Completions API - Fireworks AI Docs

The completions API provides raw text generation without automatic message formatting. Use this when you need full control over prompt formatting or when working with base models.

When to use completions

Use the completions API for:

Custom prompt templates with specific formatting requirements
Base models (non-instruct/non-chat variants)
Fine-grained control over token-level formatting
Legacy applications that depend on raw completion format

For most use cases, use chat completions instead. Chat completions handles message formatting automatically and works better with instruct-tuned models.

Basic usage

Python (Fireworks SDK)
Python (OpenAI SDK)
JavaScript
curl

from fireworks import Fireworks

client = Fireworks()

response = client.completions.create(
  model="accounts/fireworks/models/deepseek-v3p1",
  prompt="Once upon a time"
)

print(response.choices[0].text)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("FIREWORKS_API_KEY"),
    base_url="https://api.fireworks.ai/inference/v1"
)

response = client.completions.create(
    model="accounts/fireworks/models/deepseek-v3p1",
    prompt="Once upon a time"
)

print(response.choices[0].text)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.FIREWORKS_API_KEY,
  baseURL: "https://api.fireworks.ai/inference/v1",
});

const response = await client.completions.create({
  model: "accounts/fireworks/models/deepseek-v3p1",
  prompt: "Once upon a time",
});

console.log(response.choices[0].text);

curl https://api.fireworks.ai/inference/v1/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $FIREWORKS_API_KEY" \
  -d '{
    "model": "accounts/fireworks/models/deepseek-v3p1",
    "prompt": "Once upon a time"
  }'

Most models automatically prepend the beginning-of-sequence (BOS) token (e.g., <s>) to your prompt. Verify this with the raw_output parameter if needed.

Custom prompt templates

The completions API is useful when you need to implement custom prompt formats:

# Custom few-shot prompt template
prompt = """Task: Classify the sentiment of the following text.

Text: I love this product!
Sentiment: Positive

Text: This is terrible.
Sentiment: Negative

Text: The weather is nice today.
Sentiment:"""

response = client.completions.create(
    model="accounts/fireworks/models/deepseek-v3p1",
    prompt=prompt,
    max_tokens=10,
    temperature=0
)

print(response.choices[0].text)  # Output: " Positive"

Common parameters

All chat completions parameters work with completions:

temperature - Control randomness (0-2)
max_tokens - Limit output length
top_p, top_k, min_p - Sampling parameters
stream - Stream responses token-by-token
frequency_penalty, presence_penalty - Reduce repetition

See the API reference for complete parameter documentation.

Querying deployments

Use completions with on-demand deployments by specifying the deployment identifier:

response = client.completions.create(
    model="accounts/<ACCOUNT_ID>/deployments/<DEPLOYMENT_ID>",
    prompt="Your prompt here"
)

Next steps

Chat Completions

Use chat completions for most use cases

Streaming

Stream responses for real-time UX

API Reference

Complete API documentation

​When to use completions

​Basic usage

​Custom prompt templates

​Common parameters

​Querying deployments

​Next steps

Chat Completions

Streaming

API Reference

When to use completions

Basic usage

Custom prompt templates

Common parameters

Querying deployments

Next steps