muse-spark-open
Meta/Open weights/2 providers
Muse Spark Open is an open weights reasoning model from Meta optimized for agentic coding, with reliable tool calling, deep codebase understanding and native image understanding. Sparse MoE with 816B total and 42B active parameters, 1M token context.MoreLess
Which id to call
muse-spark-openRequesty routes this id across every provider serving muse-spark-open, picking on price and health and failing over automatically. The id stays valid when a provider changes underneath it.
From /1M input
$1.25
Fireworks AI
Context
1.0M
131K output
Endpoints
2
1 region
Regions
1
chat
Capabilities 4/8
2 endpoints / 1 region
Providers serving muse-spark-open
Provider prices, per 1M tokens. Pay as you go adds 5%, or 0% on your own keys.
| Rank | Privacy | ||||||
|---|---|---|---|---|---|---|---|
| 1 |  Fireworks AI | Global | 1.0M | $1.25 | $4.25 | $0.15 | zdr |
| 2 |  Together AI | Global | 1.0M | $1.25 | $4.25 | $0.15 | zdr |
A column is blank where no qualifying sample exists, and every row links to that provider's endpoint page.
model=
Which id to call
One base url, https://router.requesty.ai/v1, and one key for every id here.
muse-spark-openRequesty routes this id across every provider serving muse-spark-open, picking on price and health and failing over automatically. The id stays valid when a provider changes underneath it.
OpenAI compatible
Call it in three lines
Change the base url, use your Requesty key, set the model to any id on the left. Existing OpenAI SDK code needs no other edit.
123456789101112131415from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1", ) response = client.chat.completions.create( model="muse-spark-open", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ], ) print(response.choices[0].message.content)
6
More from Meta
muse-spark-1.3
1.0M ctx/from $1.25/1 provider
muse-wonder-1.0
1.0M ctx/from $4.00/1 provider
muse-glimmer-30b
131K ctx/from free/2 providers
llama-4-maverick-17b-128e-instruct
1.0M ctx/from $0.20/1 provider
llama-3.3-70b-instruct
131K ctx/from $0.13/3 providers
llama-3.3-70b-instruct-turbo
131K ctx/from $0.08/1 provider
Reference
muse-spark-open questions
Which providers serve muse-spark-open?
muse-spark-open is available from 2 providers through Requesty: Fireworks AI, Together AI. All endpoints share one OpenAI-compatible API and one key, and Requesty fails over between them automatically.
How much does muse-spark-open cost?
Pricing starts at $1.25 per million input tokens and $4.25 per million output tokens on Fireworks AI, the cheapest endpoint. Prices vary by provider and region; the table above shows every endpoint. Those are the upstream provider rates: pay as you go adds 5% on top, or 0% if you bring your own provider keys.
Is muse-spark-open open weights?
Yes. muse-spark-open is an open-weights model from Meta, which is why multiple inference providers can host it. Provider choice affects price, latency, and data-privacy terms, all compared above.
What is the context window of muse-spark-open?
muse-spark-open supports up to 1.0M tokens of context, with up to 131K output tokens per response. Some providers expose a smaller window; check the per-endpoint context column above.
How do I use muse-spark-open with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "muse-spark-open" or any endpoint id from the table above. The quickstart section shows Python, JavaScript and cURL snippets.
Should I call muse-spark-open by its managed id or a provider id?
Use the managed id, "muse-spark-open". Requesty picks which of the 2 providers serves each request based on price and health, and fails over when one degrades, so the id keeps working while the routing changes underneath it. Send a provider id like "fireworks/muse-spark-open" only when you need one specific deployment and want no failover.
Route muse-spark-open through one endpoint
One key for 2 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in.