nexos.ai Chat API
Generate a response from conversation messages.
OpenAPI Specification
openapi: 3.0.0
info:
title: Nexos AI Public API Production Agent Management Chat API
version: 1.0.0
description: Manage agents.
servers:
- url: https://api.nexos.ai
security:
- bearerAuth: []
- apiKeyHeader: []
tags:
- name: Chat
description: Generate a response from conversation messages.
paths:
/v1/chat/completions:
post:
tags:
- Chat
operationId: post-chat-completions-v1
summary: Create chat completion
description: Generate a response from conversation messages.
parameters:
- in: query
name: fallbacks
schema:
type: string
enum:
- 'true'
- 'false'
required: false
description: To use or not fallbacks in chat completion request
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionsRequest'
responses:
'200':
$ref: '#/components/responses/ChatCompletionsResponse'
'400':
description: Invalid request data.
'402':
$ref: '#/components/responses/OutOfCredits'
'500':
description: Server error.
components:
schemas:
chat_completions_messages_ChatCompletionRequestAssistantMessage:
type: object
title: Assistant message
description: 'Messages sent by the model in response to user messages.
'
properties:
content:
nullable: true
oneOf:
- type: string
description: The contents of the assistant message.
title: Text content
- type: array
description: An array of content parts with a defined type. Can be one or more of type `text`, or exactly one of type `refusal`.
title: Array of content parts
items:
$ref: '#/components/schemas/chat_completions_messages_ChatCompletionRequestAssistantMessageContentPart'
minItems: 1
description: 'The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified.
'
refusal:
nullable: true
type: string
description: The refusal message by the assistant.
role:
type: string
enum:
- assistant
description: The role of the messages author, in this case `assistant`.
name:
type: string
description: An optional name for the participant. Provides the model information to differentiate between participants of the same role.
audio:
type: object
nullable: true
description: "Data about a previous audio response from the model. \n[Learn more](/docs/guides/audio).\n"
required:
- id
properties:
id:
type: string
description: 'Unique identifier for a previous audio response from the model.
'
tool_calls:
$ref: '#/components/schemas/chat_completions_messages_ChatCompletionMessageToolCalls'
function_call:
type: object
deprecated: true
description: Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model.
nullable: true
properties:
arguments:
type: string
description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.
name:
type: string
description: The name of the function to call.
required:
- arguments
- name
required:
- role
UserLocation:
type: object
required:
- type
properties:
type:
type: string
description: The type of location approximation.
enum:
- approximate
city:
type: string
description: The city to use for the location approximation.
country:
type: string
description: The two-letter ISO country code of the user.
region:
type: string
description: Free text input for the region of the user.
timezone:
type: string
description: The IANA timezone of the user.
chat_completions_messages_ChatCompletionRequestToolMessageContentPart:
oneOf:
- $ref: '#/components/schemas/chat_completions_messages_ChatCompletionRequestMessageContentPartText'
ChatCompletionModalities:
type: array
description: 'Output types that you would like the model to generate for this request.
Most models are capable of generating text, which is the default:
`["text"]`
To request that this model generate both text and audio responses, you can use:
`["text", "audio"]`
'
items:
type: string
enum:
- text
- audio
ChatCompletionToolChoiceOption:
description: 'Controls which (if any) tool is called by the model.
`none` means the model will not call any tool and instead generates a message.
`auto` means the model can pick between generating a message or calling one or more tools.
`required` means the model must call one or more tools.
Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool.
`none` is the default when no tools are present. `auto` is the default if tools are present.
'
oneOf:
- type: string
description: '`none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools.
'
enum:
- none
- auto
- required
- $ref: '#/components/schemas/ChatCompletionNamedToolChoice'
URLSearch:
type: object
required:
- tool
- url
properties:
tool:
type: string
description: The type of the web search.
enum:
- universal
url:
type: string
description: The URL to search for.
geo_location:
type: string
description: The geographic location to use for the search.
parse:
type: boolean
description: Whether to parse the search results.
default: false
chat_completions_messages_ChatCompletionRequestUserMessage:
type: object
title: User message
description: 'Messages sent by an end user, containing prompts or additional context
information.
'
properties:
content:
description: 'The contents of the user message.
'
oneOf:
- type: string
description: The text contents of the message.
title: Text content
- type: array
description: An array of content parts with a defined type. Supported options differ based on the [model](/docs/models) being used to generate the response. Can contain text, image, or audio inputs.
title: Array of content parts
items:
$ref: '#/components/schemas/chat_completions_messages_ChatCompletionRequestUserMessageContentPart'
minItems: 1
role:
type: string
enum:
- user
description: The role of the messages author, in this case `user`.
name:
type: string
description: An optional name for the participant. Provides the model information to differentiate between participants of the same role.
required:
- content
- role
ResponseFormatJsonSchemaSchema:
type: object
description: The schema for the response format, described as a JSON Schema object.
additionalProperties: true
ChatCompletionWebSearch:
type: object
description: The web search that the model called.
properties:
search_context_size:
type: string
description: High level guidance for the amount of context window space to use for the search.
enum:
- low
- medium
- high
user_location:
$ref: '#/components/schemas/UserLocation'
mcp:
$ref: '#/components/schemas/WebSearchMCP'
ChatCompletionsRequest:
type: object
properties:
messages:
description: 'A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio.
'
type: array
minItems: 1
items:
$ref: '#/components/schemas/chat_completions_messages_ChatCompletionRequestMessage'
model:
type: string
description: Model name, UUID, or agent UUID.
store:
type: boolean
description: 'Whether or not to store the output of this chat completion request
'
metadata:
type: object
description: 'Developer-defined tags and values used for filtering completions
in the dashboard.
'
additionalProperties:
type: string
frequency_penalty:
type: number
default: 0
minimum: -2
maximum: 2
description: 'Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model''s likelihood to repeat the same line verbatim.
'
logit_bias:
type: object
additionalProperties:
type: integer
description: 'Modify the likelihood of specified tokens appearing in the completion.
Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.
'
logprobs:
description: Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`.
type: boolean
top_logprobs:
description: An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used.
type: integer
minimum: 0
maximum: 20
max_tokens:
description: 'The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API.
This value is now deprecated in favor of `max_completion_tokens`, and is not compatible with o1 series models.
'
type: integer
nullable: true
deprecated: true
max_completion_tokens:
description: 'An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.
'
type: integer
nullable: true
n:
type: integer
minimum: 1
maximum: 128
default: 1
description: How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs.
modalities:
$ref: '#/components/schemas/ChatCompletionModalities'
prediction:
description: 'Configuration for a Predicted Output,
which can greatly improve response times when large parts of the model
response are known ahead of time. This is most common when you are
regenerating a file with only minor changes to most of the content.
'
oneOf:
- $ref: '#/components/schemas/PredictionContent'
audio:
type: object
description: 'Parameters for audio output. Required when audio output is requested with
`modalities: ["audio"]`.
'
required:
- voice
- format
properties:
voice:
type: string
enum:
- alloy
- ash
- ballad
- coral
- echo
- sage
- shimmer
- verse
description: 'The voice the model uses to respond. Supported voices are `alloy`,
`ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, and `verse`.
'
format:
type: string
enum:
- wav
- mp3
- flac
- opus
- pcm16
description: 'Specifies the output audio format. Must be one of `wav`, `mp3`, `flac`,
`opus`, or `pcm16`.
'
presence_penalty:
type: number
default: 0
minimum: -2
maximum: 2
description: 'Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model''s likelihood to talk about new topics.
'
response_format:
description: 'An object specifying the format that the model must output. Compatible with GPT-4o, GPT-4o mini, GPT-4 Turbo and all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which ensures the model will match your supplied JSON schema.
Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the message the model generates is valid JSON.
**Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length.
'
oneOf:
- $ref: '#/components/schemas/ResponseFormatText'
- $ref: '#/components/schemas/ResponseFormatJsonObject'
- $ref: '#/components/schemas/ResponseFormatJsonSchema'
seed:
type: integer
minimum: -9223372036854776000
maximum: 9223372036854776000
description: 'This feature is in Beta.
If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result.
Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.
'
service_tier:
description: 'Specifies the processing type used for serving the request.
If set to ''default'' or ''auto'', then the request will be processed with the standard pricing and performance for the selected model.
If set to ''flex'' or ''priority'', then the request will be processed with the corresponding service tier.
When not set, the default behavior is ''auto''.
When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.
'
type: string
enum:
- auto
- default
- flex
- scale
- priority
default: auto
stop:
description: 'Up to 4 sequences where the API will stop generating further tokens.
'
oneOf:
- type: string
- type: array
minItems: 1
maxItems: 4
items:
type: string
stream:
description: 'If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message.
'
type: boolean
stream_options:
$ref: '#/components/schemas/ChatCompletionStreamOptions'
temperature:
type: number
minimum: 0
maximum: 2
default: 1
description: 'What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
We generally recommend altering this or `top_p` but not both.
'
top_p:
type: number
minimum: 0
maximum: 1
default: 1
description: 'An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or `temperature` but not both.
'
tools:
type: array
description: 'A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.
'
items:
$ref: '#/components/schemas/ChatCompletionTool'
tool_choice:
$ref: '#/components/schemas/ChatCompletionToolChoiceOption'
parallel_tool_calls:
$ref: '#/components/schemas/ParallelToolCalls'
function_call:
deprecated: true
description: 'Deprecated in favor of `tool_choice`.
Controls which (if any) function is called by the model.
`none` means the model will not call a function and instead generates a message.
`auto` means the model can pick between generating a message or calling a function.
Specifying a particular function via `{"name": "my_function"}` forces the model to call that function.
`none` is the default when no functions are present. `auto` is the default if functions are present.
'
oneOf:
- type: string
description: '`none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function.
'
enum:
- none
- auto
- $ref: '#/components/schemas/ChatCompletionFunctionCallOption'
functions:
deprecated: true
description: 'Deprecated in favor of `tools`.
A list of functions the model may generate JSON inputs for.
'
type: array
minItems: 1
maxItems: 128
items:
$ref: '#/components/schemas/ChatCompletionFunctions'
thinking:
type: object
properties:
type:
type: string
description: The type of thinking configuration
budget_tokens:
type: integer
description: The token budget allocation for thinking operations
reasoning_effort:
type: string
description: Reasoning effort for models that support reasoning.
enum:
- none
- minimal
- low
- medium
- high
- xhigh
- max
verbosity:
type: string
description: Constrains the verbosity of the model's response.
enum:
- low
- medium
- high
required:
- model
- messages
ChatCompletionTool:
type: object
properties:
type:
type: string
enum:
- function
- web_search
- rag
- tika_ocr
description: The type of the tool. Supports `function`, `web_search`, `rag` and `tika_ocr`.
function:
$ref: '#/components/schemas/FunctionObject'
web_search:
$ref: '#/components/schemas/ChatCompletionWebSearch'
rag:
$ref: '#/components/schemas/ChatCompletionRAG'
tika_ocr:
$ref: '#/components/schemas/ChatCompletionTikaOCR'
required:
- type
chat_completions_messages_ChatCompletionMessageToolCall:
type: object
properties:
id:
type: string
description: The ID of the tool call.
type:
type: string
enum:
- function
description: The type of the tool. Currently, only `function` is supported.
function:
type: object
description: The function that the model called.
properties:
name:
type: string
description: The name of the function to call.
arguments:
type: string
description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.
required:
- name
- arguments
required:
- id
- type
- function
ChatCompletionRequestMessageContentPartText:
type: object
title: Text content part
properties:
type:
type: string
enum:
- text
description: The type of the content part.
text:
type: string
description: The text content.
required:
- type
- text
chat_completions_messages_ChatCompletionRequestSystemMessageContentPart:
oneOf:
- $ref: '#/components/schemas/chat_completions_messages_ChatCompletionRequestMessageContentPartText'
ParallelToolCalls:
description: Whether to enable parallel function calling during tool use.
type: boolean
default: true
ChatCompletionFunctionCallOption:
type: object
description: 'Specifying a particular function via `{"name": "my_function"}` forces the model to call that function.
'
properties:
name:
type: string
description: The name of the function to call.
required:
- name
chat_completions_messages_ChatCompletionRequestMessage:
oneOf:
- $ref: '#/components/schemas/ChatCompletionRequestDeveloperMessage'
- $ref: '#/components/schemas/chat_completions_messages_ChatCompletionRequestSystemMessage'
- $ref: '#/components/schemas/chat_completions_messages_ChatCompletionRequestUserMessage'
- $ref: '#/components/schemas/chat_completions_messages_ChatCompletionRequestAssistantMessage'
- $ref: '#/components/schemas/chat_completions_messages_ChatCompletionRequestToolMessage'
- $ref: '#/components/schemas/chat_completions_messages_ChatCompletionRequestFunctionMessage'
FunctionObject:
type: object
properties:
description:
type: string
description: A description of what the function does, used by the model to choose when and how to call the function.
name:
type: string
description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
parameters:
$ref: '#/components/schemas/FunctionParameters'
strict:
type: boolean
nullable: true
default: false
description: Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the `parameters` field. Only a subset of JSON Schema is supported when `strict` is `true`.
required:
- name
WebSearchMCP:
type: object
description: Custom MCP web_search
required:
- type
- options`
properties:
type:
type: string
description: The type of the web search.
enum:
- url
- query
options:
oneOf:
- $ref: '#/components/schemas/QuerySearch'
- $ref: '#/components/schemas/URLSearch'
chat_completions_messages_ChatCompletionMessageToolCalls:
type: array
description: The tool calls generated by the model, such as function calls.
items:
$ref: '#/components/schemas/chat_completions_messages_ChatCompletionMessageToolCall'
chat_completions_messages_ChatCompletionRequestToolMessage:
type: object
title: Tool message
properties:
role:
type: string
enum:
- tool
description: The role of the messages author, in this case `tool`.
content:
oneOf:
- type: string
description: The contents of the tool message.
title: Text content
- type: array
description: An array of content parts with a defined type. For tool messages, only type `text` is supported.
title: Array of content parts
items:
$ref: '#/components/schemas/chat_completions_messages_ChatCompletionRequestToolMessageContentPart'
minItems: 1
description: The contents of the tool message.
tool_call_id:
type: string
description: Tool call that this message is responding to.
required:
- role
- content
- tool_call_id
ResponseFormatText:
type: object
properties:
type:
type: string
description: 'The type of response format being defined: `text`'
enum:
- text
required:
- type
PredictionContent:
type: object
title: Static Content
description: 'Static predicted output content, such as the content of a text file that is being regenerated.
'
required:
- type
- content
properties:
type:
type: string
enum:
- content
description: 'The type of the predicted content you want to provide. This type is
currently always `content`.
'
content:
description: 'The content that should be matched when generating a model response.
If generated tokens would match this content, the entire model response
can be returned much more quickly.
'
oneOf:
- type: string
title: Text content
description: 'The content used for a Predicted Output. This is often the
text of a file you are regenerating with minor changes.
'
- type: array
description: An array of content parts with a defined type. Supported options differ based on the [model](/docs/models) being used to generate the response. Can contain text inputs.
title: Array of content parts
items:
$ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText'
minItems: 1
chat_completions_messages_ChatCompletionRequestUserMessageContentPart:
oneOf:
- $ref: '#/components/schemas/chat_completions_messages_ChatCompletionRequestMessageContentPartText'
- $ref: '#/components/schemas/chat_completions_messages_ChatCompletionRequestMessageContentPartImage'
- $ref: '#/components/schemas/chat_completions_messages_ChatCompletionRequestMessageContentPartAudio'
ResponseFormatJsonSchema:
type: object
properties:
type:
type: string
description: 'The type of response format being defined: `json_schema`'
enum:
- json_schema
json_schema:
type: object
properties:
description:
type: string
description: A description of what the response format is for, used by the model to determine how to respond in the format.
name:
type: string
description: The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
schema:
$ref: '#/components/schemas/ResponseFormatJsonSchemaSchema'
strict:
type: boolean
nullable: true
default: false
description: Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the `schema` field. Only a subset of JSON Schema is supported when `strict` is `true`. To learn more, read the [Structured Outputs guide](/docs/guides/structured-outputs).
required:
- type
- name
required:
- type
- json_schema
ChatCompletionNamedToolChoice:
type: object
description: Specifies a tool the model should use. Use to force the model to call a specific function.
properties:
type:
type: string
enum:
- function
description: The type of the tool. Currently, only `function` is supported.
function:
type: object
properties:
name:
type: string
description: The name of the function to call.
required:
- name
required:
- type
- function
ResponseFormatJsonObject:
type: object
properties:
type:
type: string
description: 'The type of response format being defined: `json_object`'
enum:
- json_object
required:
- type
ChatCompletionTikaOCR:
type: object
description: Tika OCR that the model called.
properties:
file_id:
type: string
required:
- file_id
chat_completions_messages_ChatCompletionRequestSystemMessage:
type: object
title: System message
description: 'Developer-provided instructions that the model should follow, regardless of
messages sent by the user. With o1 models and newer, use `developer` messages
for this purpose instead.
'
properties:
content:
description: The contents of the system message.
oneOf:
- type: string
description: The contents of the system message.
title: Text content
- type: array
description: An array of content parts with a defined type. For system messages, only type `text` is supported.
title: Array of content parts
items:
$ref: '#/components/schemas/chat_completions_messages_ChatCompletionRequestSystemMessageContentPart'
minItems: 1
role:
type: string
enum:
- system
description: The role of the messages author, in this case `system`.
name:
type: string
description: An optional name for the participant. Provides the model information to differentiate between participants of the same role.
required:
- content
- role
chat_completions_messages_ChatCompletionRequestMessageContentPartAudio:
type: object
title: Audio content part
description: 'Learn about [audio inputs](/docs/guides/audio).
'
# --- truncated at 32 KB (39 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/nexosai/refs/heads/main/openapi/nexosai-chat-api-openapi.yml