# Muse Spark 1.3

Muse Spark 1.3 is a text generation model from Meta, available through the Impossibl API. Its published context window is 1,048,576 tokens. The advertised input rate is $1.25 per million input tokens. The advertised output rate is $4.25 per million output tokens.

- Model identifier: ` meta/muse-spark-1.3 `
- Creator: Meta
- Model type: Text generation
- Canonical model page: [Muse Spark 1.3](<https://impossibl.com/meta/muse-spark-1.3>)
- API availability: Listed as serving through Impossibl.
- Creator release date: 2026-09-02

## Capabilities and limits

- Context window: 1,048,576 tokens
- Maximum output tokens: Not published in the public catalog; this is separate from the context window.
- Inputs: text, image
- Outputs: text
- Tool calling: Not published

## API access

Use ` meta/muse-spark-1.3 ` as the model identifier through the Impossibl API.

Published API endpoints:

- ` /v1/chat/completions `

[API quickstart](<https://impossibl.com/docs/agent-quickstart>) · [Models and billing documentation](<https://impossibl.com/docs/models>)

## Published API prices

All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid.

| Usage | Published base rate | Billing unit |
| --- | --- | --- |
| Input | $1.25 | per million input tokens |
| Output | $4.25 | per million output tokens |
| Cache read | $0.15 | per million cached input tokens |
| Cache write (default retention) | Not published | per million tokens |
| Cache write (one-hour retention) | Not published | per million tokens |
| Audio input | Not published | per million audio input tokens |

## Independent benchmarks

Source: [Artificial Analysis](<https://artificialanalysis.ai/>). Last checked: 2026-09-11T12:23:22.823Z.
Configurations are evaluated separately. API scores retain their original units. Unmeasured scores are omitted.

### Muse Spark 1.3 (max)

Source: [Evaluation source](<https://artificialanalysis.ai/models/muse-spark-1-3>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 48.17 |
| Omniscience Index | 25.00 |
| GPQA | 93.54% |
| Humanity’s Last Exam | 48.70% |
| SciCode | 58.80% |
| CritPt | 24.86% |
| Terminal-Bench v2.1 | 84.27% |
| Terminal-Bench v4.0 | 33.33% |
| AA-LCR | 83.00% |
| Multilingual LCR | 41.11% |
| GDPval Elo | 1703.34 |
| GDP.pdf All-pass | 26.60% |
| AutomationBench Partial | 57.85% |
| Tau Banking | 50.52% |
| coding index (API) | 75.8 |
| agentic index (API) | 55.7 |
| intelligence index (API) | 48.2 |

### Muse Spark 1.3 (xhigh)

Source: [Evaluation source](<https://artificialanalysis.ai/models/muse-spark-1-3-xhigh>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 45.16 |
| Omniscience Index | 23.12 |
| GPQA | 94.14% |
| Humanity’s Last Exam | 47.45% |
| SciCode | 59.72% |
| CritPt | 26.00% |
| Terminal-Bench v2.1 | 85.39% |
| Terminal-Bench v4.0 | 16.67% |
| AA-LCR | 83.00% |
| Harvey LAB | 95.48% |
| GDPval Elo | 1662.34 |
| GDP.pdf All-pass | 24.20% |
| AutomationBench Partial | 56.84% |
| MMMU-Pro | 82.02% |
| Tau Banking | 47.22% |
| coding index (API) | 76.5 |
| agentic index (API) | 51.8 |
| intelligence index (API) | 45.2 |

Full benchmark data and breakdowns: [Complete benchmark snapshot](<https://api.impossibl.com/v1/models/meta/muse-spark-1.3/benchmarks>).


## Availability and retirement

The model is listed as serving. No retirement is announced in the current public catalog.

## Frequently asked questions

### What is Muse Spark 1.3?

Muse Spark 1.3 is a text-generation model from Meta, available through the Impossibl API.

### How much does Muse Spark 1.3 cost?

Muse Spark 1.3 costs $1.25 per million input tokens and $4.25 per million output tokens through the Impossibl API. Cache reads cost $0.15 per million tokens. All rates are in USD.

### What is the context length of Muse Spark 1.3?

Muse Spark 1.3 has a 1,048,576-token context window through the Impossibl API.

### What inputs and outputs does Muse Spark 1.3 support?

Muse Spark 1.3 accepts text and image as input. Muse Spark 1.3 returns text.

### How do I use Muse Spark 1.3 through an API?

Muse Spark 1.3 is available through the Impossibl API. Use meta/muse-spark-1.3 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

### When was Muse Spark 1.3 released?

Meta released Muse Spark 1.3 on September 2, 2026.

Sources: [Creator release announcement](<https://research.meta.ai/blog/introducing-muse-spark-1-3>)

## Sources and related links

Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [Muse Spark 1.3: model details and pricing](<https://impossibl.com/meta/muse-spark-1.3>)
- [Model directory](<https://impossibl.com/models>)