Models, measured side by side
Hy3 vs Muse Spark 1.3
Compare Hy3, Muse Spark 1.3 by token pricing, context length, benchmark results, speed and tool support.
Monthly workload
Monthly cost breakdown
InputOutput
Hy3
$5.28 / mo
Muse Spark 1.3
$46 / mo
Performance comparison
Hy3
25.3
Muse Spark 1.3
48.1
Overview
Pricing & capacity
| Pricing & capacity | Hy3 | Muse Spark 1.3 |
|---|---|---|
| Input / 1M tokens | $0.13 | $1.25 |
| Output / 1M tokens | $0.53 | $4.25 |
| Cached input / 1M | $0.03 | $0.15 |
| Monthly cost | $5.28 | $46 |
| Context window | 262K | 1M |
| Maximum output | 128K | 944K |
Input / 1M tokens
- Hy3
- $0.13
- Muse Spark 1.3
- $1.25
Output / 1M tokens
- Hy3
- $0.53
- Muse Spark 1.3
- $4.25
Cached input / 1M
- Hy3
- $0.03
- Muse Spark 1.3
- $0.15
Monthly cost
- Hy3
- $5.28
- Muse Spark 1.3
- $46
Context window
- Hy3
- 262K
- Muse Spark 1.3
- 1M
Maximum output
- Hy3
- 128K
- Muse Spark 1.3
- 944K
Benchmarks & performance
| Benchmarks & performance | Hy3 | Muse Spark 1.3 |
|---|---|---|
| Intelligence Index | 25.3 | 48.1 |
| GPQA | 89.7% | 93.5% |
| Humanity’s Last Exam | 33.5% | 48.7% |
| SciCode | 48.6% | 58.8% |
| Output speed | 88 tokens/s | 146 tokens/s |
| Time to first token | 3.08 s | 47.86 s |
| DesignArena rating | 1,180 | 1,358 |
| DesignArena win rate | 41.1% | 57.3% |
Intelligence Index
- Hy3
- 25.3
- Muse Spark 1.3
- 48.1
GPQA
- Hy3
- 89.7%
- Muse Spark 1.3
- 93.5%
Humanity’s Last Exam
- Hy3
- 33.5%
- Muse Spark 1.3
- 48.7%
SciCode
- Hy3
- 48.6%
- Muse Spark 1.3
- 58.8%
Output speed
- Hy3
- 88 tokens/s
- Muse Spark 1.3
- 146 tokens/s
Time to first token
- Hy3
- 3.08 s
- Muse Spark 1.3
- 47.86 s
DesignArena rating
- Hy3
- 1,180
- Muse Spark 1.3
- 1,358
DesignArena win rate
- Hy3
- 41.1%
- Muse Spark 1.3
- 57.3%
Tools & features
| Tools & features | Hy3 | Muse Spark 1.3 |
|---|---|---|
| Function calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Deterministic seed | Supported | Not listed |
| Prompt caching | Supported | Supported |
Function calling
- Hy3
- Supported
- Muse Spark 1.3
- Supported
Structured outputs
- Hy3
- Supported
- Muse Spark 1.3
- Supported
JSON mode
- Hy3
- Supported
- Muse Spark 1.3
- Supported
Reasoning
- Hy3
- Supported
- Muse Spark 1.3
- Supported
Deterministic seed
- Hy3
- Supported
- Muse Spark 1.3
- Not listed
Prompt caching
- Hy3
- Supported
- Muse Spark 1.3
- Supported
API & availability
| API & availability | Hy3 | Muse Spark 1.3 |
|---|---|---|
| API identifier | hy3 | muse-spark-1.3 |
| Prices checked | Oct 8, 2026 | Oct 8, 2026 |
API identifier
- Hy3
hy3- Muse Spark 1.3
muse-spark-1.3
Prices checked
- Hy3
- Oct 8, 2026
- Muse Spark 1.3
- Oct 8, 2026
About the models
Hy3
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
Full pricing & detailsMuse 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
Hy3: $0.13 input and $0.53 output per million tokens. Muse Spark 1.3: $1.25 input and $4.25 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.