Models, measured side by side
Muse Spark 1.3 vs Phi-4
Compare Muse Spark 1.3, Phi-4 by token pricing, context length, benchmark results, speed and tool support.
Monthly workload
Monthly cost breakdown
InputOutput
Muse Spark 1.3
$46 / mo
Phi-4
$2.10 / mo
Performance comparison
Muse Spark 1.3
48.1
Phi-4
5.9
Overview
Pricing & capacity
| Pricing & capacity | Muse Spark 1.3 | Phi-4 |
|---|---|---|
| Input / 1M tokens | $1.25 | $0.07 |
| Output / 1M tokens | $4.25 | $0.14 |
| Cached input / 1M | $0.15 | Not listed |
| Monthly cost | $46 | $2.10 |
| Context window | 1M | 16K |
| Maximum output | 944K | 15K |
Input / 1M tokens
- Muse Spark 1.3
- $1.25
- Phi-4
- $0.07
Output / 1M tokens
- Muse Spark 1.3
- $4.25
- Phi-4
- $0.14
Cached input / 1M
- Muse Spark 1.3
- $0.15
- Phi-4
- Not listed
Monthly cost
- Muse Spark 1.3
- $46
- Phi-4
- $2.10
Context window
- Muse Spark 1.3
- 1M
- Phi-4
- 16K
Maximum output
- Muse Spark 1.3
- 944K
- Phi-4
- 15K
Benchmarks & performance
| Benchmarks & performance | Muse Spark 1.3 | Phi-4 |
|---|---|---|
| Arena Elo | Not listed | 1,123 |
| MMLU-Pro | Not listed | 60.7% |
| Intelligence Index | 48.1 | 5.9 |
| GPQA | 93.5% | 57.5% |
| Humanity’s Last Exam | 48.7% | 3.8% |
| SciCode | 58.8% | Not listed |
| Output speed | 146 tokens/s | 39 tokens/s |
| Time to first token | 47.86 s | 2.59 s |
| DesignArena rating | 1,358 | Not listed |
| DesignArena win rate | 57.3% | Not listed |
Arena Elo
- Muse Spark 1.3
- Not listed
- Phi-4
- 1,123
MMLU-Pro
- Muse Spark 1.3
- Not listed
- Phi-4
- 60.7%
Intelligence Index
- Muse Spark 1.3
- 48.1
- Phi-4
- 5.9
GPQA
- Muse Spark 1.3
- 93.5%
- Phi-4
- 57.5%
Humanity’s Last Exam
- Muse Spark 1.3
- 48.7%
- Phi-4
- 3.8%
SciCode
- Muse Spark 1.3
- 58.8%
- Phi-4
- Not listed
Output speed
- Muse Spark 1.3
- 146 tokens/s
- Phi-4
- 39 tokens/s
Time to first token
- Muse Spark 1.3
- 47.86 s
- Phi-4
- 2.59 s
DesignArena rating
- Muse Spark 1.3
- 1,358
- Phi-4
- Not listed
DesignArena win rate
- Muse Spark 1.3
- 57.3%
- Phi-4
- Not listed
Tools & features
| Tools & features | Muse Spark 1.3 | Phi-4 |
|---|---|---|
| Function calling | Supported | Not listed |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Not listed |
| Deterministic seed | Not listed | Supported |
| Prompt caching | Supported | Not listed |
Function calling
- Muse Spark 1.3
- Supported
- Phi-4
- Not listed
Structured outputs
- Muse Spark 1.3
- Supported
- Phi-4
- Supported
JSON mode
- Muse Spark 1.3
- Supported
- Phi-4
- Supported
Reasoning
- Muse Spark 1.3
- Supported
- Phi-4
- Not listed
Deterministic seed
- Muse Spark 1.3
- Not listed
- Phi-4
- Supported
Prompt caching
- Muse Spark 1.3
- Supported
- Phi-4
- Not listed
API & availability
| API & availability | Muse Spark 1.3 | Phi-4 |
|---|---|---|
| API identifier | muse-spark-1.3 | phi-4 |
| API providers | Not listed | DeepInfra |
| Knowledge cutoff | Not listed | 2024-06-30 |
| Prices checked | Oct 8, 2026 | Oct 8, 2026 |
API identifier
- Muse Spark 1.3
muse-spark-1.3- Phi-4
phi-4
API providers
- Muse Spark 1.3
- Not listed
- Phi-4
- DeepInfra
Knowledge cutoff
- Muse Spark 1.3
- Not listed
- Phi-4
- 2024-06-30
Prices checked
- Muse Spark 1.3
- Oct 8, 2026
- Phi-4
- 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 & detailsComparison FAQ
Muse Spark 1.3: $1.25 input and $4.25 output per million tokens. Phi-4: $0.07 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.
