Authors can use Sudowrite without ever changing the default settings, but it's still helpful to know that Sudowrite does offer a variety of Prose Modes and AI models to suit different purposes.

Prose Modes are AI model suites specific to Sudowrite, designed specifically for fiction writing. These modes let you experience different output styles at varying costs, each offering unique balances of creativity, control, content filtering, and credit usage. We'll dive in below on the Prose Modes and AI models available on Sudowrite.

Muse is Sudowrite's flagship proprietary model, purpose-built just for fiction. It was trained by writers for writers, unlike general AI models that try to "do everything." This focus allows Muse to achieve a higher level of story quality and nuance.

Prose Quality & Style: Muse delivers vivid, original prose with a strong creative voice, free from common AI clichés. Excels at rich descriptions, emotional beats, and maintaining consistent tone throughout your story.

Instruction Following: Prioritizes creative interpretation over strict obedience. Continues your story in imaginative ways while still incorporating Story Bible context and outline scenes effectively for narrative continuity.

Content Filter Level: Virtually none. Handles any content from dark and gritty to light and humorous, including graphic or mature themes that other AIs might refuse. Use discretion, but know Muse won't shy away from adult content.

Credit Usage: Higher credit cost than Basic mode (comparable to former "Premium" setting). Many authors find the quality worth the expense, though consider switching to cheaper models for brainstorming or extremely long outputs.

Best Use Cases: Ideal for high-quality fiction prose, especially creative, character-driven writing. Excels in impactful scenes, character interactions, and climactic moments. Perfect for unfiltered content including mature themes. Outputs often require less editing than other models.

Weaknesses: Not optimized for non-fiction or highly structured tasks. Definitely voice-y, and perhaps not to everyone's taste. May occasionally produce unexpectedly edgy content. Available exclusively within Sudowrite's ecosystem.

Excellent utilizes Anthropic's Claude 3.7 Sonnet model as its primary engine. This mode is named "Excellent" because it aims for an excellent balance between creative prose and obedience to your instructions.

Prose Quality: Produces well-structured, descriptive writing with a flair for action and character movement. While not as stylistically unique as Muse, delivers engaging narrative that typically needs minimal polishing.

Instruction Following: Excellent's standout feature. Claude follows complex instructions precisely while maintaining context. Adheres closely to outlines and scenes while still expanding them creatively. Reliable for both storytelling and non-prose tasks like summarizing or brainstorming.

Content Filter Level: Moderate. More permissive than OpenAI models regarding violence and mild adult content, but has boundaries. May imply rather than explicitly describe adult situations or graphic content. Handles typical novel scenes well but might gloss over extremely explicit content.

Credit Usage: Mid-tier cost—more expensive than Basic but cheaper than Muse. Efficiently provides substantial output without rapidly depleting credits, making it ideal for budget-conscious writers who still want quality.

Best Use Cases: Perfect for general drafting and rewriting with balanced creativity and reliability. Excels with dialogue-heavy scenes, structured narratives, and when following outlines closely. Ideal for co-writing projects where story beats and world-building details must be respected. Works well for instruction-heavy tasks in plugins.

Weaknesses: Prose can feel less distinctive than Muse, sometimes "safer" or generic with minimal guidance. May faithfully reproduce errors in your outline or scenes. Might not deliver the intensity needed for certain scenes in your first attempt, due to its caution with mature content.

Basic uses the lightweight and economical GPT-4o Mini as its backbone. This mode is all about speed and efficiency, giving you decent writing while stretching your credit budget. Don't let the name "Basic" mislead you – it's quite powerful, just tuned for cost-effectiveness.

Prose Quality: Delivers coherent, straightforward content that serves as solid first-draft material. Provides clear descriptions without poetic flourishes (e.g., "small and dimly lit room" vs. "bathed in faint flickering light"). Still remarkably competent for its size—better than older GPT-3.5 models with fewer errors, if less original.

Instruction Following: Highly obedient and literal, following scenes and instructions closely. Stays on track without introducing unexpected plot elements. Limited "story sense" compared to larger models—won't infer beyond what's explicitly prompted, which can lead to generic output if guidance is minimal.

Content Filter Level: Strict, inheriting OpenAI's content moderation. Avoids explicit sexual content and extreme violence, often skipping or neutralizing such elements. Adequate for mainstream fiction but may refuse or severely water down mature content in erotica or intense horror.

Credit Usage: Exceptionally credit-efficient—Basic's standout feature. Generates substantial text at minimal cost, making it ideal for limited budgets or massive projects. Perfect for exploratory writing, generating multiple scene versions, or any high-volume text needs.

Best Use Cases: Excels at speed-writing, brainstorming, quick drafting, and plot development. Ideal for connective scenes, experimentation, and utility tasks (summarizing, listing ideas). A dependable workhorse for getting words on the page efficiently.

Weaknesses: Lacks sophisticated elements like metaphors or emotional subtext. Complex or character-rich scenes may feel flat. May fall back on clichés or tropes. Best used for basics with plans to enhance later.

Sudowrite's Experimental selector offers AI models beyond the main Prose Modes. These provide granular control for specific chapters or specialized plugin tasks. Keep in mind these models haven't been extensively optimized for Sudowrite's specific fiction-writing workflows, but you may find their unique voices and capabilities suit your needs.

Anthropic's Claude models are known for knowledgeable, thoughtful writing with large context windows, making them excellent for novelists who feed substantial story context. The Claude family on Sudowrite now spans multiple generations.

The Claude 4 generation introduced hybrid reasoning capabilities, allowing models to switch between fast responses and extended thinking modes.

Prose Quality: Claude 4 models produce polished, coherent prose with strong narrative flow. Sonnet 4.5 in particular is praised for following instructions precisely while maintaining creative flair—it picks up on your writing style and keeps quirks intact rather than smoothing everything into generic prose. Opus variants offer richer detail and deeper world-feel, though at higher cost.

Instruction Following: Exceptional across the Claude 4 family. These models excel at adhering to complex outlines, maintaining character consistency, and respecting story constraints. Sonnet 4.5 rewards specific prompting—give it clear examples and direction, and it will match your voice closely.

Content Filter Level: Moderate. More permissive than OpenAI models but maintains boundaries. Claude 4 models handle typical novel content well, including violence and mature themes, though they may soften extremely explicit scenes.

Credit Usage: Varies by tier. Haiku 4.5 is the most economical option for everyday tasks. Sonnet 4.5 offers strong value as the balanced workhorse. Opus variants (4, 4.1, 4.5) are premium-priced—reserve them for complex scenes requiring maximum intelligence and nuance.

Best Use Cases:

Weaknesses: Can occasionally be wordy—Sonnet 4.5 sometimes doubles word counts during rewrites. Watch for AI-isms like em-dash overuse. Opus variants are slow and expensive, best reserved for critical work.

The previous Claude generation remains available and still performs admirably for many tasks. Claude 3.7 Sonnet powers the Excellent Prose Mode and offers a proven balance of quality and economy. The Haiku variants are fast and affordable options for quick drafts or iterative work.

OpenAI's model families offer different balances of capability, speed, and cost. These models are known for factual accuracy, logical coherence, and strong instruction-following.

OpenAI's 2025 flagship family represents their most advanced offering.

Prose Quality: GPT-5 Full excels at generating high-quality dialogue and mimicking your writing style—authors report it's particularly strong at matching fragmented, punchy voices. However, it tends toward dialogue-heavy output with less descriptive prose, which can be an asset or limitation depending on your style. Produces imaginative, detailed prose for storytelling and world-building.

Instruction Following: Strong, with improved ability to maintain narrative consistency across long passages. GPT-5's massive context window supports extended narratives without losing track of earlier details. The model benefits from clear, specific prompting.

Content Filter Level: Strict. Inherits OpenAI's content policies, though somewhat relaxed within Sudowrite. May avoid or soften explicit content.

Credit Usage:

Best Use Cases:

Weaknesses: GPT-5 can try to "take over" stories rather than collaboratively continue them—it sometimes veers off-plot toward its own conclusions. Nano performs poorly for actual prose writing. The model may feel "clean" but lacks the raw creative spark some authors prefer.

A strong mid-tier option with excellent instruction-following and a massive one-million-token context window.

Prose Quality: Produces precise, grammatically polished text. GPT-4.1 follows intricate instructions well from the first draft, making it valuable for authors who need tight adherence to complex plot details. Tone can feel somewhat formal.

Instruction Following: Standout capability. Superior at following complex, multi-part instructions and maintaining story continuity across very long narratives.

Credit Usage:

Best Use Cases: Detailed long-form writing, maintaining continuity in series, scenes requiring precise adherence to outlines.

Weaknesses: Prose can feel "academic" without stylistic guidance. Responds well to tone direction, so provide clear examples.

The established workhorse of the OpenAI lineup.

Prose Quality: Versatile, producing vivid sensory-rich descriptions and detailed settings. Particularly strong for structured tasks and maintaining consistency. GPT-4o Mini delivers impressive quality at low cost.

Best Use Cases: General drafting, plugins, scenes requiring precision, consistency checks.

Google's Gemini models have emerged as strong contenders, particularly excelling at long-context understanding and deep reasoning.

Google's latest generation, released November 2025.

Prose Quality: Gemini 3 Pro produces smart, concise, direct responses—less prone to AI clichés and flattery than predecessors. Prose feels cleaner and more measured. Flash prioritizes speed while maintaining reasonable quality.

Instruction Following: Strong reasoning capabilities. Gemini 3 Pro handles complex problems with depth and nuance, grasping context and intent with less prompting needed. Flash is more straightforward but reliable.

Content Filter Level: Variable. Generally cautious with mature content, though users report it's less preachy than some alternatives.

Credit Usage:

Best Use Cases:

Weaknesses: Creative writing can feel "safe" compared to models specifically tuned for fiction. Better for scaffolding than polished final prose.

Previous generation, still available and praised for creative writing. Gemini 2.5 Pro developed a following for its handling of nuanced creative tasks and emotional depth. Flash Thinking adds deliberate reasoning for complex tasks.

DeepSeek offers cost-effective alternatives with strong reasoning capabilities, appealing for budget-conscious authors or high-volume work.

Prose Quality: Competent, "serviceable" prose with solid grammar and basic creativity. Functions as a stylistic blank canvas you can shape. V3.1 represents iterative improvements over V3.

Credit Usage: Among Sudowrite's most credit-efficient options—even cheaper than GPT-4o Mini.

Best Use Cases: Quick brainstorming, rough drafts on tight budgets, generating large volumes of content for later enhancement. Output may need polishing but Quick Edit handles most issues.

Weaknesses: Occasionally awkward phrasing. Lacks sophisticated stylistic elements.

Prose Quality: Specializes in reasoning power with an internal "thinking" phase before writing. Produces coherent, logically consistent output.

Best Use Cases: Complex narrative problems, convoluted plots, mysteries requiring many clues to track, maintaining character consistency across intricate scenarios.

Weaknesses: The reasoning focus doesn't always translate to beautiful prose—strong on logic, less so on lyrical quality.

xAI's model offers unique personality and strong emotional intelligence.

Prose Quality: Grok 4 can feel surprisingly human and empathetic in conversation. Strong at brainstorming, world-building, and maintaining logical consistency across complex scenarios. However, base prose generation tends toward the literal and robotic—several users describe it as "terrible at creative writing" without careful prompting.

Instruction Following: Good for structured tasks. Benefits from prompting that frames creative tasks as system-building rather than pure storytelling.

Content Filter Level: More permissive, with a "rebellious" personality that can generate unexpected ideas.

Best Use Cases: Pre-writing tasks (outlining, character development, world-building), research assistance for historical fiction, brainstorming unconventional ideas. Better as a planning partner than a prose generator.

Weaknesses: Prose is often flat and literal. May produce unintentionally humorous results when instructions are taken too literally. Use other models for actual scene writing.

Moonshot AI's model features massive scale (1 trillion parameters) with strong reasoning and extended context capabilities.

Prose Quality: Mixed reports. Kimi K2 topped benchmarks for creative writing and emotional intelligence, producing prose some describe as "high-literary" and character-bound. However, others find it weaker for actual fiction prose over longer passages—excellent at reasoning doesn't always mean excellent at beautiful sentences.

Instruction Following: Strong long-context memory. Can process enormous documents without forgetting earlier details.

Content Filter Level: Variable—API and web interfaces may behave differently.

Best Use Cases: Complex plot tracking, manuscript analysis, scenarios requiring extensive context retention, experimental work. May excel at generating thought-provoking literary work with thematic depth.

Weaknesses: Can "overthink" on simple tasks. Some users find prose quality inconsistent, particularly over 3,000+ words. Better for reasoning-heavy work than pure prose generation.

Open-source model offering enterprise-grade capabilities with high instruction obedience.

Prose Quality: Clear, well-structured prose that follows constraints precisely. Excels at argumentative essays, explainers, and technical writing. Creative fiction can feel procedural and "safe"—less inventive than models tuned specifically for storytelling.

Instruction Following: Exceptional. Among the most obedient models for executing precise, constraint-based outputs.

Best Use Cases: Structured content, technical writing within fiction (in-world documents, etc.), SEO-style content, tasks requiring tight format control. Works well for first drafts that you'll polish with a more creative model.

Weaknesses: Fiction prose lacks emotional nuance. Not the best choice for lyrical or character-driven scenes. Consider pairing with Claude for creative passes.

Choosing the right AI model in Sudowrite significantly impacts your writing experience. For most fiction writers, start with the main Prose Modes:

As you grow comfortable with the platform, explore Experimental models for specific needs:

Remember that these models serve as collaborators, not replacements. Your voice, editing skill, and creative vision remain irreplaceable. The key is matching the right model to each specific task:

By understanding each model's strengths and limitations, you can transform Sudowrite into a personalized writing partner that adapts to different phases of your creative process. Happy writing!