API Documentation
Embeddings API
Image API
Audio Batch API
Accounts
Deployments
Models
Supervised Fine Tuning Jobs
Datasets
LLM API
Create Completion
Creates a completion for the provided prompt and parameters.
POST
https://api.fireworks.ai/inference/v1/
/
completions
curl --request POST \
--url https://api.fireworks.ai/inference/v1/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "accounts/fireworks/models/llama-v3p1-8b-instruct",
"prompt": "The sky is",
"images": [
"<string>"
],
"max_tokens": 16,
"logprobs": null,
"echo": false,
"temperature": 1,
"top_p": 1,
"top_k": 50,
"frequency_penalty": 0,
"presence_penalty": 0,
"repetition_penalty": 1,
"reasoning_effort": "low",
"mirostat_lr": 0.1,
"mirostat_target": 1.5,
"n": 1,
"ignore_eos": false,
"stop": "<string>",
"response_format": null,
"stream": false,
"context_length_exceeded_behavior": "truncate",
"user": "<string>"
}'
{
"id": "<string>",
"object": "<string>",
"created": 123,
"model": "<string>",
"choices": [
{
"text": "<string>",
"index": 123,
"logprobs": {
"tokens": [
"<string>"
],
"token_logprobs": [
123
],
"top_logprobs": [
{}
],
"text_offset": [
123
]
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
}
}
Authorizations
Bearer authentication header of the form Bearer <token>
, where <token>
is your auth token.
Body
application/json
Response
200 - application/json
OK
The response is of type object
.
Was this page helpful?
curl --request POST \
--url https://api.fireworks.ai/inference/v1/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "accounts/fireworks/models/llama-v3p1-8b-instruct",
"prompt": "The sky is",
"images": [
"<string>"
],
"max_tokens": 16,
"logprobs": null,
"echo": false,
"temperature": 1,
"top_p": 1,
"top_k": 50,
"frequency_penalty": 0,
"presence_penalty": 0,
"repetition_penalty": 1,
"reasoning_effort": "low",
"mirostat_lr": 0.1,
"mirostat_target": 1.5,
"n": 1,
"ignore_eos": false,
"stop": "<string>",
"response_format": null,
"stream": false,
"context_length_exceeded_behavior": "truncate",
"user": "<string>"
}'
{
"id": "<string>",
"object": "<string>",
"created": 123,
"model": "<string>",
"choices": [
{
"text": "<string>",
"index": 123,
"logprobs": {
"tokens": [
"<string>"
],
"token_logprobs": [
123
],
"top_logprobs": [
{}
],
"text_offset": [
123
]
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
}
}
Assistant
Responses are generated using AI and may contain mistakes.