Last refreshed 2026-10-15. Next refresh: weekly.
Why use Muse Spark Open on Fireworks AI?
Fireworks AI offers Muse Spark Open with pay-as-you-go pricing at $1.25/1M input tokens. Fireworks AI offers a generative AI platform as a service, focusing on rapid product iteration and cost-efficient AI deployment.
Compare Muse Spark Open across 4 providers to find the best fit for your use caseInput / 1M
$1.25
Output / 1M
$4.25
Cache
read $0.15
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install openaiAuth
export FIREWORKS_API_KEY=...Call
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["FIREWORKS_API_KEY"],Model ID
accounts/fireworks/models/muse-spark-openRequest example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["FIREWORKS_API_KEY"],
base_url="https://api.fireworks.ai/inference/v1"
)
response = client.chat.completions.create(
model="accounts/fireworks/models/muse-spark-open",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "accounts/fireworks/models/muse-spark-open", not the LLMReference slug "muse-spark-open".
- Fireworks model IDs use "accounts/fireworks/models/{model-name}" format, e.g. "accounts/fireworks/models/llama4-scout-instruct-basic" or "accounts/fireworks/models/deepseek-r1".
- The examples expect FIREWORKS_API_KEY; rename it only if your application config maps the new variable.
Compare Muse Spark Open Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Together AI | $1.25 | $4.25 |
| Fireworks AI | $1.25 | $4.25 |
| GroqCloud | — | — |
| OpenRouter | — | — |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.25 |
| Output tokens | $4.25 |
Capabilities
VisionMultimodalReasoningJSON / Tool useAudio
About Muse Spark Open
Muse Spark Open is the open-weight release of Meta Superintelligence Labs' Muse Spark, an 816-billion-parameter mixture-of-experts model that activates about 42 billion parameters per token. Released October 15, 2026 under the Muse Model License, it is built for coding and agentic work, takes text, image, video and audio input, returns text, and has a 1M-token context window. Weights are on Hugging Face in BF16 and NVFP4.
Get Started
Model Specs
Released2026-10-15
Parameters816B (42B activated)
Context1M
ArchitectureMixture of Experts