Chat Completions
Portkey Endpoints
Embeddings
Models
Other APIs
Completions
Moderations
Fine-tuning
Assistants
curl -X POST "https://api.portkey.ai/v1/prompts/YOUR_PROMPT_ID/render" \
-H "Content-Type: application/json" \
-H "x-portkey-api-key: $PORTKEY_API_KEY" \
-d '{
"variables": {
"user_input": "Hello world"
},
"max_tokens": 250,
"presence_penalty": 0.2
}'{
"success": true,
"data": {
"messages": [
{
"content": "<string>",
"role": "system",
"name": "<string>"
}
],
"model": "gpt-4-turbo",
"frequency_penalty": 0,
"logit_bias": null,
"logprobs": false,
"top_logprobs": 10,
"max_tokens": 123,
"n": 1,
"presence_penalty": 0,
"response_format": {
"type": "text"
},
"seed": 0,
"stop": "<string>",
"stream": false,
"stream_options": null,
"thinking": {
"type": "enabled",
"budget_tokens": 2030
},
"temperature": 1,
"top_p": 1,
"tools": [
{
"type": "function",
"function": {
"name": "<string>",
"description": "<string>",
"parameters": {},
"strict": false
}
}
],
"tool_choice": "none",
"parallel_tool_calls": true,
"user": "user-1234",
"function_call": "none",
"functions": [
{
"name": "<string>",
"description": "<string>",
"parameters": {}
}
]
}
}Prompt Render
Renders a prompt template with its variable values filled in
curl -X POST "https://api.portkey.ai/v1/prompts/YOUR_PROMPT_ID/render" \
-H "Content-Type: application/json" \
-H "x-portkey-api-key: $PORTKEY_API_KEY" \
-d '{
"variables": {
"user_input": "Hello world"
},
"max_tokens": 250,
"presence_penalty": 0.2
}'{
"success": true,
"data": {
"messages": [
{
"content": "<string>",
"role": "system",
"name": "<string>"
}
],
"model": "gpt-4-turbo",
"frequency_penalty": 0,
"logit_bias": null,
"logprobs": false,
"top_logprobs": 10,
"max_tokens": 123,
"n": 1,
"presence_penalty": 0,
"response_format": {
"type": "text"
},
"seed": 0,
"stop": "<string>",
"stream": false,
"stream_options": null,
"thinking": {
"type": "enabled",
"budget_tokens": 2030
},
"temperature": 1,
"top_p": 1,
"tools": [
{
"type": "function",
"function": {
"name": "<string>",
"description": "<string>",
"parameters": {},
"strict": false
}
}
],
"tool_choice": "none",
"parallel_tool_calls": true,
"user": "user-1234",
"function_call": "none",
"functions": [
{
"name": "<string>",
"description": "<string>",
"parameters": {}
}
]
}
}Example: Using Prompt Render output in a new request
Example: Using Prompt Render output in a new request
render API and use it for making a separate LLM call. We’ll take example of OpenAI SDKs, but you can use it simlarly for any other frameworks like Langchain etc. as well.from portkey_ai import Portkey
from openai import OpenAI
# Retrieving the Prompt from Portkey
portkey = Portkey(
api_key="PORTKEY_API_KEY"
)
render_response = portkey.prompts.render(
prompt_id="PROMPT_ID",
variables={ "movie":"Dune 2" }
)
PROMPT_TEMPLATE = render_response.data
# Making a Call to OpenAI with the Retrieved Prompt
openai = OpenAI(
api_key = "OPENAI_API_KEY",
base_url = "https://api.portkey.ai/v1",
default_headers = {
'x-portkey-provider': 'openai',
'x-portkey-api-key': 'PORTKEY_API_KEY',
'Content-Type': 'application/json',
}
)
chat_complete = openai.chat.completions.create(**PROMPT_TEMPLATE)
print(chat_complete.choices[0].message.content)
Authorizations
Path Parameters
The unique identifier of the prompt template to render
Body
Note: Although hyperparameters are shown grouped here (like messages, max_tokens, temperature, etc.), they should only be passed at the root level, alongside 'variables' and 'stream'.
Variables to substitute in the prompt template
Note: All hyperparameters are optional. Pass them at the root level, and not nested under hyperparameters. Their grouping here is for educational purposes only.
- Chat Completions
- Completions
Show child attributes
Show child attributes
A list of messages comprising the conversation so far. Example Python code.
1- System message
- Developer message
- User message
- Assistant message
- Tool message
- Function message
Show child attributes
Show child attributes
The contents of the system message.
The role of the messages author, in this case system.
system An optional name for the participant. Provides the model information to differentiate between participants of the same role.
ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.
"gpt-4-turbo"
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.
-2 <= x <= 2Modify 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.
Show child attributes
Show child attributes
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.
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.
0 <= x <= 20The maximum number of tokens that can be generated in the chat completion.
The total length of input tokens and generated tokens is limited by the model's context length. Example Python code for counting tokens.
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.
1 <= x <= 1281
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.
-2 <= x <= 2An 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, Gemini & Vertex AI.
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.
Default response format. Used to generate text responses.
- Text
- JSON schema
- JSON object
Show child attributes
Show child attributes
The type of response format being defined. Always text.
text 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.
-9223372036854776000 <= x <= 9223372036854776000Up to 4 sequences where the API will stop generating further tokens.
If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.
Options for streaming response. Only set this when you set stream: true.
Show child attributes
Show child attributes
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.
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.
Show child attributes
Show child attributes
Enables or disables the thinking mode capability.
enabled, disabled 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.
x >= 12030
{ "type": "enabled", "budget_tokens": 2030 }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.
0 <= x <= 21
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.
0 <= x <= 11
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.
Show child attributes
Show child attributes
The type of the tool. Currently, only function is supported.
function Show child attributes
Show child attributes
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.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
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. Learn more about Structured Outputs in the function calling guide.
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.
none, auto, required Whether to enable parallel function calling during tool use.
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.
"user-1234"
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.
none, auto Deprecated in favor of tools.
A list of functions the model may generate JSON inputs for.
1 - 128 elementsShow child attributes
Show child attributes
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.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Response
Successful rendered prompt
Indicates if the render was successful
- Chat Completions
- Completions
Show child attributes
Show child attributes
A list of messages comprising the conversation so far. Example Python code.
1- System message
- Developer message
- User message
- Assistant message
- Tool message
- Function message
Show child attributes
Show child attributes
The contents of the system message.
The role of the messages author, in this case system.
system An optional name for the participant. Provides the model information to differentiate between participants of the same role.
ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.
"gpt-4-turbo"
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.
-2 <= x <= 2Modify 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.
Show child attributes
Show child attributes
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.
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.
0 <= x <= 20The maximum number of tokens that can be generated in the chat completion.
The total length of input tokens and generated tokens is limited by the model's context length. Example Python code for counting tokens.
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.
1 <= x <= 1281
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.
-2 <= x <= 2An 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, Gemini & Vertex AI.
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.
Default response format. Used to generate text responses.
- Text
- JSON schema
- JSON object
Show child attributes
Show child attributes
The type of response format being defined. Always text.
text 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.
-9223372036854776000 <= x <= 9223372036854776000Up to 4 sequences where the API will stop generating further tokens.
If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.
Options for streaming response. Only set this when you set stream: true.
Show child attributes
Show child attributes
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.
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.
Show child attributes
Show child attributes
Enables or disables the thinking mode capability.
enabled, disabled 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.
x >= 12030
{ "type": "enabled", "budget_tokens": 2030 }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.
0 <= x <= 21
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.
0 <= x <= 11
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.
Show child attributes
Show child attributes
The type of the tool. Currently, only function is supported.
function Show child attributes
Show child attributes
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.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
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. Learn more about Structured Outputs in the function calling guide.
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.
none, auto, required Whether to enable parallel function calling during tool use.
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.
"user-1234"
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.
none, auto Deprecated in favor of tools.
A list of functions the model may generate JSON inputs for.
1 - 128 elementsShow child attributes
Show child attributes
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.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Was this page helpful?