Background

Updated on May 15, 2026

Scopes of Data

Scope of data decides which saved context is used for a chat. Every message you send is routed into either global scope or project scope, and that choice determines which memories and files the system can see. This keeps everyday chats, project chats, and persona chats cleanly separated so replies stay relevant and nothing leaks across boundaries you didn't intend.

Understanding scopes helps you organize your work: put sensitive or project-specific context in a project, keep general preferences in global, and use personas when you want consistent voice across both without merging the underlying data.

Global

Global scope is used when you chat outside any project. It draws from your account-level memories and account-level files—the context you've chosen to share across all everyday conversations.

Global scope does not pull in project-only details. If you have a project for work notes or a side venture, those memories and files stay out of your regular chats. This helps keep everyday conversations separate from focused project work, so you can switch contexts without worrying about cross-talk.

Project

Project scope is used when you chat inside a specific project. It uses that project's memories and files only—nothing from other projects or from your global account.

Each project stays isolated. Details from one project do not spill into other projects or into regular global chats. That isolation is intentional: you can have a project for a client, another for personal research, and another for a hobby, and each one keeps its own context clean.

Persona

Persona is a style layer that can be used in both global and project chats. It keeps voice, tone, and behavior consistent across spaces without merging the underlying memory or file stores.

Persona can travel across chats, while global and project memory spaces remain separate. You get continuity in tone—the same personality whether you're in a global chat or a project chat—without mixing private context. It's the best of both: consistent voice, strict data boundaries.

Files

Files follow the same scope rules as memories. Global files are available in global chats; project files are available only when you're chatting inside that project. There is no shared file pool that crosses scope boundaries.

Upload files where they belong: account-level docs for everyday use, project-specific docs inside the project. The system retrieves only the files that match the current scope when you send a message.

Customization And Scope Interaction

Customization settings are account-level and can be managed from Account in the Customization and Memories sections. The same options are also available in the chat account modal.

In regular chats, customization settings guide reply style—how the assistant structures responses, how formal or casual it sounds, and other preferences. When a persona is active, persona guidance takes priority so tone stays consistent for that persona across every chat.

Global chats continue to use global memory space, and project chats continue to use project memory space. Persona can move across both without merging those spaces. You get a single, coherent voice without blurring the lines between work and personal context.

Models

Model providers have different strengths. Use the summaries below to choose a provider, then pick a model family that matches the task.

OpenAI logo

OpenAI (GPT)

Strong all-around for writing, planning, coding, and everyday questions. Includes GPT models from OpenAI plus GPT OSS variants served through Fireworks and Cerebras.

GPT-4o series
ModelRequestsBest For
GPT-4o · May 20242 premium requestsMay 2024 checkpoint of gpt-4o for that special voice.
GPT-4o · Aug. 20241 premium requestAugust 2024 checkpoint of gpt-4o with enhanced capabilities.
GPT-4o · Nov. 20241 premium requestNovember 2024 checkpoint of gpt-4o with latest improvements.
GPT-4o1 premium requestOpenAI's default gpt-4o through API.
GPT-4o mini1 base requestAgile, cost-efficient 4o variant ideal for everyday conversation.
GPT-3.5 Turbo
ModelRequestsBest For
GPT-3.5 Turbo1 base requestLegacy GPT model for cheaper chat and non-chat tasks.
GPT-3.5 Turbo · 01251 base requestPinned January 2024 snapshot of GPT-3.5 Turbo.
GPT-3.5 Turbo · 11061 base requestPinned November 2023 snapshot of GPT-3.5 Turbo.
GPT-audio series
ModelRequestsBest For
GPT audio mini2 base requestsCost-efficient audio-native chat model. Supports text + audio output in chat completions.
GPT audio mini · Oct. 20252 base requestsPinned October 2025 snapshot of GPT Audio mini for stable behavior.
GPT audio mini · Dec. 20252 base requestsPinned December 2025 snapshot of GPT Audio mini for stable behavior.
GPT-5.4 series
ModelRequestsBest For
GPT-5.42 premium requestsLatest GPT-5.4 flagship chat model with stronger reasoning and accuracy.
GPT-5.4 mini1 premium requestHigher-capability GPT-5.4 mini for high-volume coding, computer use, and subagent workflows.
GPT-5.4 nano1 base requestCheapest GPT-5.4-class model for simple high-volume tasks such as extraction, ranking, and lightweight subagents.
GPT-5.3 series
ModelRequestsBest For
GPT-5.3-Codex1 premium requestThe most capable agentic coding model to date. Optimized for agentic coding tasks in Codex or similar environments. 400K context, 128K max output. Reasoning off by default.
GPT-5.3 latest1 premium requestGPT-5.3 model used in ChatGPT. Best general-purpose model with high intelligence and vision support. Pricing assumed same as 5.2/5.1 chat latest until announced.
GPT-5.2 series
ModelRequestsBest For
GPT-5.2 latest1 premium requestGPT-5.2 model used in ChatGPT. Best general-purpose model with high intelligence and vision support.
GPT-5.21 premium requestPinned GPT-5.2 snapshot for stable behavior.
GPT-5.1 series
ModelRequestsBest For
GPT-5.11 premium requestPinned snapshot gpt-5.1-2025-11-13. The most intelligent model yet, with faster responses and increased steerability.
GPT-5.1 latest1 premium requestGPT-5.1 model used in ChatGPT. Continuously updated for the latest chat improvements.
GPT-5.1 codex1 premium requestGPT-5.1 optimized for agentic coding in Codex. 400K context, 128K max output.
GPT-5.1 codex mini1 base requestSmaller, more cost-effective, less-capable version of GPT-5.1-Codex. 400K context, 128K max output.
GPT-5 series
ModelRequestsBest For
GPT-51 premium requestFrontier reasoning depth with best-in-class reliability.
GPT-5 codex1 premium requestEnhanced code reasoning while staying conversation-friendly.
GPT-5 latest1 premium requestContinuously tuned GPT-5 chat experience with the latest guardrails.
GPT-5 mini1 base requestResponsive, budget-friendly member of the GPT-5 family.
GPT-5 nano1 base requestUltra light-touch assistant for simple interactions.
GPT-4.1 series
ModelRequestsBest For
GPT-4.11 premium requestGPT-4 refinement designed for coding with broad tool compatibility.
GPT-4.1 mini1 base requestCompact GPT-4.1 option for consistent tone and speed.
GPT-4.1 nano1 base requestMinimal footprint 4.1 for background automation tasks.
O-series
ModelRequestsBest For
o31 premium requestReasoning-focused o-series model optimized for long horizon tasks.
o4 mini1 premium requestLean o-series model for high volume creative projects.
o3 mini1 premium requestBalanced o-series variant with emphasis on tool use during reasoning.
GPT-oss series
ModelRequestsBest For
GPT OSS 120b1 base requestOpenAI's open-weight 117B MoE via Fireworks. Production-grade reasoning, agentic tasks, function calling. 131k context. Does not support web search or image input.
GPT OSS 120B Fast1 premium requestOpenAI's GPT OSS 120B routed through Cerebras chat completions for very fast tool-capable replies. 131k context. Does not support web search or image input.
GPT OSS 20b1 base requestOpenAI's open-weight 21B MoE via Fireworks. Lower latency, local or specialized use-cases. 131k context. Does not support web search, image input, or function calling.
Google Gemini logo

Google (Gemini)

Great for long instructions, large context, and quick iteration on bigger tasks.

Gemini 2.5 series
ModelRequestsBest For
Gemini 2.5 Pro1 premium requeststate-of-the-art multipurpose model, which excels at coding and complex reasoning tasks.
Gemini 2.5 Flash1 base requestfirst hybrid reasoning model which supports a 1M token context window and has thinking budgets.
Gemini 2.5 Flash-Lite1 base requestsmallest and most cost effective model, built for at scale usage.
Gemini 3.1 series
ModelRequestsBest For
Gemini 3.1 Pro Preview3 premium requestsNext iteration of Gemini 3 Pro: performance, behavior, and intelligence improvements. 1M/64k context. Agentic workflows, autonomous coding, complex multimodal. Jan 2025.
Gemini 3.1 Flash-Lite Preview1 base requestMost cost-efficient Gemini 3.1 model for high-volume agentic tasks, translation, and simple data processing. 1M/65k context. Preview; may have stricter rate limits.
Gemini 3 series
ModelRequestsBest For
Gemini 3 Flash Preview1 base requestPreview of Gemini 3 Flash. 1M/64k context. Jan 2025.
Anthropic Claude logo

Anthropic (Claude)

Good for careful writing, nuanced edits, and thoughtful longer responses.

Claude series
ModelRequestsBest For
Claude Opus 4.65 premium requestsAnthropic's most advanced Claude model. Exceptional emotional intelligence and warmth paired with adaptive thinking that scales to the complexity of your request.
Claude Opus 4.55 premium requestsPrevious flagship Claude with strong reasoning capabilities. Great balance of intelligence and accessibility.
Claude Sonnet 4.65 premium requestsAnthropic's most capable Sonnet yet. Full upgrade across coding, long-context reasoning, agent planning, and design. 1M token context window in beta. Same pricing as Sonnet 4.5.
Claude Sonnet 4.55 premium requestsAnthropic's balanced Claude model with strong reasoning and efficiency.
Claude Haiku 4.51 premium requestAnthropic's fastest Claude model, optimized for speed and cost efficiency.
Grok logo

xAI (Grok)

Good for quick back-and-forth, practical answers, and fast drafting.

Grok-3
ModelRequestsBest For
Grok-3 Mini1 base requestCompact Grok-3 variant for cost-effective conversations.
Grok-4.20
ModelRequestsBest For
Grok-4.20 Reasoning1 premium requestxAI's flagship Grok 4.20 reasoning model with a 2M-token context window, stronger multi-step reasoning, and native tool support.
Grok-4.20 Non-Reasoning1 premium requestLatency-optimized Grok 4.20 variant with a 2M-token context window, image understanding, and native tool support.
Grok-4.3
ModelRequestsBest For
Grok 4.31 premium requestxAI's latest flagship Grok model with 1M context, image input, configurable reasoning, and strong agentic tool use.
DeepSeek logo

DeepSeek

Strong for reasoning and complex tasks. DeepSeek v3.x models are available on all tiers; DeepSeek V4 Pro is Premium with 1M context and function calling. No web search or images.

DeepSeek
ModelRequestsBest For
DeepSeek V4 Pro1 premium requestDeepSeek-V4-Pro via Fireworks: flagship open-source 1.6T MoE model for frontier reasoning, advanced coding, and long-context agentic workflows. 1M context. Function calling supported. Uses 1 premium request per send before length multipliers. Does not support web search or image input.
Qwen logo

Qwen

Strong for multimodal chat, tool use, and general flagship work. Available on all tiers through Fireworks serverless. Supports image input, but not web search.

Qwen
ModelRequestsBest For
Qwen 3.6 Plus2 base requestsAlibaba's flagship closed Qwen model via Fireworks. 396B MoE with function calling and image input support. Available serverless on just4o.chat at the base tier. Uses 2 base requests per send before length multipliers. Does not support web search.
Moonshot AI logo

Moonshot (Kimi)

Good for complex reasoning, multimodal agentic tasks, and long-horizon coding. Kimi K2.5 and K2.6 support images. No web search.

Kimi
ModelRequestsBest For
Kimi K2.51 premium requestMoonshot AI's flagship agentic model via Fireworks. Unifies vision and text, thinking and non-thinking. 262k context. Supports image input. Does not support web search.
Kimi K2.62 premium requestsMoonshot AI's Kimi K2.6 via Fireworks: open-source, native multimodal agentic model for long-horizon coding, coding-driven design, autonomous execution, and task orchestration. 1T MoE, 262k context. Supports image input and function calling. Uses 2 premium requests per send before length multipliers. Does not support web search.
MiniMax logo

MiniMax

Strong for coding, complex tasks, and office work. MiniMax M2.7 supports image input. Available on all tiers. No web search.

MiniMax
ModelRequestsBest For
MiniMax M2.51 base requestMiniMax M2.5 via Fireworks: state-of-the-art coding, agentic tool use, search, and office work. 228B MoE, 196k context. Function calling supported. Does not support web search or image input.
MiniMax M2.71 base requestMiniMax M2.7 via Fireworks: 228B MoE model for complex agent harnesses, productivity tasks, Agent Teams, Skills, and dynamic tool search. 196k context. Supports image input and function calling. Does not support web search.
Z.ai logo

Z.ai (GLM)

Strong for coding, reasoning, and long-horizon agentic workflows. GLM models are available through Fireworks and Cerebras; GLM 4.7 Fast is the Cerebras-backed Premium OSS variant. No web search or images.

GLM 4.7 family
ModelRequestsBest For
GLM 4.7 Fast2 premium requestsZ.ai's GLM-4.7 routed through Cerebras chat completions for lower-latency coding and agentic work. 131k context. Does not support web search or image input. Cerebras currently lists it as a preview model.
GLM 5 family
ModelRequestsBest For
GLM 5.12 premium requestsZ.ai's GLM-5.1 via Fireworks: next-generation flagship for agentic engineering, stronger coding, and sustained long-horizon task performance. 202k context. Uses 2 premium requests per send before length multipliers. Does not support web search, image input, or function calling.