Muse Spark 1.3: API Pricing, Context Window & Benchmarks
Muse Spark 1.3 is a language model from Meta, released in September 2026, with multimodal input, a 1.0M-token context window, and pricing from $0.100/M input, $0.002/M cached input, $0.200/M output.
Muse Spark 1.3 is Meta Superintelligence Labs' proprietary multimodal reasoning model for long-running agentic, multi-agent, and coding workflows. It improves on Muse Spark 1.2 in long-horizon collaboration, multitasking, instruction
Muse Spark 1.3 benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Muse Spark 1.3 across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Muse Spark 1.3 holds up as conversations get longer.
Quality Tracker
Muse Spark 1.3 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Thu Sep 03 2026Muse Spark 1.3 pricing
Providers
Muse Spark 1.3 starts at $0.100 per million input tokens and $0.200 per million output tokens via Meta Model API. Reused prompt prefixes cost $0.0020 per million cached input tokens.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Meta Model API | $0.100 | $0.0020 | $0.200 | 1.0M/943.7K | 2.98 | 25 | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Muse Spark 1.3 context window
Input and output token limits for Muse Spark 1.3, plus how it ranks on long-context understanding.
Muse Spark 1.3 API
Run a request to see the response
Use it in your code
Billed at $0.10 input / $0.00 cached input / $0.20 output per 1M tokens through the LLM Stats gateway.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://gateway.llm-stats.com/v1"
)
response = client.chat.completions.create(
model="muse-spark-1.3",
messages=[
{"role": "user", "content": "What is machine learning?"}
]
)
print(response.choices[0].message.content)Need an API key? Create one above in the playground, or read the API documentation.
Muse Spark 1.3 latency
Muse Spark 1.3 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Provider operational metrics
Time to first token, output throughput, and failed-request rate from live API traffic
Muse Spark 1.3 examples
Recent arena outputs from Muse Spark 1.3, picked from the highest-ranked matchups.
Muse Spark 1.3 license
Muse Spark 1.3 is a proprietary model available under its provider's product and API terms.
- License
- Proprietary
- Hosted access
Proprietary license - usage restrictions apply
Muse Spark 1.3 resources
Official sources for Muse Spark 1.3: api documentation, official playground, paper or system card, official launch post.
Muse Spark 1.3 vs other models
The most-compared alternatives to Muse Spark 1.3 are Qwen3.8 Max, Kimi K3, GLM-5.3-Flash. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Muse Spark 1.3
Models ranked just above and below Muse Spark 1.3 by LLM Stats score.
FAQ
Common questions about Muse Spark 1.3.