Meta Muse Spark 1.3
70 +
Percs
Long context
About
Meta's Muse Spark 1.3: multimodal reasoning model tuned for longer-horizon agentic, multi-agent and coding workflows, ~20% fewer tool calls than 1.2. Omni-modal input (text, image, video, audio, files), 1M-token context. Served via OpenRouter.
Available controls: Response length, Temperature, Diversity control, Context length, Reasoning effort.
Settings
Response length- The maximum number of tokens to generate in the output.
Temperature- The temperature of the model. Higher values make the model more creative and lower values make it more focused.
Diversity control- Top_p. Filters AI responses based on probability.
Context length- The maximum number of tokens to use as input for a model.
Reasoning effort- How much reasoning the model does before answering. Reasoning is mandatory for this model. Higher values improve hard tasks but cost more output tokens and time.