---
title: "Muse Spark Open API pricing: 4 providers compared | BroadRouter"
description: "Muse Spark Open API price per token from 4 providers: lowest listed USD 1.25 input and USD 4.25 output per 1M tokens. Source linked per row."
url: https://broadrouter.com/llm-api-pricing/muse-spark-open/
lang: en
updated: 2026-11-15
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Muse Spark Open API pricing

Updated 2026-11-15

Among the 4 providers we checked (prices read 2026-11-14 to 2026-11-15), 3 tie for the lowest blended standard price for Muse Spark Open; Baseten charges USD 1.25 per 1M input tokens and USD 4.25 per 1M output tokens. The median across 4 standard prices is USD 1.25 / USD 4.25. Meta sells no API of its own for it.

Meta · slug `muse-spark-open` · up to 1,048,576 tokens of context · 4 providers with a standard price. **Every price is read from the provider's own pricing page** and linked in its row, checked 2026-11-15. No aggregator feed. [Download all prices](https://broadrouter.com/data/llm-api-provider-prices/) (every provider and model, with sources, CSV or JSON). How it compares with the market: the [LLM API price index](https://broadrouter.com/data/llm-api-price-index/).

## Does Meta sell Muse Spark Open directly?

No. Meta does not sell Llama models through an API of its own: llama.com now redirects to Meta's developer site, whose Model API lists only Meta's Muse models. Llama is available only from third-party hosts. [Checked 2026-11-14](https://dev.meta.ai/docs/overview).

## Muse Spark Open price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 25% above the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

Muse Spark Open API prices by provider
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **[Baseten](https://broadrouter.com/llm-api-pricing/providers/baseten/)** tied cheapest · `meta-models/muse-spark-open` · Note: Context from the model library page (https://www.baseten.co/library/muse-spark-open/), stated as 1M. Quote: “Muse Spark Open $1.25 $0.15 $4.25” | USD 1.25 | USD 0.15 | USD 4.25 | USD 2 | 1,000,000 | not stated | [Baseten page](https://www.baseten.co/pricing/) · checked 2026-11-14 · re-checked 2026-11-16 |
| 2 | **[Fireworks AI](https://broadrouter.com/llm-api-pricing/providers/fireworks/)** tied cheapest · `accounts/fireworks/models/muse-spark-open` · Note: Runs on US-only capacity; US premium waived. Quote: “Muse Spark Open \| $1.25 / $0.15 / $4.25 \| $1.875 / $0.225 / $6.375” | USD 1.25 | USD 0.15 | USD 4.25 | USD 2 | 1,048,576 | not stated | [Fireworks AI page](https://docs.fireworks.ai/serverless/pricing) · checked 2026-11-14 · re-checked 2026-11-16 |
| 3 | **[Together AI](https://broadrouter.com/llm-api-pricing/providers/together/)** tied cheapest · Quote: “Muse Spark Open 816B A42B $1.25 $0.15 (cached) $4.25” | USD 1.25 | USD 0.15 | USD 4.25 | USD 2 | not stated | not stated | [Together AI page](https://www.together.ai/pricing) · checked 2026-11-14 · re-checked 2026-11-16 |
| 4 | **[Venice](https://broadrouter.com/llm-api-pricing/providers/venice/)** · `muse-spark-open` · Quote: “\| Muse Spark Open \| `muse-spark-open` \| $1.5625 \| $5.3125 \| $0.1875 \| — \| Private \|” | USD 1.5625 | USD 0.1875 | USD 5.3125 | USD 2.50 | 1,048,576 | not stated | [Venice page](https://docs.venice.ai/pricing) · checked 2026-11-15 · re-checked 2026-11-16 |
| — | **[Fireworks AI](https://broadrouter.com/llm-api-pricing/providers/fireworks/)** priority · `accounts/fireworks/models/muse-spark-open` · Note: Priority mode. Quote: “Muse Spark Open \| Priority $1.875 / $0.225 / $6.375” | USD 1.875 | USD 0.225 | USD 6.375 | USD 3 | 1,048,576 | not stated | [Fireworks AI page](https://docs.fireworks.ai/serverless/pricing) · checked 2026-11-14 · re-checked 2026-11-16 |

-   **Ranked:** standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
-   **Other tiers (priority):** batch runs asynchronously within hours; flex and spot are best-effort and can be slow or refused at capacity; priority and fast cost more for reliability or speed. Shown, not ranked.
-   **Automated re-check 2026-11-16:** a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
-   **Precision** is shown only where the provider states it; "not stated" is unknown, not full precision.

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20Muse%20Spark%20Open%20API%20pricing&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fllm-api-pricing%2Fmuse-spark-open%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link filled in).

## What does Muse Spark Open cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the [LLM API cost calculator](https://broadrouter.com/tools/llm-api-cost-calculator/?model=muse-spark-open). Providers without a cached price bill cached input at the input price.

-   **Support chatbot:** 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
-   **RAG over documents:** 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
-   **Coding agent (one developer):** 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.

Monthly cost of three workloads on Muse Spark Open, by provider
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
| --- | --- | --- | --- |
| **Baseten** | USD 129.60 | USD 284.55 | USD 949.50 |
| **Fireworks AI** | USD 129.60 | USD 284.55 | USD 949.50 |
| **Together AI** | USD 129.60 | USD 284.55 | USD 949.50 |
| **Venice** | USD 162.00 | USD 355.69 | USD 1,187 |

For the support chatbot, the cheapest price (Baseten and 2 others, tied, USD 129.60 a month) saves USD 0 against the median (USD 129.60). For the coding agent the gap is USD 0 a month.

## Which Muse Spark Open provider is cheapest for your traffic?

Baseten, Fireworks AI and Together AI share the lowest input price (USD 1.25) and the lowest output price (USD 4.25), so they are the cheapest standard price at every mix of input and output tokens, before cache discounts.

Muse Spark Open: price per 1M tokens at 3 input to 1 output, by share of input served from cache
| Provider | No cache hits | 50% cached | 90% cached |
| --- | --- | --- | --- |
| **Baseten** | USD 2 cheapest | USD 1.587 cheapest | USD 1.258 cheapest |
| **Fireworks AI** | USD 2 cheapest | USD 1.587 cheapest | USD 1.258 cheapest |
| **Together AI** | USD 2 cheapest | USD 1.587 cheapest | USD 1.258 cheapest |
| **Venice** | USD 2.50 | USD 1.984 | USD 1.572 |

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

All 4 providers publish a cached-input price below the input price: Baseten (88% off), Fireworks AI (88% off), Together AI (88% off), Venice (88% off).

Context windows differ: 1,048,576 tokens at Fireworks AI and Venice; 1,000,000 tokens at Baseten. Together AI does not state one. The cheapest row is not always the one that fits a long prompt.

## Estimate your own bill

-   [LLM API cost calculator with Muse Spark Open preloaded](https://broadrouter.com/tools/llm-api-cost-calculator/?model=muse-spark-open): your traffic and cache rate, against any of 428 models.
-   [Token counter](https://broadrouter.com/tools/token-counter/): count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
-   [Prompt caching calculator](https://broadrouter.com/tools/prompt-caching-calculator/): what a higher cache-hit rate saves.

## How does Muse Spark Open compare with other Meta models?

The Meta models whose cheapest standard price is closest to Muse Spark Open's (USD 2 blended):

Meta models priced closest to Muse Spark Open
| Model | Cheapest input | Cheapest output | Max context | Providers |
| --- | --- | --- | --- | --- |
| [Llama 3 Instruct (70B)](https://broadrouter.com/llm-api-pricing/llama-3-70b-instruct/) | USD 2.65 | USD 3.50 | 8,192 | 2 |
| [Llama 3.1 Instruct (70B)](https://broadrouter.com/llm-api-pricing/llama-3.1-70b-instruct/) | USD 0.72 | USD 0.72 | 32,768 | 3 |
| [Muse Glimmer 30B](https://broadrouter.com/llm-api-pricing/muse-glimmer-30b/) | USD 0.30 | USD 1.10 | 131,072 | 3 |
| [Llama 4 Maverick 17B 128E Instruct FP8](https://broadrouter.com/llm-api-pricing/llama-4-maverick/) | USD 0.25 | USD 0.80 | 1,048,576 | 7 |
| [Llama 3.2 11B Vision Instruct](https://broadrouter.com/llm-api-pricing/llama-3.2-11b-vision-instruct/) | USD 0.16 | USD 0.16 | — | 3 |
| [Llama 3.3 70B](https://broadrouter.com/llm-api-pricing/llama-3.3-70b-instruct/) | USD 0.10 | USD 0.32 | 131,072 | 14 |

Priced closest from other makers: [Claude Haiku 4.5](https://broadrouter.com/llm-api-pricing/claude-haiku-4.5/) (Anthropic, USD 2) · [GPT-6.1 Terra](https://broadrouter.com/llm-api-pricing/gpt-6.1-terra/) (OpenAI, USD 2) · [Qwen3.7 Max](https://broadrouter.com/llm-api-pricing/qwen3.7-max/) (Qwen, USD 1.875).

[All 428 models: API prices compared](https://broadrouter.com/llm-api-pricing/) · [Cheapest LLM APIs right now](https://broadrouter.com/llm-api-pricing/cheapest/) · [LLM API price index (open data)](https://broadrouter.com/data/llm-api-price-index/) · [Download all prices (CSV, JSON)](https://broadrouter.com/data/llm-api-provider-prices/) · [Price change log](https://broadrouter.com/llm-api-pricing/changes/)

## Questions

### How much does the Muse Spark Open API cost per token?

From USD 1.25 per 1M input tokens (USD 0.00000125 per token) and USD 4.25 per 1M output tokens (USD 0.00000425 per token) at the lowest standard prices we found. The median of 4 standard prices is USD 1.25 input and USD 4.25 output. Each price was read from the provider's own pricing page; the source is linked in its row.

### Which provider is cheapest for Muse Spark Open?

Among the 4 providers we checked (prices read 2026-11-14 to 2026-11-15), 3 are tied for the lowest price: Baseten, Fireworks AI and Together AI, each USD 2 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 1.25 (Baseten and 2 others, tied); for output alone, USD 4.25 (Baseten and 2 others, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

### Does Meta sell Muse Spark Open on its own API?

Meta does not sell Llama models through an API of its own: llama.com now redirects to Meta's developer site, whose Model API lists only Meta's Muse models. Llama is available only from third-party hosts. The lowest-priced host we checked is Baseten at USD 1.25 / USD 4.25 per 1M tokens.

### Does Muse Spark Open have cached input pricing?

All 4 standard prices include one. The lowest is USD 0.15 per 1M at Baseten; the median is USD 0.15. Providers without one bill cached input at the input price. [What cached input means](https://broadrouter.com/glossary/cached-input-tokens/).

### What is the Muse Spark Open context window?

Up to 1,048,576 tokens. 1 standard price comes with less, down to 1,000,000 tokens (Baseten). Check the context column before you pick the cheapest row for long prompts. [Context window calculator](https://broadrouter.com/tools/context-window-calculator/).

### How much does a coding agent cost per month on Muse Spark Open?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 949.50 a month at Baseten, USD 949.50 at the median price and USD 1,187 at Venice. [Try your own numbers](https://broadrouter.com/tools/llm-api-cost-calculator/?model=muse-spark-open).

### Is there a batch, flex or priority price for Muse Spark Open?

Yes: priority from Fireworks AI at USD 1.875 / USD 6.375 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.

### Is Muse Spark Open free to use through an API?

No provider in our data lists a free price for Muse Spark Open as of 2026-11-15. [Free tiers and credits by provider](https://broadrouter.com/data/llm-api-free-tiers-and-rate-limits/) (checked 2026-11-14) lists general offers that do not name a model; [all free LLM API models](https://broadrouter.com/llm-api-pricing/free/) are on one page.

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-muse-spark-open&utm_content=page-cta) ·

**Sources**

-   [Baseten: pricing (checked 2026-11-14)](https://www.baseten.co/pricing/)
-   [Fireworks AI: pricing (checked 2026-11-14)](https://docs.fireworks.ai/serverless/pricing)
-   [Together AI: pricing (checked 2026-11-14)](https://www.together.ai/pricing)
-   [Venice: pricing (checked 2026-11-15)](https://docs.venice.ai/pricing)
-   [Meta developer docs (checked 2026-11-14)](https://dev.meta.ai/docs/overview)
