> ## Documentation Index
> Fetch the complete documentation index at: https://evolink.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Claude - Messages API
> - Send a structured list of input messages with text and/or image content, and the model will generate the next message in the conversation.
- The Messages API can be used for either single queries or stateless multi-turn conversations.
**BaseURL**: The default BaseURL is `https://direct.evolink.ai`, which has better support for text models and long-lived connections. `https://api.evolink.ai` is the primary endpoint for multimodal services and serves as a fallback address for text models.
## OpenAPI
````yaml en/api-manual/language-series/claude/claude-messages-api.json POST /v1/messages
openapi: 3.1.0
info:
title: Claude Messages API
description: >-
Send a structured list of input messages with text and/or image content, and
the model will generate the next message in the conversation. The Messages
API can be used for either single queries or stateless multi-turn
conversations.
license:
name: MIT
version: 1.0.0
servers:
- url: https://direct.evolink.ai
description: Production (recommended)
- url: https://api.evolink.ai
description: Alternative URL
security:
- bearerAuth: []
tags:
- name: Messages
description: Claude AI message generation and conversation APIs
paths:
/v1/messages:
post:
tags:
- Messages
summary: Create a Message
description: >-
- Send a structured list of input messages with text and/or image
content, and the model will generate the next message in the
conversation.
- The Messages API can be used for either single queries or stateless
multi-turn conversations.
operationId: createMessage
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/CreateMessageParams'
example:
model: claude-opus-5
max_tokens: 1024
messages:
- role: user
content: Hello, world
responses:
'200':
description: Message object
content:
application/json:
schema:
$ref: '#/components/schemas/Message'
example:
model: claude-haiku-4-5-20251001
id: msg_bdrk_017XLrAa77zWvfBGQ6ESvrxz
type: message
role: assistant
content:
- type: text
text: |-
# Hey there! 👋
How's it going? What can I help you with today?
stop_reason: end_turn
stop_sequence: null
usage:
input_tokens: 8
cache_creation_input_tokens: 0
cache_read_input_tokens: 0
output_tokens: 24
'400':
description: Invalid request
content:
application/json:
schema:
$ref: 5d0ca42d-5ea4-441f-acb7-88f1fc915e62
example:
error:
message: Invalid request
type: invalid_request_error
request_id:
type: error
'401':
description: Authentication error
content:
application/json:
schema:
$ref: 5d0ca42d-5ea4-441f-acb7-88f1fc915e62
example:
error:
message: Authentication error
type: authentication_error
request_id:
type: error
'402':
description: Billing error
content:
application/json:
schema:
$ref: 5d0ca42d-5ea4-441f-acb7-88f1fc915e62
example:
error:
message: Billing error
type: billing_error
request_id:
type: error
fallback_suggestion: https://evolink.ai/dashboard/billing
'403':
description: Permission error
content:
application/json:
schema:
$ref: 5d0ca42d-5ea4-441f-acb7-88f1fc915e62
example:
error:
message: Permission denied
type: permission_error
request_id:
type: error
'404':
description: Not found
content:
application/json:
schema:
$ref: 5d0ca42d-5ea4-441f-acb7-88f1fc915e62
example:
error:
message: Not found
type: not_found_error
request_id:
type: error
'429':
description: Rate limit error
content:
application/json:
schema:
$ref: 5d0ca42d-5ea4-441f-acb7-88f1fc915e62
example:
error:
message: Rate limited
type: rate_limit_error
request_id:
type: error
fallback_suggestion: retry after 60 seconds
'500':
description: Internal server error
content:
application/json:
schema:
$ref: 5d0ca42d-5ea4-441f-acb7-88f1fc915e62
example:
error:
message: Internal server error
type: api_error
request_id:
type: error
fallback_suggestion: try again later
'503':
description: Service overloaded
content:
application/json:
schema:
$ref: 5d0ca42d-5ea4-441f-acb7-88f1fc915e62
example:
error:
message: Overloaded
type: overloaded_error
request_id:
type: error
fallback_suggestion: retry after 30 seconds
'524':
description: Cloudflare gateway timeout error
content:
application/json:
schema:
$ref: 5d0ca42d-5ea4-441f-acb7-88f1fc915e62
example:
error:
message: Request timeout
type: timeout_error
request_id:
type: error
fallback_suggestion: >-
Please switch the BaseURL to https://direct.evolink.ai; this
endpoint is better for long-running tasks
components:
schemas:
CreateMessageParams:
additionalProperties: false
properties:
model:
$ref: '#/components/schemas/Model'
description: >-
Body param: The model used to generate the response. Select one of
the supported model IDs listed below.
examples:
- claude-opus-5
max_tokens:
description: >-
Body param: The maximum number of tokens to generate before
stopping.
The model may stop before reaching this limit. Supported models can
have different maximum output limits.
type: integer
minimum: 1
examples:
- 1024
messages:
description: >-
Body param: Input messages.
Our models are trained to operate on alternating `user` and
`assistant` conversational turns. When creating a new `Message`, you
specify the prior conversational turns with the `messages`
parameter, and the model then generates the next `Message` in the
conversation. Consecutive `user` or `assistant` turns in your
request will be combined into a single turn.
Each input message must be an object with a `role` and `content`.
You can specify a single `user`-role message, or you can include
multiple `user` and `assistant` messages.
If the final message uses the `assistant` role, the response content
will continue immediately from the content in that message. This can
be used to constrain part of the model's response.
Example with a single `user` message:
```json [{ "role": "user", "content": "Hello, Claude" }] ```
Example with multiple conversational turns:
```json [ { "role": "user", "content": "Hello there." }, {
"role": "assistant", "content": "Hi, I'm Claude. How can I help
you?" }, { "role": "user", "content": "Can you explain LLMs in
plain English?" } ] ```
Example with a partially-filled response from Claude:
```json [ { "role": "user", "content": "What's the Greek
name for Sun? (A) Sol (B) Helios (C) Sun" }, { "role":
"assistant", "content": "The best answer is (" } ] ```
Each input message `content` may be either a single `string` or an
array of content blocks, where each block has a specific `type`.
Using a `string` for `content` is shorthand for an array of one
content block of type `"text"`. The following input messages are
equivalent:
```json { "role": "user", "content": "Hello, Claude" } ```
```json { "role": "user", "content": [{ "type": "text", "text":
"Hello, Claude" }] } ```
Note that if you want to include a system prompt, you can use the
top-level `system` parameter — there is no `"system"` role for input
messages in the Messages API.
There is a limit of 100,000 messages in a single request.
items:
$ref: '#/components/schemas/BetaMessageParam'
type: array
minItems: 1
maxItems: 100000
container:
anyOf:
- $ref: '#/components/schemas/BetaContainerParams'
- type: string
- type: 'null'
description: 'Body param: Container identifier for reuse across requests.'
output_config:
$ref: '#/components/schemas/BetaOutputConfig'
description: >-
Body param: Configuration options for the model's output, such as
the output format.
stop_sequences:
description: >-
Body param: Custom text sequences that will cause the model to stop
generating.
Our models will normally stop when they have naturally completed
their turn, which will result in a response `stop_reason` of
`"end_turn"`.
If you want the model to stop generating when it encounters custom
strings of text, you can use the `stop_sequences` parameter. If the
model encounters one of the custom sequences, the response
`stop_reason` value will be `"stop_sequence"` and the response
`stop_sequence` value will contain the matched stop sequence.
items:
type: string
type: array
stream:
description: >-
Body param: Whether to incrementally stream the response using
server-sent events.
type: boolean
system:
anyOf:
- type: string
- items:
$ref: '#/components/schemas/BetaTextBlockParam'
type: array
description: >-
Body param: System prompt.
Use this parameter to provide context and instructions, such as
assigning the model a specific goal or role.
temperature:
type: number
minimum: 0
maximum: 1
examples:
- 1
thinking:
$ref: '#/components/schemas/BetaThinkingConfigParam'
description: >-
Body param: Configuration for enabling extended thinking.
When enabled, responses include `thinking` content blocks before the
final answer. `budget_tokens` must be at least 1,024 and counts
toward `max_tokens`.
tool_choice:
$ref: '#/components/schemas/BetaToolChoice'
description: >-
Body param: How the model should use the provided tools. The model
can use a specific tool, any available tool, decide by itself, or
not use tools at all.
tools:
description: >-
Body param: Definitions of client tools that the model may use.
If you include `tools` in your API request, the model may return
`tool_use` content blocks that represent the model's use of those
tools. You can then run the tools using the generated input and
return results in `tool_result` content blocks.
Each tool definition includes:
- `name`: Name of the tool.
- `description`: Optional, but strongly recommended description of
the tool.
- `input_schema`: JSON schema for the tool input.
items:
$ref: '#/components/schemas/BetaTool'
type: array
top_k:
type: integer
minimum: 0
examples:
- 5
top_p:
type: number
minimum: 0
maximum: 1
examples:
- 0.7
required:
- model
- messages
- max_tokens
type: object
Message:
type: object
required:
- id
- type
- role
- content
- model
- stop_reason
- stop_sequence
- usage
properties:
id:
type: string
description: |-
Unique object identifier.
The format and length of IDs may change over time.
examples:
- msg_013Zva2CMHLNnXjNJJKqJ2EF
title: Id
type:
type: string
const: message
description: |-
Object type.
For Messages, this is always `"message"`.
title: Type
role:
type: string
const: assistant
description: |-
Conversational role of the generated message.
This will always be `"assistant"`.
title: Role
content:
type: array
description: >-
Content generated by the model.
This is an array of content blocks, each of which has a `type` that
determines its shape.
items:
anyOf:
- $ref: '#/components/schemas/ResponseTextBlock'
- $ref: '#/components/schemas/ResponseThinkingBlock'
- $ref: '#/components/schemas/ResponseRedactedThinkingBlock'
- $ref: '#/components/schemas/ResponseToolUseBlock'
- $ref: '#/components/schemas/ResponseServerToolUseBlock'
- $ref: '#/components/schemas/ResponseWebSearchToolResultBlock'
- $ref: '#/components/schemas/ResponseWebFetchToolResultBlock'
- $ref: '#/components/schemas/ResponseCodeExecutionToolResultBlock'
- $ref: '#/components/schemas/ResponseBashCodeExecutionToolResultBlock'
- $ref: >-
#/components/schemas/ResponseTextEditorCodeExecutionToolResultBlock
- $ref: '#/components/schemas/ResponseMCPToolUseBlock'
- $ref: '#/components/schemas/ResponseMCPToolResultBlock'
- $ref: '#/components/schemas/ResponseContainerUploadBlock'
title: Content
model:
type: string
description: The model that handled the request.
enum:
- claude-haiku-4-5-20251001
- claude-sonnet-4-5-20250929
- claude-opus-4-5-20251101
- claude-opus-4-6
- claude-fable-5
- claude-opus-5
- claude-opus-4-8
- claude-opus-4-7
- claude-sonnet-4-6
- claude-sonnet-5
examples:
- claude-opus-5
title: Model
stop_reason:
type: string
nullable: true
description: >-
The reason that generation stopped.
A model safety refusal may be returned as a successful Message
response with `stop_reason: "refusal"`. This is different from an
HTTP `403 permission_error`, which indicates an account or
authorization problem.
enum:
- end_turn
- max_tokens
- stop_sequence
- tool_use
- pause_turn
- refusal
- model_context_window_exceeded
title: Stop Reason
stop_sequence:
type: string
nullable: true
description: Which custom stop sequence was generated, if any.
title: Stop Sequence
usage:
$ref: '#/components/schemas/Usage'
description: Billing and rate-limit usage.
context_management:
anyOf:
- $ref: '#/components/schemas/ResponseContextManagement'
- type: 'null'
description: Context management response.
container:
anyOf:
- $ref: '#/components/schemas/Container'
- type: 'null'
description: Information about the container used in this request.
Model:
type: string
enum:
- claude-haiku-4-5-20251001
- claude-sonnet-4-5-20250929
- claude-opus-4-5-20251101
- claude-opus-4-6
- claude-fable-5
- claude-opus-5
- claude-opus-4-8
- claude-opus-4-7
- claude-sonnet-4-6
- claude-sonnet-5
description: The model that will complete your prompt.
BetaMessageParam:
additionalProperties: false
properties:
content:
anyOf:
- type: string
- items:
$ref: '#/components/schemas/BetaContentBlockParam'
type: array
role:
enum:
- user
- assistant
type: string
required:
- content
- role
type: object
BetaContainerParams:
additionalProperties: false
description: Container parameters with skills to be loaded.
properties:
id:
description: Container id
type:
- string
- 'null'
skills:
anyOf:
- items:
$ref: '#/components/schemas/BetaSkillParams'
type: array
- type: 'null'
description: List of skills to load in the container
type: object
BetaOutputConfig:
additionalProperties: false
properties:
effort:
description: All possible effort levels.
enum:
- low
- medium
- high
- xhigh
- max
- null
type:
- string
- 'null'
format:
anyOf:
- $ref: '#/components/schemas/BetaJSONOutputFormat'
- type: 'null'
description: A JSON schema that defines the required response format.
task_budget:
anyOf:
- $ref: '#/components/schemas/BetaTokenTaskBudget'
- type: 'null'
description: User-configurable total token budget across contexts.
type: object
BetaTextBlockParam:
additionalProperties: false
properties:
cache_control:
anyOf:
- $ref: '#/components/schemas/BetaCacheControlEphemeral'
- type: 'null'
description: Create a cache control breakpoint at this content block.
citations:
anyOf:
- items:
$ref: '#/components/schemas/BetaTextCitationParam'
type: array
- type: 'null'
text:
type: string
type:
const: text
type: string
required:
- text
- type
type: object
BetaThinkingConfigParam:
anyOf:
- $ref: '#/components/schemas/BetaThinkingConfigEnabled'
- $ref: '#/components/schemas/BetaThinkingConfigDisabled'
- $ref: '#/components/schemas/BetaThinkingConfigAdaptive'
description: >-
Configuration for enabling extended thinking.
When enabled, responses include `thinking` content blocks before the
final answer. `budget_tokens` must be at least 1,024 and counts toward
`max_tokens`.
BetaToolChoice:
anyOf:
- $ref: '#/components/schemas/BetaToolChoiceAuto'
- $ref: '#/components/schemas/BetaToolChoiceAny'
- $ref: '#/components/schemas/BetaToolChoiceTool'
- $ref: '#/components/schemas/BetaToolChoiceNone'
description: >-
How the model should use the provided tools. The model can use a
specific tool, any available tool, decide by itself, or not use tools at
all.
BetaTool:
additionalProperties: false
properties:
allowed_callers:
items:
enum:
- direct
- code_execution_20250825
- code_execution_20260120
- code_execution_20260521
type: string
type: array
cache_control:
anyOf:
- $ref: '#/components/schemas/BetaCacheControlEphemeral'
- type: 'null'
description: Create a cache control breakpoint at this content block.
defer_loading:
description: >-
If true, tool will not be included in initial system prompt. Only
loaded when returned via tool_reference from tool search.
type: boolean
description:
description: >-
Description of what this tool does.
Tool descriptions should be as detailed as possible. The more
information that the model has about what the tool is and how to use
it, the better it will perform. You can use natural language
descriptions to reinforce important aspects of the tool input JSON
schema.
type: string
eager_input_streaming:
description: >-
Enable eager input streaming for this tool. When true, tool input
parameters will be streamed incrementally as they are generated, and
types will be inferred on-the-fly rather than buffering the full
JSON output. When false, streaming is disabled for this tool even if
the fine-grained-tool-streaming beta is active. When null (default),
uses the default behavior based on beta headers.
type:
- boolean
- 'null'
input_examples:
items:
additionalProperties: {}
type: object
type: array
input_schema:
$ref: '#/components/schemas/BetaTool.InputSchema'
description: >-
[JSON schema](https://json-schema.org/draft/2020-12) for this tool's
input.
This defines the shape of the `input` that your tool accepts and
that the model will produce.
name:
description: >-
Name of the tool.
This is how the tool will be called by the model and in `tool_use`
blocks.
type: string
strict:
description: When true, guarantees schema validation on tool names and inputs
type: boolean
type:
enum:
- custom
- null
type:
- string
- 'null'
required:
- input_schema
- name
type: object
ResponseTextBlock:
properties:
citations:
anyOf:
- items:
discriminator:
mapping:
char_location:
$ref: '#/components/schemas/ResponseCharLocationCitation'
content_block_location:
$ref: >-
#/components/schemas/ResponseContentBlockLocationCitation
page_location:
$ref: '#/components/schemas/ResponsePageLocationCitation'
search_result_location:
$ref: >-
#/components/schemas/ResponseSearchResultLocationCitation
web_search_result_location:
$ref: >-
#/components/schemas/ResponseWebSearchResultLocationCitation
propertyName: type
oneOf:
- $ref: '#/components/schemas/ResponseCharLocationCitation'
- $ref: '#/components/schemas/ResponsePageLocationCitation'
- $ref: '#/components/schemas/ResponseContentBlockLocationCitation'
- $ref: >-
#/components/schemas/ResponseWebSearchResultLocationCitation
- $ref: '#/components/schemas/ResponseSearchResultLocationCitation'
type: array
- type: 'null'
default: null
description: >-
Citations supporting the text block.
The type of citation returned will depend on the type of document
being cited. Citing a PDF results in `page_location`, plain text
results in `char_location`, and content document results in
`content_block_location`.
title: Citations
text:
maxLength: 5000000
minLength: 0
title: Text
type: string
type:
const: text
default: text
title: Type
type: string
required:
- citations
- text
- type
title: Text
type: object
ResponseThinkingBlock:
properties:
signature:
title: Signature
type: string
thinking:
title: Thinking
type: string
type:
const: thinking
default: thinking
title: Type
type: string
required:
- signature
- thinking
- type
title: Thinking
type: object
ResponseRedactedThinkingBlock:
properties:
data:
title: Data
type: string
type:
const: redacted_thinking
default: redacted_thinking
title: Type
type: string
required:
- data
- type
title: Redacted thinking
type: object
ResponseToolUseBlock:
properties:
id:
pattern: ^[a-zA-Z0-9_-]+$
title: Id
type: string
input:
additionalProperties: true
title: Input
type: object
name:
minLength: 1
title: Name
type: string
type:
const: tool_use
default: tool_use
title: Type
type: string
required:
- id
- input
- name
- type
title: Tool use
type: object
ResponseServerToolUseBlock:
properties:
id:
pattern: ^srvtoolu_[a-zA-Z0-9_]+$
title: Id
type: string
input:
additionalProperties: true
title: Input
type: object
name:
enum:
- web_search
- web_fetch
- code_execution
- bash_code_execution
- text_editor_code_execution
title: Name
type: string
type:
const: server_tool_use
default: server_tool_use
title: Type
type: string
required:
- id
- input
- name
- type
title: Server tool use
type: object
ResponseWebSearchToolResultBlock:
properties:
content:
anyOf:
- $ref: '#/components/schemas/ResponseWebSearchToolResultError'
- items:
$ref: '#/components/schemas/ResponseWebSearchResultBlock'
type: array
title: Content
tool_use_id:
pattern: ^srvtoolu_[a-zA-Z0-9_]+$
title: Tool Use Id
type: string
type:
const: web_search_tool_result
default: web_search_tool_result
title: Type
type: string
required:
- content
- tool_use_id
- type
title: Web search tool result
type: object
ResponseWebFetchToolResultBlock:
properties:
content:
anyOf:
- $ref: '#/components/schemas/ResponseWebFetchToolResultError'
- $ref: '#/components/schemas/ResponseWebFetchResultBlock'
title: Content
tool_use_id:
pattern: ^srvtoolu_[a-zA-Z0-9_]+$
title: Tool Use Id
type: string
type:
const: web_fetch_tool_result
default: web_fetch_tool_result
title: Type
type: string
required:
- content
- tool_use_id
- type
title: ResponseWebFetchToolResultBlock
type: object
ResponseCodeExecutionToolResultBlock:
properties:
content:
anyOf:
- $ref: '#/components/schemas/ResponseCodeExecutionToolResultError'
- $ref: '#/components/schemas/ResponseCodeExecutionResultBlock'
title: Content
tool_use_id:
pattern: ^srvtoolu_[a-zA-Z0-9_]+$
title: Tool Use Id
type: string
type:
const: code_execution_tool_result
default: code_execution_tool_result
title: Type
type: string
required:
- content
- tool_use_id
- type
title: Code execution tool result
type: object
ResponseBashCodeExecutionToolResultBlock:
properties:
content:
anyOf:
- $ref: '#/components/schemas/ResponseBashCodeExecutionToolResultError'
- $ref: '#/components/schemas/ResponseBashCodeExecutionResultBlock'
title: Content
tool_use_id:
pattern: ^srvtoolu_[a-zA-Z0-9_]+$
title: Tool Use Id
type: string
type:
const: bash_code_execution_tool_result
default: bash_code_execution_tool_result
title: Type
type: string
required:
- content
- tool_use_id
- type
title: ResponseBashCodeExecutionToolResultBlock
type: object
ResponseTextEditorCodeExecutionToolResultBlock:
properties:
content:
anyOf:
- $ref: >-
#/components/schemas/ResponseTextEditorCodeExecutionToolResultError
- $ref: >-
#/components/schemas/ResponseTextEditorCodeExecutionViewResultBlock
- $ref: >-
#/components/schemas/ResponseTextEditorCodeExecutionCreateResultBlock
- $ref: >-
#/components/schemas/ResponseTextEditorCodeExecutionStrReplaceResultBlock
title: Content
tool_use_id:
pattern: ^srvtoolu_[a-zA-Z0-9_]+$
title: Tool Use Id
type: string
type:
const: text_editor_code_execution_tool_result
default: text_editor_code_execution_tool_result
title: Type
type: string
required:
- content
- tool_use_id
- type
title: ResponseTextEditorCodeExecutionToolResultBlock
type: object
ResponseMCPToolUseBlock:
properties:
id:
pattern: ^[a-zA-Z0-9_-]+$
title: Id
type: string
input:
additionalProperties: true
title: Input
type: object
name:
description: The name of the MCP tool
title: Name
type: string
server_name:
description: The name of the MCP server
title: Server Name
type: string
type:
const: mcp_tool_use
default: mcp_tool_use
title: Type
type: string
required:
- id
- input
- name
- server_name
- type
title: MCP tool use
type: object
ResponseMCPToolResultBlock:
properties:
content:
anyOf:
- type: string
- items:
$ref: '#/components/schemas/ResponseTextBlock'
type: array
title: Content
is_error:
default: false
title: Is Error
type: boolean
tool_use_id:
pattern: ^[a-zA-Z0-9_-]+$
title: Tool Use Id
type: string
type:
const: mcp_tool_result
default: mcp_tool_result
title: Type
type: string
required:
- content
- is_error
- tool_use_id
- type
title: MCP tool result
type: object
ResponseContainerUploadBlock:
description: Response model for a file uploaded to the container.
properties:
file_id:
title: File Id
type: string
type:
const: container_upload
default: container_upload
title: Type
type: string
required:
- file_id
- type
title: Container upload
type: object
Usage:
properties:
cache_creation:
anyOf:
- $ref: '#/components/schemas/CacheCreation'
- type: 'null'
default: null
description: Breakdown of cached tokens by TTL
cache_creation_input_tokens:
anyOf:
- minimum: 0
type: integer
- type: 'null'
default: null
description: The number of input tokens used to create the cache entry.
examples:
- 2051
title: Cache Creation Input Tokens
cache_read_input_tokens:
anyOf:
- minimum: 0
type: integer
- type: 'null'
default: null
description: The number of input tokens read from the cache.
examples:
- 2051
title: Cache Read Input Tokens
input_tokens:
description: The number of input tokens which were used.
examples:
- 2095
minimum: 0
title: Input Tokens
type: integer
output_tokens:
description: The number of output tokens which were used.
examples:
- 503
minimum: 0
title: Output Tokens
type: integer
server_tool_use:
anyOf:
- $ref: '#/components/schemas/ServerToolUsage'
- type: 'null'
default: null
description: The number of server tool requests.
service_tier:
anyOf:
- enum:
- standard
- priority
- batch
type: string
- type: 'null'
default: null
description: If the request used the priority, standard, or batch tier.
title: Service Tier
required:
- cache_creation
- cache_creation_input_tokens
- cache_read_input_tokens
- input_tokens
- output_tokens
- server_tool_use
- service_tier
title: Usage
type: object
ResponseContextManagement:
properties:
applied_edits:
description: List of context management edits that were applied.
items:
discriminator:
mapping:
clear_thinking_20251015:
$ref: '#/components/schemas/ResponseClearThinking20251015Edit'
clear_tool_uses_20250919:
$ref: '#/components/schemas/ResponseClearToolUses20250919Edit'
propertyName: type
oneOf:
- $ref: '#/components/schemas/ResponseClearToolUses20250919Edit'
- $ref: '#/components/schemas/ResponseClearThinking20251015Edit'
title: Applied Edits
type: array
required:
- applied_edits
title: ResponseContextManagement
type: object
Container:
description: >-
Information about the container used in the request (for the code
execution tool)
properties:
expires_at:
description: The time at which the container will expire.
format: date-time
title: Expires At
type: string
id:
description: Identifier for the container used in this request
title: Id
type: string
skills:
anyOf:
- items:
$ref: '#/components/schemas/Skill'
type: array
- type: 'null'
default: null
description: Skills loaded in the container
title: Skills
required:
- expires_at
- id
- skills
title: Container
type: object
BetaContentBlockParam:
anyOf:
- $ref: '#/components/schemas/BetaTextBlockParam'
- $ref: '#/components/schemas/BetaImageBlockParam'
- $ref: '#/components/schemas/BetaRequestDocumentBlock'
- $ref: '#/components/schemas/BetaSearchResultBlockParam'
- $ref: '#/components/schemas/BetaThinkingBlockParam'
- $ref: '#/components/schemas/BetaRedactedThinkingBlockParam'
- $ref: '#/components/schemas/BetaToolUseBlockParam'
- $ref: '#/components/schemas/BetaToolResultBlockParam'
description: Regular text content.
BetaSkillParams:
additionalProperties: false
description: Specification for a skill to be loaded in a container (request model).
properties:
skill_id:
description: Skill ID
type: string
type:
description: >-
Type of skill - either 'anthropic' (built-in) or 'custom'
(user-defined)
enum:
- anthropic
- custom
type: string
version:
description: Skill version or 'latest' for most recent version
type: string
required:
- skill_id
- type
type: object
BetaJSONOutputFormat:
additionalProperties: false
properties:
schema:
additionalProperties: {}
description: The JSON schema of the format
type: object
type:
const: json_schema
type: string
required:
- schema
- type
type: object
BetaTokenTaskBudget:
additionalProperties: false
description: User-configurable total token budget across contexts.
properties:
remaining:
description: >-
Remaining tokens in the budget. Use this to track usage across
contexts when implementing compaction client-side. Defaults to total
if not provided.
type:
- number
- 'null'
total:
description: Total token budget across all contexts in the session.
type: number
type:
const: tokens
description: The budget type. Currently only 'tokens' is supported.
type: string
required:
- total
- type
type: object
BetaCacheControlEphemeral:
additionalProperties: false
properties:
ttl:
description: |-
The time-to-live for the cache control breakpoint.
Available values:
- `5m`: 5 minutes
- `1h`: 1 hour
Defaults to `5m`.
enum:
- 5m
- 1h
type: string
type:
const: ephemeral
type: string
required:
- type
type: object
BetaTextCitationParam:
anyOf:
- $ref: '#/components/schemas/BetaCitationCharLocationParam'
- $ref: '#/components/schemas/BetaCitationPageLocationParam'
- $ref: '#/components/schemas/BetaCitationContentBlockLocationParam'
- $ref: '#/components/schemas/BetaCitationWebSearchResultLocationParam'
- $ref: '#/components/schemas/BetaCitationSearchResultLocationParam'
BetaThinkingConfigEnabled:
additionalProperties: false
properties:
budget_tokens:
description: >-
Determines how many tokens the model can use for its internal
reasoning process. Larger budgets can enable more thorough analysis
for complex problems.
Must be at least 1,024 and less than `max_tokens`.
type: integer
minimum: 1024
type:
const: enabled
type: string
required:
- budget_tokens
- type
type: object
BetaThinkingConfigDisabled:
additionalProperties: false
properties:
type:
const: disabled
type: string
required:
- type
type: object
BetaThinkingConfigAdaptive:
additionalProperties: false
properties:
type:
const: adaptive
type: string
required:
- type
type: object
BetaToolChoiceAuto:
additionalProperties: false
description: The model will automatically decide whether to use tools.
properties:
disable_parallel_tool_use:
description: >-
Whether to disable parallel tool use.
Defaults to `false`. If set to `true`, the model will output at most
one tool use.
type: boolean
type:
const: auto
type: string
required:
- type
type: object
BetaToolChoiceAny:
additionalProperties: false
description: The model will use any available tools.
properties:
disable_parallel_tool_use:
description: >-
Whether to disable parallel tool use.
Defaults to `false`. If set to `true`, the model will output exactly
one tool use.
type: boolean
type:
const: any
type: string
required:
- type
type: object
BetaToolChoiceTool:
additionalProperties: false
description: The model will use the specified tool with `tool_choice.name`.
properties:
disable_parallel_tool_use:
description: >-
Whether to disable parallel tool use.
Defaults to `false`. If set to `true`, the model will output exactly
one tool use.
type: boolean
name:
description: The name of the tool to use.
type: string
type:
const: tool
type: string
required:
- name
- type
type: object
BetaToolChoiceNone:
additionalProperties: false
description: The model will not be allowed to use tools.
properties:
type:
const: none
type: string
required:
- type
type: object
BetaTool.InputSchema:
additionalProperties: {}
description: >-
[JSON schema](https://json-schema.org/draft/2020-12) for this tool's
input.
This defines the shape of the `input` that your tool accepts and that
the model will produce.
properties:
properties:
anyOf:
- {}
- type: 'null'
required:
anyOf:
- items:
type: string
type: array
- type: 'null'
type:
const: object
type: string
required:
- type
type: object
ResponseCharLocationCitation:
properties:
cited_text:
title: Cited Text
type: string
document_index:
minimum: 0
title: Document Index
type: integer
document_title:
anyOf:
- type: string
- type: 'null'
title: Document Title
end_char_index:
title: End Char Index
type: integer
file_id:
anyOf:
- type: string
- type: 'null'
default: null
title: File Id
start_char_index:
minimum: 0
title: Start Char Index
type: integer
type:
const: char_location
default: char_location
title: Type
type: string
required:
- cited_text
- document_index
- document_title
- end_char_index
- file_id
- start_char_index
- type
title: Character location
type: object
ResponseContentBlockLocationCitation:
properties:
cited_text:
title: Cited Text
type: string
document_index:
minimum: 0
title: Document Index
type: integer
document_title:
anyOf:
- type: string
- type: 'null'
title: Document Title
end_block_index:
title: End Block Index
type: integer
file_id:
anyOf:
- type: string
- type: 'null'
default: null
title: File Id
start_block_index:
minimum: 0
title: Start Block Index
type: integer
type:
const: content_block_location
default: content_block_location
title: Type
type: string
required:
- cited_text
- document_index
- document_title
- end_block_index
- file_id
- start_block_index
- type
title: Content block location
type: object
ResponsePageLocationCitation:
properties:
cited_text:
title: Cited Text
type: string
document_index:
minimum: 0
title: Document Index
type: integer
document_title:
anyOf:
- type: string
- type: 'null'
title: Document Title
end_page_number:
title: End Page Number
type: integer
file_id:
anyOf:
- type: string
- type: 'null'
default: null
title: File Id
start_page_number:
minimum: 1
title: Start Page Number
type: integer
type:
const: page_location
default: page_location
title: Type
type: string
required:
- cited_text
- document_index
- document_title
- end_page_number
- file_id
- start_page_number
- type
title: Page location
type: object
ResponseSearchResultLocationCitation:
properties:
cited_text:
title: Cited Text
type: string
end_block_index:
title: End Block Index
type: integer
search_result_index:
minimum: 0
title: Search Result Index
type: integer
source:
title: Source
type: string
start_block_index:
minimum: 0
title: Start Block Index
type: integer
title:
anyOf:
- type: string
- type: 'null'
title: Title
type:
const: search_result_location
default: search_result_location
title: Type
type: string
required:
- cited_text
- end_block_index
- search_result_index
- source
- start_block_index
- title
- type
title: ResponseSearchResultLocationCitation
type: object
ResponseWebSearchResultLocationCitation:
properties:
cited_text:
title: Cited Text
type: string
encrypted_index:
title: Encrypted Index
type: string
title:
anyOf:
- maxLength: 512
type: string
- type: 'null'
title: Title
type:
const: web_search_result_location
default: web_search_result_location
title: Type
type: string
url:
title: Url
type: string
required:
- cited_text
- encrypted_index
- title
- type
- url
title: ResponseWebSearchResultLocationCitation
type: object
ResponseWebSearchToolResultError:
properties:
error_code:
$ref: '#/components/schemas/WebSearchToolResultErrorCode'
type:
const: web_search_tool_result_error
default: web_search_tool_result_error
title: Type
type: string
required:
- error_code
- type
title: ResponseWebSearchToolResultError
type: object
ResponseWebSearchResultBlock:
properties:
encrypted_content:
title: Encrypted Content
type: string
page_age:
anyOf:
- type: string
- type: 'null'
default: null
title: Page Age
title:
title: Title
type: string
type:
const: web_search_result
default: web_search_result
title: Type
type: string
url:
title: Url
type: string
required:
- encrypted_content
- page_age
- title
- type
- url
title: ResponseWebSearchResultBlock
type: object
ResponseWebFetchToolResultError:
properties:
error_code:
$ref: '#/components/schemas/WebFetchToolResultErrorCode'
type:
const: web_fetch_tool_result_error
default: web_fetch_tool_result_error
title: Type
type: string
required:
- error_code
- type
title: ResponseWebFetchToolResultError
type: object
ResponseWebFetchResultBlock:
properties:
content:
$ref: '#/components/schemas/ResponseDocumentBlock'
retrieved_at:
anyOf:
- type: string
- type: 'null'
default: null
description: ISO 8601 timestamp when the content was retrieved
title: Retrieved At
type:
const: web_fetch_result
default: web_fetch_result
title: Type
type: string
url:
description: Fetched content URL
title: Url
type: string
required:
- content
- retrieved_at
- type
- url
title: ResponseWebFetchResultBlock
type: object
ResponseCodeExecutionToolResultError:
properties:
error_code:
$ref: '#/components/schemas/CodeExecutionToolResultErrorCode'
type:
const: code_execution_tool_result_error
default: code_execution_tool_result_error
title: Type
type: string
required:
- error_code
- type
title: Code execution tool error
type: object
ResponseCodeExecutionResultBlock:
properties:
content:
items:
$ref: '#/components/schemas/ResponseCodeExecutionOutputBlock'
title: Content
type: array
return_code:
title: Return Code
type: integer
stderr:
title: Stderr
type: string
stdout:
title: Stdout
type: string
type:
const: code_execution_result
default: code_execution_result
title: Type
type: string
required:
- content
- return_code
- stderr
- stdout
- type
title: Code execution result
type: object
ResponseBashCodeExecutionToolResultError:
properties:
error_code:
$ref: '#/components/schemas/BashCodeExecutionToolResultErrorCode'
type:
const: bash_code_execution_tool_result_error
default: bash_code_execution_tool_result_error
title: Type
type: string
required:
- error_code
- type
title: ResponseBashCodeExecutionToolResultError
type: object
ResponseBashCodeExecutionResultBlock:
properties:
content:
items:
$ref: '#/components/schemas/ResponseBashCodeExecutionOutputBlock'
title: Content
type: array
return_code:
title: Return Code
type: integer
stderr:
title: Stderr
type: string
stdout:
title: Stdout
type: string
type:
const: bash_code_execution_result
default: bash_code_execution_result
title: Type
type: string
required:
- content
- return_code
- stderr
- stdout
- type
title: ResponseBashCodeExecutionResultBlock
type: object
ResponseTextEditorCodeExecutionToolResultError:
properties:
error_code:
$ref: '#/components/schemas/TextEditorCodeExecutionToolResultErrorCode'
error_message:
anyOf:
- type: string
- type: 'null'
default: null
title: Error Message
type:
const: text_editor_code_execution_tool_result_error
default: text_editor_code_execution_tool_result_error
title: Type
type: string
required:
- error_code
- error_message
- type
title: ResponseTextEditorCodeExecutionToolResultError
type: object
ResponseTextEditorCodeExecutionViewResultBlock:
properties:
content:
title: Content
type: string
file_type:
enum:
- text
- image
- pdf
title: File Type
type: string
num_lines:
anyOf:
- type: integer
- type: 'null'
default: null
title: Num Lines
start_line:
anyOf:
- type: integer
- type: 'null'
default: null
title: Start Line
total_lines:
anyOf:
- type: integer
- type: 'null'
default: null
title: Total Lines
type:
const: text_editor_code_execution_view_result
default: text_editor_code_execution_view_result
title: Type
type: string
required:
- content
- file_type
- num_lines
- start_line
- total_lines
- type
title: ResponseTextEditorCodeExecutionViewResultBlock
type: object
ResponseTextEditorCodeExecutionCreateResultBlock:
properties:
is_file_update:
title: Is File Update
type: boolean
type:
const: text_editor_code_execution_create_result
default: text_editor_code_execution_create_result
title: Type
type: string
required:
- is_file_update
- type
title: ResponseTextEditorCodeExecutionCreateResultBlock
type: object
ResponseTextEditorCodeExecutionStrReplaceResultBlock:
properties:
lines:
anyOf:
- items:
type: string
type: array
- type: 'null'
default: null
title: Lines
new_lines:
anyOf:
- type: integer
- type: 'null'
default: null
title: New Lines
new_start:
anyOf:
- type: integer
- type: 'null'
default: null
title: New Start
old_lines:
anyOf:
- type: integer
- type: 'null'
default: null
title: Old Lines
old_start:
anyOf:
- type: integer
- type: 'null'
default: null
title: Old Start
type:
const: text_editor_code_execution_str_replace_result
default: text_editor_code_execution_str_replace_result
title: Type
type: string
required:
- lines
- new_lines
- new_start
- old_lines
- old_start
- type
title: ResponseTextEditorCodeExecutionStrReplaceResultBlock
type: object
CacheCreation:
properties:
ephemeral_1h_input_tokens:
default: 0
description: The number of input tokens used to create the 1 hour cache entry.
minimum: 0
title: Ephemeral 1H Input Tokens
type: integer
ephemeral_5m_input_tokens:
default: 0
description: The number of input tokens used to create the 5 minute cache entry.
minimum: 0
title: Ephemeral 5M Input Tokens
type: integer
required:
- ephemeral_1h_input_tokens
- ephemeral_5m_input_tokens
title: CacheCreation
type: object
ServerToolUsage:
properties:
web_fetch_requests:
default: 0
description: The number of web fetch tool requests.
examples:
- 2
minimum: 0
title: Web Fetch Requests
type: integer
web_search_requests:
default: 0
description: The number of web search tool requests.
examples:
- 0
minimum: 0
title: Web Search Requests
type: integer
required:
- web_fetch_requests
- web_search_requests
title: ServerToolUsage
type: object
ResponseClearThinking20251015Edit:
properties:
cleared_input_tokens:
description: Number of input tokens cleared by this edit.
minimum: 0
title: Cleared Input Tokens
type: integer
cleared_thinking_turns:
description: Number of thinking turns that were cleared.
minimum: 0
title: Cleared Thinking Turns
type: integer
type:
const: clear_thinking_20251015
default: clear_thinking_20251015
description: The type of context management edit applied.
title: Type
type: string
required:
- cleared_input_tokens
- cleared_thinking_turns
- type
title: ResponseClearThinking20251015Edit
type: object
ResponseClearToolUses20250919Edit:
properties:
cleared_input_tokens:
description: Number of input tokens cleared by this edit.
minimum: 0
title: Cleared Input Tokens
type: integer
cleared_tool_uses:
description: Number of tool uses that were cleared.
minimum: 0
title: Cleared Tool Uses
type: integer
type:
const: clear_tool_uses_20250919
default: clear_tool_uses_20250919
description: The type of context management edit applied.
title: Type
type: string
required:
- cleared_input_tokens
- cleared_tool_uses
- type
title: ResponseClearToolUses20250919Edit
type: object
Skill:
description: A skill that was loaded in a container (response model).
properties:
skill_id:
description: Skill ID
maxLength: 64
minLength: 1
title: Skill Id
type: string
type:
description: >-
Type of skill - either 'anthropic' (built-in) or 'custom'
(user-defined)
enum:
- anthropic
- custom
title: Type
type: string
version:
description: Skill version or 'latest' for most recent version
maxLength: 64
minLength: 1
title: Version
type: string
required:
- skill_id
- type
- version
title: Skill
type: object
BetaImageBlockParam:
additionalProperties: false
properties:
cache_control:
anyOf:
- $ref: '#/components/schemas/BetaCacheControlEphemeral'
- type: 'null'
description: Create a cache control breakpoint at this content block.
source:
anyOf:
- $ref: '#/components/schemas/BetaBase64ImageSource'
- $ref: '#/components/schemas/BetaURLImageSource'
- $ref: '#/components/schemas/BetaFileImageSource'
type:
const: image
type: string
required:
- source
- type
type: object
BetaRequestDocumentBlock:
additionalProperties: false
properties:
cache_control:
anyOf:
- $ref: '#/components/schemas/BetaCacheControlEphemeral'
- type: 'null'
description: Create a cache control breakpoint at this content block.
citations:
anyOf:
- $ref: '#/components/schemas/BetaCitationsConfigParam'
- type: 'null'
context:
type:
- string
- 'null'
source:
anyOf:
- $ref: '#/components/schemas/BetaBase64PDFSource'
- $ref: '#/components/schemas/BetaPlainTextSource'
- $ref: '#/components/schemas/BetaContentBlockSource'
- $ref: '#/components/schemas/BetaURLPDFSource'
- $ref: '#/components/schemas/BetaFileDocumentSource'
title:
type:
- string
- 'null'
type:
const: document
type: string
required:
- source
- type
type: object
BetaSearchResultBlockParam:
additionalProperties: false
properties:
cache_control:
anyOf:
- $ref: '#/components/schemas/BetaCacheControlEphemeral'
- type: 'null'
description: Create a cache control breakpoint at this content block.
citations:
$ref: '#/components/schemas/BetaCitationsConfigParam'
content:
items:
$ref: '#/components/schemas/BetaTextBlockParam'
type: array
source:
type: string
title:
type: string
type:
const: search_result
type: string
required:
- content
- source
- title
- type
type: object
BetaThinkingBlockParam:
additionalProperties: false
properties:
signature:
type: string
thinking:
type: string
type:
const: thinking
type: string
required:
- signature
- thinking
- type
type: object
BetaRedactedThinkingBlockParam:
additionalProperties: false
properties:
data:
type: string
type:
const: redacted_thinking
type: string
required:
- data
- type
type: object
BetaToolUseBlockParam:
additionalProperties: false
properties:
cache_control:
anyOf:
- $ref: '#/components/schemas/BetaCacheControlEphemeral'
- type: 'null'
description: Create a cache control breakpoint at this content block.
caller:
anyOf:
- $ref: '#/components/schemas/BetaDirectCaller'
- $ref: '#/components/schemas/BetaServerToolCaller'
- $ref: '#/components/schemas/BetaServerToolCaller20260120'
description: Tool invocation directly from the model.
id:
type: string
input: {}
name:
type: string
type:
const: tool_use
type: string
required:
- id
- input
- name
- type
type: object
BetaToolResultBlockParam:
additionalProperties: false
properties:
cache_control:
anyOf:
- $ref: '#/components/schemas/BetaCacheControlEphemeral'
- type: 'null'
description: Create a cache control breakpoint at this content block.
content:
anyOf:
- type: string
- items:
anyOf:
- $ref: '#/components/schemas/BetaTextBlockParam'
- $ref: '#/components/schemas/BetaImageBlockParam'
- $ref: '#/components/schemas/BetaSearchResultBlockParam'
- $ref: '#/components/schemas/BetaRequestDocumentBlock'
- $ref: '#/components/schemas/BetaToolReferenceBlockParam'
type: array
is_error:
type: boolean
tool_use_id:
type: string
type:
const: tool_result
type: string
required:
- tool_use_id
- type
type: object
BetaCitationCharLocationParam:
additionalProperties: false
properties:
cited_text:
type: string
document_index:
type: number
document_title:
type:
- string
- 'null'
end_char_index:
type: number
start_char_index:
type: number
type:
const: char_location
type: string
required:
- cited_text
- document_index
- document_title
- end_char_index
- start_char_index
- type
type: object
BetaCitationPageLocationParam:
additionalProperties: false
properties:
cited_text:
type: string
document_index:
type: number
document_title:
type:
- string
- 'null'
end_page_number:
type: number
start_page_number:
type: number
type:
const: page_location
type: string
required:
- cited_text
- document_index
- document_title
- end_page_number
- start_page_number
- type
type: object
BetaCitationContentBlockLocationParam:
additionalProperties: false
properties:
cited_text:
description: >-
The full text of the cited block range, concatenated.
Always equals the contents of
`content[start_block_index:end_block_index]` joined together. The
text block is the minimal citable unit; this field is never a
substring of a single block. Not counted toward output tokens, and
not counted toward input tokens when sent back in subsequent turns.
type: string
document_index:
type: number
document_title:
type:
- string
- 'null'
end_block_index:
description: >-
Exclusive 0-based end index of the cited block range in the source's
`content` array.
Always greater than `start_block_index`; a single-block citation has
`end_block_index = start_block_index + 1`.
type: number
start_block_index:
description: >-
0-based index of the first cited block in the source's `content`
array.
type: number
type:
const: content_block_location
type: string
required:
- cited_text
- document_index
- document_title
- end_block_index
- start_block_index
- type
type: object
BetaCitationWebSearchResultLocationParam:
additionalProperties: false
properties:
cited_text:
type: string
encrypted_index:
type: string
title:
type:
- string
- 'null'
type:
const: web_search_result_location
type: string
url:
type: string
required:
- cited_text
- encrypted_index
- title
- type
- url
type: object
BetaCitationSearchResultLocationParam:
additionalProperties: false
properties:
cited_text:
description: >-
The full text of the cited block range, concatenated.
Always equals the contents of
`content[start_block_index:end_block_index]` joined together. The
text block is the minimal citable unit; this field is never a
substring of a single block. Not counted toward output tokens, and
not counted toward input tokens when sent back in subsequent turns.
type: string
end_block_index:
description: >-
Exclusive 0-based end index of the cited block range in the source's
`content` array.
Always greater than `start_block_index`; a single-block citation has
`end_block_index = start_block_index + 1`.
type: number
search_result_index:
description: >-
0-based index of the cited search result among all `search_result`
content blocks in the request, in the order they appear across
messages and tool results.
Counted separately from `document_index`; server-side web search
results are not included in this count.
type: number
source:
type: string
start_block_index:
description: >-
0-based index of the first cited block in the source's `content`
array.
type: number
title:
type:
- string
- 'null'
type:
const: search_result_location
type: string
required:
- cited_text
- end_block_index
- search_result_index
- source
- start_block_index
- title
- type
type: object
WebSearchToolResultErrorCode:
enum:
- invalid_tool_input
- unavailable
- max_uses_exceeded
- too_many_requests
- query_too_long
title: WebSearchToolResultErrorCode
type: string
WebFetchToolResultErrorCode:
enum:
- invalid_tool_input
- url_too_long
- url_not_allowed
- url_not_accessible
- unsupported_content_type
- too_many_requests
- max_uses_exceeded
- unavailable
title: WebFetchToolResultErrorCode
type: string
ResponseDocumentBlock:
properties:
citations:
anyOf:
- $ref: '#/components/schemas/ResponseCitationsConfig'
- type: 'null'
default: null
description: Citation configuration for the document
source:
discriminator:
mapping:
base64:
$ref: '#/components/schemas/Base64PDFSource'
text:
$ref: '#/components/schemas/PlainTextSource'
propertyName: type
oneOf:
- $ref: '#/components/schemas/Base64PDFSource'
- $ref: '#/components/schemas/PlainTextSource'
title: Source
title:
anyOf:
- type: string
- type: 'null'
default: null
description: The title of the document
title: Title
type:
const: document
default: document
title: Type
type: string
required:
- citations
- source
- title
- type
title: ResponseDocumentBlock
type: object
CodeExecutionToolResultErrorCode:
enum:
- invalid_tool_input
- unavailable
- too_many_requests
- execution_time_exceeded
title: CodeExecutionToolResultErrorCode
type: string
ResponseCodeExecutionOutputBlock:
properties:
file_id:
title: File Id
type: string
type:
const: code_execution_output
default: code_execution_output
title: Type
type: string
required:
- file_id
- type
title: ResponseCodeExecutionOutputBlock
type: object
BashCodeExecutionToolResultErrorCode:
enum:
- invalid_tool_input
- unavailable
- too_many_requests
- execution_time_exceeded
- output_file_too_large
title: BashCodeExecutionToolResultErrorCode
type: string
ResponseBashCodeExecutionOutputBlock:
properties:
file_id:
title: File Id
type: string
type:
const: bash_code_execution_output
default: bash_code_execution_output
title: Type
type: string
required:
- file_id
- type
title: ResponseBashCodeExecutionOutputBlock
type: object
TextEditorCodeExecutionToolResultErrorCode:
enum:
- invalid_tool_input
- unavailable
- too_many_requests
- execution_time_exceeded
- file_not_found
title: TextEditorCodeExecutionToolResultErrorCode
type: string
BetaBase64ImageSource:
additionalProperties: false
properties:
data:
type: string
media_type:
enum:
- image/jpeg
- image/png
- image/gif
- image/webp
type: string
type:
const: base64
type: string
required:
- data
- media_type
- type
type: object
BetaURLImageSource:
additionalProperties: false
properties:
type:
const: url
type: string
url:
type: string
required:
- type
- url
type: object
BetaFileImageSource:
additionalProperties: false
properties:
file_id:
type: string
type:
const: file
type: string
required:
- file_id
- type
type: object
BetaCitationsConfigParam:
additionalProperties: false
properties:
enabled:
type: boolean
type: object
BetaBase64PDFSource:
additionalProperties: false
properties:
data:
type: string
media_type:
const: application/pdf
type: string
type:
const: base64
type: string
required:
- data
- media_type
- type
type: object
BetaPlainTextSource:
additionalProperties: false
properties:
data:
type: string
media_type:
const: text/plain
type: string
type:
const: text
type: string
required:
- data
- media_type
- type
type: object
BetaContentBlockSource:
additionalProperties: false
properties:
content:
anyOf:
- type: string
- items:
$ref: '#/components/schemas/BetaContentBlockSourceContent'
type: array
type:
const: content
type: string
required:
- content
- type
type: object
BetaURLPDFSource:
additionalProperties: false
properties:
type:
const: url
type: string
url:
type: string
required:
- type
- url
type: object
BetaFileDocumentSource:
additionalProperties: false
properties:
file_id:
type: string
type:
const: file
type: string
required:
- file_id
- type
type: object
BetaDirectCaller:
additionalProperties: false
description: Tool invocation directly from the model.
properties:
type:
const: direct
type: string
required:
- type
type: object
BetaServerToolCaller:
additionalProperties: false
description: Tool invocation generated by a server-side tool.
properties:
tool_id:
type: string
type:
const: code_execution_20250825
type: string
required:
- tool_id
- type
type: object
BetaServerToolCaller20260120:
additionalProperties: false
properties:
tool_id:
type: string
type:
const: code_execution_20260120
type: string
required:
- tool_id
- type
type: object
BetaToolReferenceBlockParam:
additionalProperties: false
description: Tool reference block that can be included in tool_result content.
properties:
cache_control:
anyOf:
- $ref: '#/components/schemas/BetaCacheControlEphemeral'
- type: 'null'
description: Create a cache control breakpoint at this content block.
tool_name:
type: string
type:
const: tool_reference
type: string
required:
- tool_name
- type
type: object
ResponseCitationsConfig:
properties:
enabled:
default: false
title: Enabled
type: boolean
required:
- enabled
title: ResponseCitationsConfig
type: object
Base64PDFSource:
additionalProperties: false
properties:
data:
format: byte
title: Data
type: string
media_type:
const: application/pdf
title: Media Type
type: string
type:
const: base64
title: Type
type: string
required:
- data
- media_type
- type
title: PDF (base64)
type: object
PlainTextSource:
additionalProperties: false
properties:
data:
title: Data
type: string
media_type:
const: text/plain
title: Media Type
type: string
type:
const: text
title: Type
type: string
required:
- data
- media_type
- type
title: Plain text
type: object
BetaContentBlockSourceContent:
anyOf:
- $ref: '#/components/schemas/BetaTextBlockParam'
- $ref: '#/components/schemas/BetaImageBlockParam'
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: >-
##All APIs require Bearer Token authentication##
**Get API Key:**
Visit [API Key Management Page](https://evolink.ai/dashboard/keys) to
get your API Key
**Add to request header:**
```
Authorization: Bearer YOUR_API_KEY
```
````