Models, measured side by side
MiniMax M3 vs Muse Spark 1.3
Compare MiniMax M3, Muse Spark 1.3 by token pricing, context length, benchmark results, speed and tool support.
Monthly workload
Monthly cost breakdown
InputOutput
MiniMax M3
$12 / mo
Muse Spark 1.3
$46 / mo
Performance comparison
MiniMax M3
29.2
Muse Spark 1.3
48.1
Overview
Pricing & capacity
| Pricing & capacity | MiniMax M3 | Muse Spark 1.3 |
|---|---|---|
| Input / 1M tokens | $0.30 | $1.25 |
| Output / 1M tokens | $1.20 | $4.25 |
| Cached input / 1M | $0.06 | $0.15 |
| Monthly cost | $12 | $46 |
| Context window | 1M | 1M |
| Maximum output | 512K | 944K |
Input / 1M tokens
- MiniMax M3
- $0.30
- Muse Spark 1.3
- $1.25
Output / 1M tokens
- MiniMax M3
- $1.20
- Muse Spark 1.3
- $4.25
Cached input / 1M
- MiniMax M3
- $0.06
- Muse Spark 1.3
- $0.15
Monthly cost
- MiniMax M3
- $12
- Muse Spark 1.3
- $46
Context window
- MiniMax M3
- 1M
- Muse Spark 1.3
- 1M
Maximum output
- MiniMax M3
- 512K
- Muse Spark 1.3
- 944K
Benchmarks & performance
| Benchmarks & performance | MiniMax M3 | Muse Spark 1.3 |
|---|---|---|
| Intelligence Index | 29.2 | 48.1 |
| GPQA | 92.9% | 93.5% |
| Humanity’s Last Exam | 39% | 48.7% |
| SciCode | 47.1% | 58.8% |
| Output speed | 97 tokens/s | 146 tokens/s |
| Time to first token | 2.03 s | 47.86 s |
| DesignArena rating | 1,252 | 1,358 |
| DesignArena win rate | 50.9% | 57.3% |
Intelligence Index
- MiniMax M3
- 29.2
- Muse Spark 1.3
- 48.1
GPQA
- MiniMax M3
- 92.9%
- Muse Spark 1.3
- 93.5%
Humanity’s Last Exam
- MiniMax M3
- 39%
- Muse Spark 1.3
- 48.7%
SciCode
- MiniMax M3
- 47.1%
- Muse Spark 1.3
- 58.8%
Output speed
- MiniMax M3
- 97 tokens/s
- Muse Spark 1.3
- 146 tokens/s
Time to first token
- MiniMax M3
- 2.03 s
- Muse Spark 1.3
- 47.86 s
DesignArena rating
- MiniMax M3
- 1,252
- Muse Spark 1.3
- 1,358
DesignArena win rate
- MiniMax M3
- 50.9%
- Muse Spark 1.3
- 57.3%
Tools & features
| Tools & features | MiniMax M3 | Muse Spark 1.3 |
|---|---|---|
| Function calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Log probabilities | Supported | Not listed |
| Deterministic seed | Supported | Not listed |
| Prompt caching | Supported | Supported |
Function calling
- MiniMax M3
- Supported
- Muse Spark 1.3
- Supported
Structured outputs
- MiniMax M3
- Supported
- Muse Spark 1.3
- Supported
JSON mode
- MiniMax M3
- Supported
- Muse Spark 1.3
- Supported
Reasoning
- MiniMax M3
- Supported
- Muse Spark 1.3
- Supported
Log probabilities
- MiniMax M3
- Supported
- Muse Spark 1.3
- Not listed
Deterministic seed
- MiniMax M3
- Supported
- Muse Spark 1.3
- Not listed
Prompt caching
- MiniMax M3
- Supported
- Muse Spark 1.3
- Supported
API & availability
| API & availability | MiniMax M3 | Muse Spark 1.3 |
|---|---|---|
| API identifier | minimax-m3 | muse-spark-1.3 |
| Prices checked | Oct 8, 2026 | Oct 8, 2026 |
API identifier
- MiniMax M3
minimax-m3- Muse Spark 1.3
muse-spark-1.3
Prices checked
- MiniMax M3
- Oct 8, 2026
- Muse Spark 1.3
- Oct 8, 2026
About the models
MiniMax M3
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
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
MiniMax M3: $0.30 input and $1.20 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.