Models, measured side by side
Muse Spark 1.3 vs Nemotron 3.5 Lightning
Compare Muse Spark 1.3, Nemotron 3.5 Lightning by token pricing, context length, benchmark results, speed and tool support.
Monthly workload
Monthly cost breakdown
InputOutput
Muse Spark 1.3
$46 / mo
Nemotron 3.5 Lightning
$1.68 / mo
Performance comparison
Muse Spark 1.3
48.1
Nemotron 3.5 Lightning
12.9
Overview
| Overview | Muse Spark 1.3 | Nemotron 3.5 Lightning |
|---|---|---|
| Provider | Meta | NVIDIA |
| Released | 2026-09-02 | 2026-08-11 |
| Status | Active | Active |
| Input formats | textimagevideofile | text |
| Output formats | text | text |
Provider
Released
- Muse Spark 1.3
- 2026-09-02
- Nemotron 3.5 Lightning
- 2026-08-11
Status
- Muse Spark 1.3
- Active
- Nemotron 3.5 Lightning
- Active
Input formats
- Muse Spark 1.3
- textimagevideofile
- Nemotron 3.5 Lightning
- text
Output formats
- Muse Spark 1.3
- text
- Nemotron 3.5 Lightning
- text
Pricing & capacity
| Pricing & capacity | Muse Spark 1.3 | Nemotron 3.5 Lightning |
|---|---|---|
| Input / 1M tokens | $1.25 | $0.05 |
| Output / 1M tokens | $4.25 | $0.14 |
| Cached input / 1M | $0.15 | $0.02 |
| Monthly cost | $46 | $1.68 |
| Context window | 1M | 262K |
| Maximum output | 944K | 33K |
Input / 1M tokens
- Muse Spark 1.3
- $1.25
- Nemotron 3.5 Lightning
- $0.05
Output / 1M tokens
- Muse Spark 1.3
- $4.25
- Nemotron 3.5 Lightning
- $0.14
Cached input / 1M
- Muse Spark 1.3
- $0.15
- Nemotron 3.5 Lightning
- $0.02
Monthly cost
- Muse Spark 1.3
- $46
- Nemotron 3.5 Lightning
- $1.68
Context window
- Muse Spark 1.3
- 1M
- Nemotron 3.5 Lightning
- 262K
Maximum output
- Muse Spark 1.3
- 944K
- Nemotron 3.5 Lightning
- 33K
Benchmarks & performance
| Benchmarks & performance | Muse Spark 1.3 | Nemotron 3.5 Lightning |
|---|---|---|
| Intelligence Index | 48.1 | 12.9 |
| GPQA | 93.5% | 74.3% |
| Humanity’s Last Exam | 48.7% | 10.6% |
| SciCode | 58.8% | 32.1% |
| Output speed | 146 tokens/s | 301 tokens/s |
| Time to first token | 47.86 s | 0.56 s |
| DesignArena rating | 1,358 | Not listed |
| DesignArena win rate | 57.3% | Not listed |
Intelligence Index
- Muse Spark 1.3
- 48.1
- Nemotron 3.5 Lightning
- 12.9
GPQA
- Muse Spark 1.3
- 93.5%
- Nemotron 3.5 Lightning
- 74.3%
Humanity’s Last Exam
- Muse Spark 1.3
- 48.7%
- Nemotron 3.5 Lightning
- 10.6%
SciCode
- Muse Spark 1.3
- 58.8%
- Nemotron 3.5 Lightning
- 32.1%
Output speed
- Muse Spark 1.3
- 146 tokens/s
- Nemotron 3.5 Lightning
- 301 tokens/s
Time to first token
- Muse Spark 1.3
- 47.86 s
- Nemotron 3.5 Lightning
- 0.56 s
DesignArena rating
- Muse Spark 1.3
- 1,358
- Nemotron 3.5 Lightning
- Not listed
DesignArena win rate
- Muse Spark 1.3
- 57.3%
- Nemotron 3.5 Lightning
- Not listed
Tools & features
| Tools & features | Muse Spark 1.3 | Nemotron 3.5 Lightning |
|---|---|---|
| Function calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Log probabilities | Not listed | Supported |
| Deterministic seed | Not listed | Supported |
| Prompt caching | Supported | Supported |
Function calling
- Muse Spark 1.3
- Supported
- Nemotron 3.5 Lightning
- Supported
Structured outputs
- Muse Spark 1.3
- Supported
- Nemotron 3.5 Lightning
- Supported
JSON mode
- Muse Spark 1.3
- Supported
- Nemotron 3.5 Lightning
- Supported
Reasoning
- Muse Spark 1.3
- Supported
- Nemotron 3.5 Lightning
- Supported
Log probabilities
- Muse Spark 1.3
- Not listed
- Nemotron 3.5 Lightning
- Supported
Deterministic seed
- Muse Spark 1.3
- Not listed
- Nemotron 3.5 Lightning
- Supported
Prompt caching
- Muse Spark 1.3
- Supported
- Nemotron 3.5 Lightning
- Supported
API & availability
| API & availability | Muse Spark 1.3 | Nemotron 3.5 Lightning |
|---|---|---|
| API identifier | muse-spark-1.3 | nemotron-3.5-lightning |
| Prices checked | Oct 8, 2026 | Oct 8, 2026 |
API identifier
- Muse Spark 1.3
muse-spark-1.3- Nemotron 3.5 Lightning
nemotron-3.5-lightning
Prices checked
- Muse Spark 1.3
- Oct 8, 2026
- Nemotron 3.5 Lightning
- Oct 8, 2026
About the models
Muse Spark 1.3
Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...
Full pricing & detailsNemotron 3.5 Lightning
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
Full pricing & detailsComparison FAQ
Muse Spark 1.3: $1.25 input and $4.25 output per million tokens. Nemotron 3.5 Lightning: $0.05 input and $0.14 output per million tokens. The cheaper choice depends on your input-to-output ratio; a model can have a lower input rate but a higher output rate.