openapi: 3.0.0
info:
title: Portkey Analytics > Graphs Chat API
description: The Portkey REST API. Please see https://portkey.ai/docs/api-reference for more details.
version: 2.0.0
termsOfService: https://portkey.ai/terms
contact:
name: Portkey Developer Forum
url: https://portkey.wiki/community
license:
name: MIT
url: https://github.com/Portkey-AI/portkey-openapi/blob/master/LICENSE
servers:
- url: https://api.portkey.ai/v1
description: Portkey API Public Endpoint
security:
- Portkey-Key: []
tags:
- name: Chat
description: Given a list of messages comprising a conversation, the model will return a response.
paths:
/chat/completions:
servers:
- url: https://api.portkey.ai/v1
description: Portkey API Public Endpoint
- url: SELF_HOSTED_GATEWAY_URL
description: Self-Hosted Gateway URL
post:
operationId: createChatCompletion
tags:
- Chat
summary: Chat
parameters:
- $ref: '#/components/parameters/PortkeyTraceId'
- $ref: '#/components/parameters/PortkeySpanId'
- $ref: '#/components/parameters/PortkeyParentSpanId'
- $ref: '#/components/parameters/PortkeySpanName'
- $ref: '#/components/parameters/PortkeyMetadata'
- $ref: '#/components/parameters/PortkeyCacheNamespace'
- $ref: '#/components/parameters/PortkeyCacheForceRefresh'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/CreateChatCompletionRequest'
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/CreateChatCompletionResponse'
security:
- Portkey-Key: []
Virtual-Key: []
- Portkey-Key: []
Provider-Auth: []
Provider-Name: []
- Portkey-Key: []
Config: []
- Portkey-Key: []
Provider-Auth: []
Provider-Name: []
Custom-Host: []
x-code-samples:
- lang: cURL
label: Default
source: "curl https://api.portkey.ai/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"x-portkey-api-key: $PORTKEY_API_KEY\" \\\n -H \"x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY\" \\\n -d '{\n \"model\": \"gpt-5\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Hello!\"\n }\n ],\n \"max_completion_tokens\": 250\n }'\n"
- lang: cURL
label: Self-Hosted
source: "curl SELF_HOSTED_GATEWAY_URL/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"x-portkey-api-key: $PORTKEY_API_KEY\" \\\n -H \"x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY\" \\\n -d '{\n \"model\": \"gpt-5\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Hello!\"\n }\n ],\n \"max_completion_tokens\": 250\n }'\n"
- lang: python
label: Default
source: "from portkey_ai import Portkey\n\nportkey = Portkey(\n api_key = \"PORTKEY_API_KEY\",\n virtual_key = \"PROVIDER_VIRTUAL_KEY\"\n)\n\nresponse = portkey.chat.completions.create(\n model=\"gpt-5\",\n messages=[\n {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n {\"role\": \"user\", \"content\": \"Hello!\"}\n ],\n max_completion_tokens=250\n)\n\nprint(response.choices[0].message)\n"
- lang: python
label: Self-Hosted
source: "from portkey_ai import Portkey\n\nportkey = Portkey(\n api_key = \"PORTKEY_API_KEY\",\n base_url = \"SELF_HOSTED_GATEWAY_URL\",\n virtual_key = \"PROVIDER_VIRTUAL_KEY\"\n)\n\nresponse = portkey.chat.completions.create(\n model=\"gpt-5\",\n messages=[\n {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n {\"role\": \"user\", \"content\": \"Hello!\"}\n ],\n max_completion_tokens=250\n)\n\nprint(response.choices[0].message)\n"
- lang: javascript
label: Default
source: "import Portkey from 'portkey-ai';\n\nconst portkey = new Portkey({\n apiKey: 'PORTKEY_API_KEY',\n virtualKey: 'PROVIDER_VIRTUAL_KEY'\n});\n\nasync function main() {\n const response = await portkey.chat.completions.create({\n messages: [{ role: \"system\", content: \"You are a helpful assistant.\" }],\n model: \"gpt-5\",\n max_completion_tokens: 250,\n });\n\n console.log(response.choices[0]);\n}\n\nmain();\n"
- lang: javascript
label: Self-Hosted
source: "import Portkey from 'portkey-ai';\n\nconst portkey = new Portkey({\n apiKey: 'PORTKEY_API_KEY',\n virtualKey: 'PROVIDER_VIRTUAL_KEY',\n baseUrl: 'SELF_HOSTED_GATEWAY_URL'\n});\n\nasync function main() {\n const response = await portkey.chat.completions.create({\n messages: [{ role: \"system\", content: \"You are a helpful assistant.\" }],\n model: \"gpt-5\",\n max_completion_tokens: 250,\n });\n\n console.log(response.choices[0]);\n}\n\nmain();\n"
components:
schemas:
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'
x-oaiExpandable: true
ChatCompletionRequestAssistantMessage:
type: object
title: Assistant message
properties:
content:
nullable: true
type: string
description: 'The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified.
'
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.
tool_calls:
$ref: '#/components/schemas/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
ChatCompletionRequestDeveloperMessage:
type: object
title: Developer message
description: New role by OpenAI for select models. Must be explicitly used for models that support it. When used with incompatible models or providers, Portkey automatically converts it to a system role.
properties:
content:
description: The contents of the Developer message.
type: string
role:
type: string
enum:
- developer
description: The role of the messages author, in this case `Developer`.
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
ChatCompletionRequestSystemMessage:
type: object
title: System message
properties:
content:
description: The contents of the system message.
type: string
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
ChatCompletionTokenLogprob:
type: object
properties:
token: &id001
description: The token.
type: string
logprob: &id002
description: The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely.
type: number
bytes: &id003
description: A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token.
type: array
items:
type: integer
nullable: true
top_logprobs:
description: List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested `top_logprobs` returned.
type: array
items:
type: object
properties:
token: *id001
logprob: *id002
bytes: *id003
required:
- token
- logprob
- bytes
required:
- token
- logprob
- bytes
- top_logprobs
ParallelToolCalls:
description: Whether to enable [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling) during tool use.
type: boolean
default: true
ChatCompletionRequestMessage:
oneOf:
- $ref: '#/components/schemas/ChatCompletionRequestSystemMessage'
- $ref: '#/components/schemas/ChatCompletionRequestDeveloperMessage'
- $ref: '#/components/schemas/ChatCompletionRequestUserMessage'
- $ref: '#/components/schemas/ChatCompletionRequestAssistantMessage'
- $ref: '#/components/schemas/ChatCompletionRequestToolMessage'
- $ref: '#/components/schemas/ChatCompletionRequestFunctionMessage'
x-oaiExpandable: true
CreateChatCompletionRequest:
type: object
properties:
messages:
description: A list of messages comprising the conversation so far. [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models).
type: array
minItems: 1
items:
$ref: '#/components/schemas/ChatCompletionRequestMessage'
model:
description: ID of the model to use. See the [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility) table for details on which models work with the Chat API.
example: gpt-5
anyOf:
- type: string
- type: string
enum:
- gpt-5
- gpt-5-mini
- gpt-5-nano
- o4-mini
- o3
- o3-mini
- o1
- o1-mini
- gpt-4o
- gpt-4o-mini
- gpt-4o-2024-05-13
- gpt-4-turbo
- gpt-4-turbo-2024-04-09
- gpt-4-0125-preview
- gpt-4-turbo-preview
- gpt-4-1106-preview
- gpt-4-vision-preview
- gpt-4
- gpt-4-0314
- gpt-4-0613
- gpt-4-32k
- gpt-4-32k-0314
- gpt-4-32k-0613
- gpt-3.5-turbo
- gpt-3.5-turbo-16k
- gpt-3.5-turbo-0301
- gpt-3.5-turbo-0613
- gpt-3.5-turbo-1106
- gpt-3.5-turbo-0125
- gpt-3.5-turbo-16k-0613
x-oaiTypeLabel: string
frequency_penalty:
type: number
default: 0
minimum: -2
maximum: 2
nullable: true
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.
[See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
'
logit_bias:
type: object
x-oaiTypeLabel: map
default: null
nullable: true
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
default: false
nullable: true
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
nullable: true
max_tokens:
description: 'Deprecated in favor of `max_completion_tokens`.
The maximum number of [tokens](https://platform.openai.com/tokenizer?view=bpe) that can be generated in the chat completion. This value can be used to control [costs](https://openai.com/api/pricing/) for text generated via API.
**Supported models:** GPT-4o, GPT-4o-mini, GPT-4, GPT-4 Turbo, GPT-3.5 Turbo.
**Not supported:** o-series reasoning models (o1, o3, o3-mini, o4-mini) and GPT-5 series — use `max_completion_tokens` instead.
'
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](https://platform.openai.com/docs/guides/reasoning).
**Supported models:** GPT-5 series, o-series reasoning models (o1, o3, o3-mini, o4-mini) — required. Also supported on GPT-4o, GPT-4o-mini, GPT-4, GPT-4 Turbo, GPT-3.5 Turbo as a replacement for `max_tokens`.
'
type: integer
nullable: true
n:
type: integer
minimum: 1
maximum: 128
default: 1
example: 1
nullable: true
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.
presence_penalty:
type: number
default: 0
minimum: -2
maximum: 2
nullable: true
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.
[See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
'
response_format:
type: object
description: 'An object specifying the format that the model must output.
Setting to `{ "type": "json_schema", "json_schema": {...} }`enables Structured Outputs which ensures the model will match your
supplied JSON schema. Works across all the providers that support this functionality. [OpenAI & Azure OpenAI](/integrations/llms/openai/structured-outputs), [Gemini & Vertex AI](/integrations/llms/vertex-ai/controlled-generations).
Setting to `{ "type": "json_object" }` enables the older JSON mode, which ensures the message the model generates is valid JSON.
Using `json_schema` is preferred for models that support it.
'
oneOf:
- $ref: '#/components/schemas/ResponseFormatText'
- $ref: '#/components/schemas/ResponseFormatJsonSchema'
- $ref: '#/components/schemas/ResponseFormatJsonObject'
seed:
type: integer
minimum: -9223372036854775808
maximum: 9223372036854775807
nullable: true
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.
'
x-code-samples:
beta: true
stop:
description: 'Up to 4 sequences where the API will stop generating further tokens.
'
default: null
oneOf:
- type: string
nullable: true
- 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-UShttps://platform.openai.com/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. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
'
type: boolean
nullable: true
default: false
stream_options:
$ref: '#/components/schemas/ChatCompletionStreamOptions'
thinking:
type: object
nullable: true
description: 'View the thinking/reasoning tokens as part of your response. Thinking models produce a long internal chain of thought before generating a response. Supported only for specific Claude models on Anthropic, Google Vertex AI, and AWS Bedrock. Requires setting `strict_openai_compliance = false` in your API call.
'
properties:
type:
type: string
enum:
- enabled
- disabled
description: Enables or disables the thinking mode capability.
default: disabled
budget_tokens:
type: integer
description: 'The maximum number of tokens to allocate for the thinking process.
A higher token budget allows for more thorough reasoning but may increase overall response time.
'
minimum: 1
example: 2030
required:
- type
example:
type: enabled
budget_tokens: 2030
temperature:
type: number
minimum: 0
maximum: 2
default: 1
example: 1
nullable: true
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
example: 1
nullable: true
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'
user:
type: string
example: user-1234
description: 'A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids).
'
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'
x-oaiExpandable: true
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'
required:
- model
- messages
CompletionUsage:
type: object
description: Usage statistics for the completion request.
properties:
completion_tokens:
type: integer
description: Number of tokens in the generated completion.
prompt_tokens:
type: integer
description: Number of tokens in the prompt.
total_tokens:
type: integer
description: Total number of tokens used in the request (prompt + completion).
completion_tokens_details:
type: object
nullable: true
description: Breakdown of tokens used in a completion.
properties:
reasoning_tokens:
type: integer
description: Tokens generated by the model for reasoning.
accepted_prediction_tokens:
type: integer
description: When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.
rejected_prediction_tokens:
type: integer
description: When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion.
prompt_tokens_details:
type: object
nullable: true
description: Breakdown of tokens used in the prompt.
properties:
cached_tokens:
type: integer
description: Cached tokens present in the prompt.
required:
- prompt_tokens
- completion_tokens
- total_tokens
ChatCompletionRequestMessageContentPartImage:
type: object
title: Image content part
properties:
type:
type: string
enum:
- image_url
description: The type of the content part.
image_url:
type: object
properties:
url:
type: string
description: Either a URL of the image or the base64 encoded image data.
format: uri
detail:
type: string
description: Specifies the detail level of the image. Learn more in the [Vision guide](https://platform.openai.com/docs/guides/vision/low-or-high-fidelity-image-understanding).
enum:
- auto
- low
- high
default: auto
required:
- url
required:
- type
- image_url
FunctionParameters:
type: object
description: "The parameters the functions accepts, described as a JSON Schema object. See the [guide](https://platform.openai.com/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. \n\nOmitting `parameters` defines a function with an empty parameter list."
additionalProperties: true
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
ChatCompletionTool:
type: object
properties:
type:
type: string
enum:
- function
description: The type of the tool. Currently, only `function` is supported.
function:
$ref: '#/components/schemas/FunctionObject'
required:
- type
- function
ChatCompletionMessageContentPartRedactedThinking:
type: object
title: Redacted thinking content part
properties:
type:
type: string
enum:
- redacted_thinking
description: The type of the content part.
data:
type: string
description: The redacted thinking content.
required:
- type
- data
ChatCompletionStreamOptions:
description: 'Options for streaming response. Only set this when you set `stream: true`.
'
type: object
nullable: true
default: null
properties:
include_usage:
type: boolean
description: 'If set, an additional chunk will be streamed before the `data: [DONE]` message. The `usage` field on this chunk shows the token usage statistics for the entire request, and the `choices` field will always be an empty array. All other chunks will also include a `usage` field, but with a null value.
'
ChatCompletionRequestFunctionMessage:
type: object
title: Function message
deprecated: true
properties:
role:
type: string
enum:
- function
description: The role of the messages author, in this case `function`.
content:
nullable: true
type: string
description: The contents of the function message.
name:
type: string
description: The name of the function to call.
required:
- role
- content
- name
ChatCompletionRequestUserMessage:
type: object
title: User message
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, each can be of type `text` or `image_url` when passing in images. You can pass multiple images by adding multiple `image_url` content parts. Image input is only supported when using the `gpt-4-visual-preview` model.
title: Array of content parts
items:
$ref: '#/components/schemas/ChatCompletionRequestMessageContentPart'
minItems: 1
x-oaiExpandable: true
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
ResponseFormatJsonObject:
type: object
title: JSON object
description: 'JSON object response format. An older method of generating JSON responses.
Using `json_schema` is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
'
properties:
type:
type: string
description: The type of response format being defined. Always `json_object`.
enum:
- json_object
x-stainless-const: true
required:
- type
ResponseFormatText:
type: object
title: Text
description: 'Default response format. Used to generate text responses.
'
properties:
type:
type: string
description: The type of response format being defined. Always `text`.
enum:
- text
x-stainless-const: true
required:
- type
ChatCompletionRequestToolMessage:
type: object
title: Tool message
properties:
role:
type: string
enum:
- tool
description: The role of the messages author, in this case `tool`.
content:
type: string
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
ResponseFormatJsonSchemaSchema:
type: object
title: JSON schema
description: 'The schema for the response format, described as a JSON Schema object.
Learn how to build JSON schemas [here](https://json-schema.org/).
'
additionalProperties: true
ChatCompletionMessageContentPartThinking:
type: object
title: Thinking content part
properties:
type:
type:
# --- truncated at 32 KB (58 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/portkey/refs/heads/main/openapi/portkey-chat-api-openapi.yml