Model comparison

Muse Spark 1.2 vs Muse Spark 1.3

Meta's Muse Spark 1.2 against Meta's Muse Spark 1.3: vendor list prices, limits, abilities and the Artificial Analysis indexes side by side - and what OpenSmartRoute does when both are available.

Same priceEven

Both list at $2.00 per million tokens blended (3 input : 1 output).

Stronger on intelligenceMuse Spark 1.2

Muse Spark 1.2 scores 40 on the intelligence index against 36 - 3 points apart.

Stronger on codingMuse Spark 1.3

Muse Spark 1.3 scores 76 on the coding index against 72 - 4 points apart.

Stronger on agenticMuse Spark 1.3

Muse Spark 1.3 scores 56 on the agentic index against 43 - 12 points apart.

Side by side

Vendor list prices per million tokens and published limits; indexes are Artificial Analysis composites (0-100).

Specification	Muse Spark 1.2	Muse Spark 1.3
Input price / 1M tokens	$1.25	$1.25
Output price / 1M tokens	$4.25	$4.25
Blended (3 in : 1 out)	$2.00	$2.00
Cached input / 1M	$0.15	$0.15
Context window	1.0M	1.0M
Max output	944K	944K
Input	text, image, video, file	text, image, video, file
Output	text	text
Tool calls
Structured output
Reasoning
Open weights
Intelligence index	40	36
Coding index	72	76
Agentic index	43	56
Released	Aug 5, 2026	Sep 2, 2026
Available on this deployment

What a month costs

List price times tokens for three typical workloads; your mix of input and output decides which model's pricing suits you.

Workload	Muse Spark 1.2	Muse Spark 1.3	Difference
Support chat20M tokens in, 5M out a month - a help desk answering a few thousand conversations.	$46.25	$46.25	same
Document summaries100M in, 5M out - long inputs, short answers.	$146	$146	same
Coding assistant60M in, 20M out - a team's editor assistant, output-heavy.	$160	$160	same

What the router does with the pair

Muse Spark 1.2 is both cheaper and stronger on the intelligence index, so with both in the catalogue the router sends it almost everything; Muse Spark 1.3 earns a request only on something it alone offers - a longer context, a modality, a data boundary or a region your rules require.

Price a request Playground

yaml

# targets.yaml - both models as routing targets (metadata.model links each to the catalogue entry)
targets:
  - { id: muse-spark-1.2, kind: llm, metadata: { model: meta/muse-spark-1.2 } }
  - { id: muse-spark-1.3, kind: llm, metadata: { model: meta/muse-spark-1.3 } }

# rules.yaml - the cheaper model by default, the stronger one when the request is hard
rules:
  - name: simple-requests-stay-cheap
    when: { max_complexity: 0.45 }
    prefer: [muse-spark-1.2]
    weight: 0.8
  - name: hard-requests-escalate
    when: { min_complexity: 0.45 }
    prefer: [muse-spark-1.3]
    weight: 0.8

Frequently asked

Is Muse Spark 1.2 cheaper than Muse Spark 1.3?: No - both list at $2.00 per million tokens blended (three input tokens per output token).
Which is better, Muse Spark 1.2 or Muse Spark 1.3?: On the Artificial Analysis intelligence index Muse Spark 1.2 scores higher (40 against 36). "Better" depends on the task: the coding and agentic indexes below and the abilities row may point the other way for your requests.
Which has the longer context window?: Both accept 1.0M tokens.
Can I use Muse Spark 1.2 and Muse Spark 1.3 together?: Yes. Declare both as targets and OpenSmartRoute picks one per request on quality for the task, price and your rules - the cheaper model for the requests it can answer, the stronger one for the rest - and records why in the trace.

Also compared

Every Meta and Meta model, with prices, is on the vendor pages; the rankings show what the router actually picks.

For the business

What it means for which models you pay for.

Catalogue of every vendor
The right model, not the famous one
Price, context, abilities and benchmark indexes side by side, with the model that fits each task named.
The rankings
89% less
Lower cost per request
On the 150-prompt benchmark the router spent 89% less than sending every prompt to the reference model, and the judged quality went up, not down.
Read the benchmark
Per million tokens, every model
Prices you can compare
The catalogue prints input and output prices and what three typical monthly workloads cost on each.
The model catalogue

Which LLM is the cheapest for our workload?: The best-for pages rank the live catalogue per task by the index that measures it, and the router picks the cheapest model that meets your quality rule for each request.
How much can we save on our LLM bill?: On the public benchmark the router saved 89% against sending everything to the reference model. Import last month's provider bill on the bill page and the estimate is computed on your own traffic before you change a line of code.
How often do model prices change?: The catalogue is refreshed from the vendors' price lists; each model page shows the date of its data.

Stop choosing between Muse Spark 1.2 and Muse Spark 1.3. Route to both.

Declare the pair as targets and OpenSmartRoute picks per request - the cheaper one where it holds up, the stronger one where it matters - with the comparison in every trace.

Create a free account Try a request

Free plan, no card. Fifteen thousand decisions a month with the full trace.

Specification

Muse Spark 1.2

Muse Spark 1.3

Input price / 1M tokens

$1.25

Output price / 1M tokens

$4.25

Blended (3 in : 1 out)

$2.00

Cached input / 1M

$0.15

Context window

1.0M

Max output

944K

Input

text, image, video, file

Output

text

Tool calls

Structured output

Reasoning

Open weights

Intelligence index

Coding index

Agentic index

Released

Aug 5, 2026

Sep 2, 2026

Available on this deployment

Workload

Muse Spark 1.2

Muse Spark 1.3

Difference

Support chat20M tokens in, 5M out a month - a help desk answering a few thousand conversations.

$46.25

same

Document summaries100M in, 5M out - long inputs, short answers.

$146

same

Coding assistant60M in, 20M out - a team's editor assistant, output-heavy.

$160

same

What the router does with the pair

# targets.yaml - both models as routing targets (metadata.model links each to the catalogue entry) targets: - { id: muse-spark-1.2, kind: llm, metadata: { model: meta/muse-spark-1.2 } } - { id: muse-spark-1.3, kind: llm, metadata: { model: meta/muse-spark-1.3 } } # rules.yaml - the cheaper model by default, the stronger one when the request is hard rules: - name: simple-requests-stay-cheap when: { max_complexity: 0.45 } prefer: [muse-spark-1.2] weight: 0.8 - name: hard-requests-escalate when: { min_complexity: 0.45 } prefer: [muse-spark-1.3] weight: 0.8

Frequently asked

Is Muse Spark 1.2 cheaper than Muse Spark 1.3?

No - both list at $2.00 per million tokens blended (three input tokens per output token).

Which is better, Muse Spark 1.2 or Muse Spark 1.3?

On the Artificial Analysis intelligence index Muse Spark 1.2 scores higher (40 against 36). "Better" depends on the task: the coding and agentic indexes below and the abilities row may point the other way for your requests.

Which has the longer context window?

Both accept 1.0M tokens.

Can I use Muse Spark 1.2 and Muse Spark 1.3 together?

Yes. Declare both as targets and OpenSmartRoute picks one per request on quality for the task, price and your rules - the cheaper model for the requests it can answer, the stronger one for the rest - and records why in the trace.

Muse Spark 1.2 vs Muse Spark 1.3

Side by side

What a month costs

What the router does with the pair

Frequently asked

Also compared

What it means for which models you pay for.

The right model, not the famous one

Lower cost per request

Prices you can compare

Stop choosing between Muse Spark 1.2 and Muse Spark 1.3. Route to both.

Muse Spark 1.2 vs Muse Spark 1.3

Side by side

What a month costs

What the router does with the pair

Frequently asked

Also compared

What it means for which models you pay for.

The right model, not the famous one

Lower cost per request

Prices you can compare

Stop choosing between Muse Spark 1.2 and Muse Spark 1.3. Route to both.