:
- index: 0
id: call_101
type: function
function:
name: get_weather
arguments: '{"city": "Beijing"}'
meta:
usage:
num_search_queries: 0
full_content_tokens: 0
prompt_tokens: 85
completion_tokens: 42
total_tokens: 127
reasoning_tokens: 0
latency: 1300
streamSearchDone:
summary: 'Streaming chunk — search results (type: search_done)'
value:
type: search_done
request_id: 20260318143837845RJQ9P28ZEC
object: chat.completion.chunk
created: 1773844717
model: anthropic/claude-opus-4.6
search_results:
- query: James Webb Space Telescope latest discoveries 2026
results:
- title: >-
JWST Reveals New Insights into Early Galaxy
Formation
url: https://www.shenzhenware.com/articles/11884
highlight: >-
The James Webb Space Telescope has identified a
cluster of galaxies forming just 350 million years
after the Big Bang, challenging previous models of
cosmic evolution...
authors: NASA
time_published: '2026-02-18T00:00:00Z'
time_last_crawled: '2026-03-01T10:45:00Z'
latency: 59
streamContent:
summary: 'Streaming chunk — content (type: content)'
value:
type: content
request_id: gen-1749812600-stream001
object: chat.completion.chunk
created: 1749812600
model: anthropic/claude-sonnet-4.6
choices:
- index: 0
delta:
role: assistant
content: OpenRouter is
finish_reason: null
streamToolCall:
summary: 'Streaming chunk — tool call (type: content)'
value:
type: content
request_id: gen-1749812600-stream002
object: chat.completion.chunk
created: 1749812600
model: anthropic/claude-sonnet-4.6
choices:
- index: 0
delta:
role: assistant
tool_calls:
- index: 0
id: call_101
type: function
function:
name: get_weather
arguments: '{"city": "Tokyo"}'
finish_reason: null
streamReasoning:
summary: 'Streaming chunk — reasoning content (type: content)'
value:
type: content
request_id: gen-1749812800-reason001
object: chat.completion.chunk
created: 1749812800
model: google/gemini-3.1-pro-preview
choices:
- index: 0
delta:
role: assistant
reasoning_content: >-
The user is asking about the capital of France. This
is a straightforward factual question.
finish_reason: null
streamFinish:
summary: 'Streaming chunk — finish (type: finish)'
value:
type: finish
request_id: gen-1749812600-stream001
object: chat.completion.chunk
created: 1749812600
model: anthropic/claude-sonnet-4.6
choices:
- index: 0
delta: {}
finish_reason: stop
streamUsage:
summary: 'Streaming chunk — usage (type: usage)'
value:
type: usage
request_id: 20260318143837845RJQ9P28ZEC
object: chat.completion.chunk
created: 1773844727
model: anthropic/claude-opus-4.6
meta:
usage:
num_search_queries: 1
full_content_tokens: 18
prompt_tokens: 1841
completion_tokens: 638
total_tokens: 2479
reasoning_tokens: 30
latency: 4500
refusal:
summary: Safety refusal response
value:
request_id: gen-1749812700-refusal
object: chat.completion
created: 1749812700
model: anthropic/claude-sonnet-4.6
choices:
- index: 0
finish_reason: stop
message:
role: assistant
content: null
refusal: I can't help with that request.
'400':
description: >-
Bad request — Returned when a required parameter is missing or
invalid.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
code: 400
msg: Messages is required.
'401':
$ref: '#/components/responses/Unauthorized'
'403':
$ref: '#/components/responses/InsufficientBalance'
'429':
$ref: '#/components/responses/RateLimited'
'500':
$ref: '#/components/responses/InternalError'
security:
- apiKeyAuth: []
- bearerAuth: []
components:
schemas:
ChatCompletionRequest:
type: object
required:
- model
- messages
description: Request body for the Web Chat API.
properties:
model:
type: string
enum:
- anthropic/claude-opus-4.8
- anthropic/claude-opus-4.6
- anthropic/claude-sonnet-4.6
- anthropic/claude-haiku-4.5
- google/gemini-3.5-flash
- google/gemini-3.1-pro-preview
- google/gemini-3.1-flash-lite
- google/gemini-3-flash-preview
- openai/gpt-5.5-pro
- openai/gpt-5.5
- openai/gpt-5.4
- moonshotai/kimi-k2.6
- moonshotai/kimi-k2.5
- minimax/minimax-m2.5
- qwen/qwen3.6-plus
description: The model to use for chat completion.
messages:
type: array
description: >-
A list of messages comprising the conversation so far. System prompt
+ user and assistant messages in chronological order.
items:
$ref: '#/components/schemas/ChatMessage'
web_search:
type: string
enum:
- auto
- 'on'
- 'off'
default: auto
description: Whether to enable search augmentation.
web_search_options:
$ref: '#/components/schemas/ChatWebSearchOptions'
stream:
type: boolean
default: false
description: >-
Whether to enable streaming output. When `true`, returns
`chat.completion.chunk` objects incrementally.
max_tokens:
type: integer
minimum: 1
description: >-
Maximum number of tokens the model can output. If not set, the
model's internal default limit is used.
max_completion_tokens:
type: integer
minimum: 1
description: >-
Maximum completion tokens (including reasoning tokens and visible
output tokens). If not set, the model's internal default limit is
used.
temperature:
type: number
minimum: 0
maximum: 2
default: 1
description: >-
Controls randomness in generation. Higher values produce more
diverse output; lower values produce more deterministic output.
top_p:
type: number
exclusiveMinimum: 0
maximum: 1
default: 1
description: >-
Nucleus sampling parameter. Only tokens with cumulative probability
up to `top_p` are considered. Smaller values produce more
conservative output.
frequency_penalty:
type: number
minimum: -2
maximum: 2
default: 0
description: >-
Penalizes tokens based on their frequency in the output so far.
Positive values reduce repetition; negative values encourage
consistency.
presence_penalty:
type: number
minimum: -2
maximum: 2
default: 0
description: >-
Penalizes tokens that have already appeared in the output. Positive
values encourage topic diversity; negative values encourage focus.
response_format:
$ref: '#/components/schemas/ChatResponseFormat'
stop:
type: array
items:
type: string
description: >-
Stop sequences. Generation stops when any of these strings is
encountered. May not be supported by all models.
seed:
type: integer
description: >-
Seed for reproducibility. With the same parameters and model
version, output should be as consistent as possible.
reasoning:
$ref: '#/components/schemas/ChatReasoningOptions'
logit_bias:
type: object
additionalProperties:
type: number
minimum: -100
maximum: 100
description: >-
A JSON object mapping token IDs to bias values (-100 to 100). The
bias is added to the model's logits before sampling.
tools:
type: array
description: >-
Tool definitions for function calling. Follows the OpenAI tool
calling format; non-OpenAI models are automatically converted.
items:
$ref: '#/components/schemas/ChatToolDefinition'
tool_choice:
description: >-
Controls tool invocation behavior. `none`: never call tools; `auto`:
model decides; `required`: must call a tool. Can also be an object
to specify a particular function: `{"type": "function", "function":
{"name": "my_function"}}`.
oneOf:
- type: string
enum:
- none
- auto
- required
- $ref: '#/components/schemas/ChatToolChoiceObject'
user:
type: string
description: >-
A unique identifier for the end user. Use hashed or pseudonymous
identifiers to avoid passing personally identifiable information.
ChatCompletionResponse:
type: object
description: A non-streaming chat completion response. Returned when `stream=false`.
required:
- request_id
- object
- created
- model
- choices
properties:
request_id:
type: string
description: The unique identifier for this request.
object:
type: string
enum:
- chat.completion
description: >-
The object type, always `chat.completion` for non-streaming
responses.
created:
type: number
description: Unix timestamp (in seconds) of when the completion was created.
model:
type: string
description: The model used for this completion.
choices:
type: array
description: A list of completion choices.
items:
$ref: '#/components/schemas/ChatCompletionChoice'
search_results:
type: array
description: >-
Search results used to augment the response. Only present when
search was used.
items:
$ref: '#/components/schemas/ChatSearchResultGroup'
meta:
$ref: '#/components/schemas/ChatCompletionMeta'
warning:
type: string
nullable: true
description: Warning message, if any.
ChatCompletionChunk:
type: object
description: >-
A streaming chunk of a chat completion response. Returned when
`stream=true`. Chunks are sent incrementally and should be concatenated
in order. The `type` field indicates the chunk kind: `search_done`
(search results available), `content` (incremental content), `finish`
(generation complete), `usage` (token usage summary).
required:
- request_id
- object
- created
- model
properties:
type:
type: string
enum:
- search_done
- content
- finish
- usage
description: The type of this streaming chunk.
request_id:
type: string
description: The unique identifier for this request.
object:
type: string
enum:
- chat.completion.chunk
description: >-
The object type, always `chat.completion.chunk` for streaming
responses.
created:
type: number
description: Unix timestamp (in seconds) of when the chunk was created.
model:
type: string
description: The model used for this completion.
choices:
type: array
description: Incremental choices. Present in `content` and `finish` chunks.
items:
$ref: '#/components/schemas/ChatCompletionChunkChoice'
search_results:
type: array
description: Search results. Present in `search_done` chunks.
items:
$ref: '#/components/schemas/ChatSearchResultGroup'
meta:
$ref: '#/components/schemas/ChatCompletionMeta'
ErrorResponse:
type: object
properties:
code:
type: integer
description: Business status code. Non-zero values indicate an error.
msg:
type: string
description: A human-readable message describing the error.
required:
- code
- msg
ChatMessage:
description: A single message in the conversation. Discriminated by `role`.
oneOf:
- $ref: '#/components/schemas/SystemMessage'
- $ref: '#/components/schemas/UserMessage'
- $ref: '#/components/schemas/AssistantMessage'
- $ref: '#/components/schemas/ToolMessage'
discriminator:
propertyName: role
mapping:
system:
$ref: '#/components/schemas/SystemMessage'
user:
$ref: '#/components/schemas/UserMessage'
assistant:
$ref: '#/components/schemas/AssistantMessage'
tool:
$ref: '#/components/schemas/ToolMessage'
ChatWebSearchOptions:
type: object
description: >-
Search-related options for the Web Chat API. All parameters are optional
and share the same semantics and defaults as the Search API. The query
is automatically generated from the messages and does not need to be
provided.
properties:
count:
type: integer
minimum: 1
maximum: 100
description: Number of search results to return.
include_domains:
type: array
items:
type: string
description: Domains to include in search results.
exclude_domains:
type: array
items:
type: string
description: Domains to exclude from search results.
include_text:
type: array
items:
type: string
maxItems: 5
description: Strings that must appear in the result page text.
exclude_text:
type: array
items:
type: string
maxItems: 5
description: Strings that must not appear in the result page text.
time_basis:
type: string
enum:
- auto
- published
- crawled
description: Determines which time field is used for time filtering.
start_time:
type: string
format: date-time
description: Start time for filtering results. ISO 8601 format.
end_time:
type: string
format: date-time
description: End time for filtering results. ISO 8601 format.
highlight:
$ref: '#/components/schemas/HighlightOptions'
format:
type: string
enum:
- markdown
- text
description: Controls the formatting of highlight outputs.
safesearch:
type: string
enum:
- 'off'
- strict
description: Controls filtering of explicit/adult content.
full_content:
$ref: '#/components/schemas/FullContentOptions'
ChatResponseFormat:
type: object
description: >-
Controls the output format. Some models may not support structured
output and will automatically fall back to `text`.
properties:
type:
type: string
enum:
- text
- json_object
- json_schema
default: text
description: The output format type.
json_schema:
$ref: '#/components/schemas/ChatJsonSchemaSpec'
ChatReasoningOptions:
type: object
description: >-
Options for reasoning models. When `stream=false`, reasoning models
(`google/gemini-3.1-pro-preview`, `moonshotai/kimi-k2.6`,
`moonshotai/kimi-k2.5`, `minimax/minimax-m2.5`) include their reasoning
process as `...` tags within the `content` field. When
`stream=true`, reasoning content is delivered via a separate
`delta.reasoning_content` field (not in `content`). In both cases, the
token count is reported in `reasoning_tokens` in the usage metadata.
properties:
effort:
type: string
enum:
- xhigh
- high
- medium
- low
- minimal
- none
description: The reasoning effort level for reasoning models.
ChatToolDefinition:
type: object
description: A tool definition for function calling.
properties:
type:
type: string
enum:
- function
description: The type of tool. Currently only `function` is supported.
function:
$ref: '#/components/schemas/ChatFunctionDefinition'
required:
- type
- function
ChatToolChoiceObject:
type: object
description: Specifies a particular tool to call.
properties:
type:
type: string
enum:
- function
description: The type of tool.
function:
type: object
description: The function to call.
properties:
name:
type: string
description: The name of the function to call.
required:
- name
required:
- type
- function
ChatCompletionChoice:
type: object
description: A single completion choice in a non-streaming response.
properties:
index:
type: number
description: The index of this choice in the list. Usually 0.
finish_reason:
type: string
enum:
- stop
- length
- tool_calls
- content_filter
- error
description: >-
The reason the model stopped generating. `stop` indicates normal
completion.
message:
$ref: '#/components/schemas/ChatCompletionMessage'
ChatSearchResultGroup:
type: object
description: >-
A group of search results for a single query. One original message may
generate multiple queries.
properties:
query:
type: string
description: >-
The actual search query used by Search API (auto-generated from the
messages).
results:
type: array
description: The search results for this query.
items:
$ref: '#/components/schemas/ChatSearchResultItem'
latency:
type: number
description: Search latency for this query in milliseconds.
ChatCompletionMeta:
type: object
description: Metadata for the chat completion response.
properties:
usage:
$ref: '#/components/schemas/ChatCompletionUsage'
latency:
type: number
description: Total request latency in milliseconds.
ChatCompletionChunkChoice:
type: object
description: A single choice in a streaming chunk.
properties:
index:
type: number
description: The index of this choice. Usually 0.
delta:
$ref: '#/components/schemas/ChatCompletionDelta'
finish_reason:
type: string
nullable: true
enum:
- stop
- length
- tool_calls
- content_filter
- error
- null
description: >-
The reason generation stopped. `null` for intermediate chunks; set
in the `finish` chunk.
SystemMessage:
type: object
required:
- role
- content
description: A system prompt message that sets the behavior or context for the model.
properties:
role:
type: string
enum:
- system
description: The role of the message author. Always `system`.
content:
type: string
description: The system prompt content.
UserMessage:
type: object
required:
- role
- content
description: A message from the user.
properties:
role:
type: string
enum:
- user
description: The role of the message author. Always `user`.
content:
description: >-
The content of the message. Can be a plain string or an array of
content blocks (text and/or image).
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/ChatContentBlock'
AssistantMessage:
type: object
required:
- role
description: >-
A message from the assistant. May contain text content, tool calls, or
both. When replaying a multi-turn conversation with tool use, include
the assistant's `tool_calls` so the model can match them with the
subsequent `tool` messages.
properties:
role:
type: string
enum:
- assistant
description: The role of the message author. Always `assistant`.
content:
type: string
nullable: true
description: >-
The assistant's text content. May be `null` or omitted when the
assistant only produces tool calls.
tool_calls:
type: array
description: >-
Tool calls generated by the model. Each tool call must be answered
by a corresponding `tool` message with a matching `tool_call_id`.
items:
$ref: '#/components/schemas/ChatToolCall'
ToolMessage:
type: object
required:
- role
- tool_call_id
- content
description: >-
A tool result message, providing the output of a tool call back to the
model. The `tool_call_id` must match the `id` of a preceding
`tool_calls` entry in an assistant message.
properties:
role:
type: string
enum:
- tool
description: The role of the message author. Always `tool`.
tool_call_id:
type: string
description: >-
The ID of the tool call this message is responding to. Must match an
`id` from a preceding assistant message's `tool_calls`.
content:
type: string
description: The tool output, typically a JSON string with the function result.
HighlightOptions:
type: object
description: Controls highlight extraction from result pages.
properties:
enable:
type: boolean
default: true
description: If true, returns query-relevant highlight in each result.
max_tokens:
type: integer
default: 512
minimum: 100
maximum: 20000
description: Max tokens returned per highlight.
FullContentOptions:
type: object
description: Controls whether to return the full raw content of each result page.
properties:
enable:
type: boolean
default: false
description: If true, returns full_content for each result.
max_tokens:
type: integer
default: 2048
minimum: 100
maximum: 100000
description: Maximum tokens of full content included per result.
ChatJsonSchemaSpec:
type: object
required:
- name
description: >-
JSON Schema specification for structured output. Required when
`response_format.type` is `json_schema`.
properties:
name:
type: string
description: A user-defined name for the schema.
strict:
type: boolean
default: true
description: Whether the model output must strictly conform to the schema.
description:
type: string
description: A description of the schema.
schema:
type: object
description: >-
The JSON Schema definition object. May contain `type`, `properties`,
`required`, `additionalProperties`, etc.
ChatFunctionDefinition:
type: object
description: A function definition within a tool.
properties:
name:
type: string
description: The name of the function.
description:
type: string
description: A description of what the function does.
parameters:
type: object
description: The function's parameter definition in JSON Schema format.
strict:
type: boolean
default: false
description: >-
Whether to enable strict mode. When enabled, the model's generated
call arguments will strictly conform to the `parameters` schema.
required:
- name
ChatCompletionMessage:
type: object
description: >-
The assistant's response message (non-streaming). For reasoning models,
the thinking process appears as `...` tags within the
`content` field. In streaming mode, reasoning content is delivered via
`delta.reasoning_content` instead.
properties:
role:
type: string
enum:
- assistant
- tool
description: The role of the message author. Usually `assistant`.
content:
type: string
nullable: true
description: >-
The assistant's text content. May be `null` when the model only
produces tool calls, or in refusal scenarios. For reasoning models,
this field may contain `...` tags wrapping the
model's reasoning process before the final answer.
tool_calls:
type: array
description: >-
Tool calls generated by the model. Only present when the model
decides to invoke one or more tools. Each call includes an `id` that
must be referenced by a subsequent `tool` message.
items:
$ref: '#/components/schemas/ChatToolCall'
refusal:
type: string
description: >-
A model-generated refusal message. Only present when the model
refuses a request.
ChatSearchResultItem:
type: object
description: A single search result item within a chat search result group.
properties:
title:
type: string
description: The title of the result page.
url:
type: string
description: The URL of the result page.
highlight:
type: string
description: >-
Query-relevant highlight content. Only returned when
`highlight.enable` is `true`.
full_content:
type: string
description: >-
Full page content. Only returned when `full_content.enable` is
`true`.
authors:
type: string
description: Website name or author.
time_published:
type: string
format: date-time
description: Publish time in ISO 8601.
time_last_crawled:
type: string
format: date-time
description: Last crawl time in ISO 8601.
ChatCompletionUsage:
type: object
description: >-
Token usage information for the chat completion. When `stream=true`,
this may only appear in the final chunk.
properties:
num_search_queries:
type: integer
description: >-
Number of search queries executed. Always present; 0 when search was
not used.
full_content_tokens:
type: integer
description: >-
Tokens used for full content retrieval. Always present (as 0) in
non-streaming responses. In streaming, only present when full
content retrieval was used.
prompt_tokens:
type: integer
description: Number of input tokens.
completion_tokens:
type: integer
description: >-
Number of output tokens (reasoning_tokens are included in this
count).
total_tokens:
type: integer
description: Total tokens used (prompt_tokens + completion_tokens).
reasoning_tokens:
type: integer
description: >-
Number of reasoning tokens. Always present (as 0) in non-streaming
responses. In streaming, only present when reasoning was enabled.
required:
- num_search_queries
- prompt_tokens
- completion_tokens
- total_tokens
ChatCompletionDelta:
type: object
description: >-
Incremental content in a streaming chunk. Contains only the new fields
for this chunk.
properties:
role:
type: string
enum:
- assistant
description: The role. Typically included in the first chunk.
reasoning_content:
type: string
description: >-
Incremental reasoning content from reasoning models. Present during
the thinking phase before the final answer. Concatenate across
chunks to build the complete reasoning. Only appears for
reasoning-capable models (`google/gemini-3.1-pro-preview`,
`moonshotai/kimi-k2.6`, `moonshotai/kimi-k2.5`,
`minimax/minimax-m2.5`).
content:
type: string
description: Incremental text content.
tool_calls:
type: array
description: >-
Incremental tool call data. Present when the model invokes tools
during streaming. Each chunk may contain partial function name or
arguments that should be concatenated.
items:
$ref: '#/components/schemas/ChatToolCallDelta'
ChatContentBlock:
type: object
description: A content block within a message. Supports text and image types.
properties:
type:
type: string
enum:
- text
- image_url
description: The type of content block.
text:
type: string
description: The text content. Required when `type` is `text`.
image_url:
type: object
description: Image URL object. Required when `type` is `image_url`.
properties:
url:
type: string
description: The URL of the image.
required:
- url
required:
- type
ChatToolCall:
type: object
required:
- id
- type
- function
description: A tool call generated by the model.
properties:
index:
type: number
description: The index of this tool call in the tool_calls array.
id:
type: string
description: >-
A unique identifier for this tool call. Referenced by the
corresponding `tool` message's `tool_call_id`.
type:
type: string
enum:
- function
description: The type of tool call. Currently only `function` is supported.
function:
$ref: '#/components/schemas/ChatToolCallFunction'
ChatToolCallDelta:
type: object
description: >-
Incremental tool call data in a streaming chunk. The first chunk for a
tool call includes `id`, `type`, and `function.name`. Subsequent chunks
append to `function.arguments`.
properties:
index:
type: number
description: The index of this tool call in the tool_calls array.
id:
type: string
description: >-
The tool call ID. Only present in the first chunk for this tool
call.
type:
type: string
enum:
- function
description: The type of tool call.
function:
type: object
description: Incremental function call data.
properties:
name:
type: string
description: >-
The function name. Only present in the first chunk for this tool
call.
arguments:
type: string
description: >-
Incremental JSON string of the function arguments. Concatenate
across chunks to build the complete arguments.
ChatToolCallFunction:
type: object
required:
- name
- arguments
description: The function invocation details within a tool call.
properties:
name:
type: string
description: The name of the function to call.
arguments:
type: string
description: >-
The arguments to the function, as a JSON string generated by the
model.
responses:
Unauthorized:
description: Invalid API Key — Returned when the API key is missing or invalid.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
code: 401
msg: Invalid API Key
InsufficientBalance:
description: >-
Insufficient balance in account — Returned when the account balance is
insufficient to complete the request.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
code: 403
msg: Insufficient balance in account
RateLimited:
description: >-
Exceeding the rate limit — Returned when the request exceeds the
configured rate limit.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
code: 429
msg: Exceeding the rate limit
InternalError:
description: Internal error — Returned when an unexpected server-side error occurs.
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
code: 500
msg: Internal error
securitySchemes:
apiKeyAuth:
type: apiKey
in: header
name: x-api-key
description: >-
API key used for request authentication. Obtain an API key before using
the API. Note: A payment method is required to use the API.
bearerAuth:
type: http
scheme: bearer
description: >-
Bearer token authentication. Compatible with OpenAI protocol. Pass the
API key as `Authorization: Bearer `.
````