Get List Chat Completions
Last updated
Was this helpful?
Last updated
Was this helpful?
Model
The model used to generate the Chat Completions.
Metadata
A list of metadata keys to filter the Chat Completions by. (Optional)
example) metadata[key1]=value1&metadata[key2]=value2
Limit
Number of Chat Completions to retrieve. (Optional)
Defaults to 20, Maximum : 100
Order
Sort order for Chat Completions by timestamp. (Optional)
Ascending (Default) Descending
data[]
An array of chat completion objects.
data[].object
The object type, which is always chat.completion.
data[].id
A unique identifier for the chat completion.
data[].model
The model used for the chat completion.
data[].created
The Unix timestamp (in seconds) of when the chat completion was created.
data[].usage
Usage statistics for the completion request.
data[].usage.total_tokens
Total number of tokens used in the request (prompt + completion).
data[].usage.completion_tokens
Number of tokens in the generated completion.
data[].usage.prompt_tokens
Number of tokens in the prompt.
data[].seed
Random seed value
data[].top_p
Probability value for token sampling (nucleus sampling)
data[].temperature
Temperature value for sampling (controls randomness)
data[].presence_penalty
Penalty value for introducing new topics in the conversation
data[].frequency_penalty
Penalty value for restricting repeated word usage
data[].system_fingerprint
Unique identifier of the system
data[].input_user
User input (this value may be optional or absent)
data[].service_tier
Service Tier value
data[].tools
Information about the tool used (null if not used)
data[].metadata
Metadata information (may be an empty object)
data[].choices[]
List of responses
data[].choices[].index
The index of the response, used to distinguish between multiple responses in a single request.
data[].choices[].message.role
The role of the entity that generated the message.
data[].choices[].message.content
The content of the generated response.
data[].choices[].message.refusal
Indicates whether the request was denied.
data[].choices[].logprobs
Log probabilities used during response generation.
data[].choices[].finish_reason
The reason why the response generation was stopped.
